ICEIS 2023 Abstracts

Area 1 - Databases and Information Systems Integration
Full Papers Short Papers
Area 2 - Artificial Intelligence and Decision Support Systems
Full Papers Short Papers
Area 3 - Information Systems Analysis and Specification
Full Papers Short Papers
Area 4 - Software Agents and Internet Computing
Full Papers Short Papers
Area 5 - Human-Computer Interaction
Full Papers Short Papers
Area 6 - Enterprise Architecture
Full Papers Short Papers

Area 1 - Databases and Information Systems Integration

Full Papers
Paper Nr: 34
Title:

Adoption of Intelligent Information Systems: An Approach to the Colombian Context
Authors:

Sofía Abadía and Oscar Avila
Abstract: Enterprise Information Systems (EIS) are widely used to support operational and tactical processes of companies and have begun, in recent years, to be used at the strategic level to support decision-making processes. To do so, new systems, known as intelligent EIS, integrate data analytics modules to provide the necessary information and reports to make informed decisions. There are certain influencing factors for the adoption of such systems, however, from a first analysis of the academic literature, it was found that research works in the domain are very scarce and even more, there are no research works on the subject in Colombia. Consequently, this article aims at identifying the relevant factors for the adoption of intelligent EIS based on an analysis of the academic literature, and then structuring a focus group activity with 5 experts on the subject to obtain a first approach to the adoption of this kind of systems for the Colombian context. As a preliminary result, we found that in the Colombian industry the most important influencing factors include cost and IT capabilities which differs from main factors identified in the revision of the international scholar literature.
Download
Paper Nr: 35
Title:

Indexing High-Dimensional Vector Streams
Authors:

João V. Pinheiro, Lucas R. Borges, Bruno F. Martins da Silva, Luiz P. Leme and Marco A. Casanova
Abstract: This paper addresses the vector stream similarity search problem, defined as: “Given a (high-dimensional) vector q and a time interval T, find a ranked list of vectors, retrieved from a vector stream, that are similar to q and that were received in the time interval T.” The paper first introduces a family of methods, called staged vector stream similarity search methods, or briefly SVS methods, to help solve this problem. SVS methods are continuous in the sense that they do not depend on having the full set of vectors available beforehand, but adapt to the vector stream. The paper then presents experiments to assess the performance of two SVS methods, one based on product quantization, called staged IVFADC, and another based on Hierarchical Navigable Small World graphs, called staged HNSW. The experiments with staged IVFADC use well-known image datasets, while those with staged HNSW use real data. The paper concludes with a brief description of a proof-of-concept implementation of a classified ad retrieval tool that uses staged HNSW.
Download
Paper Nr: 72
Title:

Assessing the Lakehouse: Analysis, Requirements and Definition
Authors:

Jan Schneider, Christoph Gröger, Arnold Lutsch, Holger Schwarz and Bernhard Mitschang
Abstract: The digital transformation opens new opportunities for enterprises to optimize their business processes by applying data-driven analysis techniques. For storing and organizing the required huge amounts of data, different types of data platforms have been employed in the past, with data warehouses and data lakes being the most prominent ones. Since they possess rather contrary characteristics and address different types of analytics, companies typically utilize both of them, leading to complex architectures with replicated data and slow analytical processes. To counter these issues, vendors have recently been making efforts to break the boundaries and to combine features of both worlds into integrated data platforms. Such systems are commonly called lakehouses and promise to simplify enterprise analytics architectures by serving all kinds of analytical workloads from a single platform. However, it remains unclear how lakehouses can be characterized, since existing definitions focus almost arbitrarily on individual architectural or functional aspects and are often driven by marketing. In this paper, we assess prevalent definitions for lakehouses and finally propose a new definition, from which several technical requirements for lakehouses are derived. We apply these requirements to several popular data management tools, such as Delta Lake, Snowflake and Dremio in order to evaluate whether they enable the construction of lakehouses.
Download
Paper Nr: 74
Title:

Design Principles and a Software Reference Architecture for Big Data Question Answering Systems
Authors:

Leonardo P. Moraes, Pedro C. Jardim and Cristina D. Aguiar
Abstract: Companies continuously produce several documents containing valuable information for users. However, querying these documents is challenging, mainly because of the heterogeneity and volume of documents available. In this work, we investigate the challenge of developing a Big Data Question Answering system, i.e., a system that provides a unified, reliable, and accurate way to query documents through naturally asked questions. We define a set of design principles and introduce BigQA, the first software reference architecture to meet these design principles. The architecture consists of high-level layers and is independent of programming language, technology, querying and answering algorithms. BigQA was validated through a pharmaceutical case study managing over 18k documents from Wikipedia articles and FAQ about Coronavirus. The results demonstrated the applicability of BigQA to real-world applications. In addition, we conducted 27 experiments on three open-domain datasets and compared the recall results of the well-established BM25, TF-IDF, and Dense Passage Retriever algorithms to find the most appropriate generic querying algorithm. According to the experiments, BM25 provided the highest overall performance.
Download
Paper Nr: 129
Title:

Perception of Agile Teams About Home Office During the Covid-19
Authors:

Edna D. Canedo, Angelica S. Calazans, Geovana S. Silva, Isabel S. Brito and Eloisa S. Masson
Abstract: Due to the COVID-19 pandemic, there was a massive migration from working in the office to working from home (WFH) and the software development teams had to adapt to the new reality. This paper focused on how the agile teams dealt with the challenges of WFH and how this affected the software development process. To capture the perceptions of the agile teams, we carried out a survey that investigated the following aspects of WFH: work routine, collaboration, communication, productivity, transparency, challenges, and the software development process itself. The survey received 127 valid responses from agile team members and the results revealed that i) most of the members of agile teams considered the work continued as usual regardless of the place (office or remote); ii) 80% of members of agile teams mentioned an increase in productivity during WFH; iii) 85% of participants are using Scrum as management strategy; iv) communication between teams members during the remote working model was perceived as more effective; v) Microsoft Teams and Google Meets were the most used interactions tools by members of agile teams.
Download
Paper Nr: 172
Title:

Algorithm for Selecting Words to Compose Phonological Assessments
Authors:

João B. Marques, João D. Lima, Márcia Keske-Soares, Cristiano C. Rocha, Fabrício A. Rubin and Raphael V. Miollo
Abstract: The phonological assessment is one of the main resources that speech-language therapist has to identify phonological disorders in children. For this, it is necessary to be composed of a words set that have a variety of phonemes in different positions of the syllable and the word, in order to obtain a representative sample of the phonological system. Thus, the present work aimed to analyze a set of 84 words from a phonological assessment instrument, with the objective of identifying and removing words with over-represented phonemes. Aiming to facilitate the phonological evaluation by making it more succinct with the reduction of the number of words, the present work describes a judicious method organized in three steps, which was implemented in Javascript and obtained a subset of 55 words, which have at least two occurrences of the same phonemes in the proper positions in which they appeared in the initial set, representing a 35% reduction in the number of words without losing quality.
Download
Short Papers
Paper Nr: 42
Title:

Problems and Causes of Data Privacy in Big Data Systems in Brazil
Authors:

Danilo F. Oliveira and Edmir V. Prado
Abstract: User interactions with computerized systems have led to ethical dilemmas in data use, such as privacy violations. Occasionally, organizations’ interests may conflict with the users’ privacy interests. Ethical dilemmas arise from this conflict. Furthermore, there is no consensus between organizations and users on the ethical use of data. It is difficult to achieve data privacy in Information Systems that use Big Data Analytics (ISBDA). On the order hand, there is not enough research in the literature on data privacy issues in ISBDA. This study aims to analyze data privacy problems in ISBDA, and their causes, in the Brazilian context. We conducted a systematic literature review to find data privacy problems and their causes. This is exploratory research performed with 16 experts in data privacy and ISBDA, using the Delphi technique for data collection. We identified nine data privacy problems which have seven causes. The research contributed to managerial and organizational practices by associating data privacy problems and their causes.
Download
Paper Nr: 43
Title:

Probability Distribution as an Input to Machine Learning Tasks
Authors:

Karel Macek, Nicholas Čapek and Nikola Pajerová
Abstract: Machine Learning has been working with various inputs, including multimedia or graphs. Some practical applications motivate using unordered sets considered to be samples from a probability distribution. These sets might be significant in size and not fixed in length. Standard sequence models do not seem appropriate since the order does not play any role. The present work examines four alternative transformations of these inputs into fixed-length vectors. This paper demonstrates the approach in two case studies. In the first one, pairs of scans as coming from the same document based were classified on the distribution of lengths between the reference points. In the second one, the person’s age based on the distribution of D1 characteristics of the 3D scan of their hip bones was predicted.
Download
Paper Nr: 49
Title:

A Multidimensional-Paradigm-Centered Architecture for Cooperative Digital Ecosystems
Authors:

Alfredo Cuzzocrea and Luigi Canadè
Abstract: Cooperative Digital Ecosystems are an emerging class of information systems where the main goal is that of supporting cooperation in human activities, driven by ICT technologies. Inspired by this main area, in this paper we provide the anatomy and definitions of a multidimensional-paradigm-centered architecture for supporting Cooperative Digital Ecosystems.
Download
Paper Nr: 52
Title:

Novel Topic Models for Content Based Recommender Systems
Authors:

Kamal Maanicshah, Manar Amayri and Nizar Bouguila
Abstract: Content based recommender systems play a vital role in applications related to user suggestions. In this paper, we introduce novel topic models which help tackle the recommendation task. Being one of the prominent approaches in the field of natural language processing, topic models like latent Dirichlet allocation (LDA) try to identify patterns of topics across multiple documents. Due to the proven efficiency of generalized Dirichlet allocation and Beta-Liouville allocation in recent times, we use these models for better performance. In addition, since it is a known fact that co-occurences of words are commonplace in text documents, the models have been designed with this reality in mind. Our models follow a mixture based design to achieve better topic quality. We use variational inference for estimating the parameters. Our models are validated with two different datasets for recommendation tasks.
Download
Paper Nr: 127
Title:

IT Project Portfolio Management: Development and Validation of a Reference Model
Authors:

Ruud Wissenburg, Rob Kusters and Harry Martin
Abstract: IT Project Portfolio Management has been implemented in most organizations to effectively manage complex portfolios of IT projects and balance them with business strategy. Several standards for portfolio management have been published, but the scientific literature still lacks a theoretically grounded and practically validated reference model for analyzing the implementation of IT Project Portfolio Management in an organization. Therefore, this study designs and validates a reference model for systematically analyzing IT Project Portfolio Management design choices in an organization in terms of processes, roles, responsibilities, and authority. Organizations can use the reference model to systematically assess their local implementation of IT Project Portfolio Management and identify areas for improvement.
Download
Paper Nr: 162
Title:

FakeSpreadersWhatsApp.BR: Misinformation Spreaders Detection in Brazilian Portuguese WhatsApp Messages
Authors:

Lucas Cabral, Diogo Martins, José M. Monteiro, Javam Machado and Wellington Franco
Abstract: In the past few years, the large-scale dissemination of misinformation through social media has become a critical issue. In many developing countries such as Brazil, India, and Mexico, one of the primary sources of misinformation is the messaging application WhatsApp. Recently, a few methods for automatic misinforma- tion detection for the WhatsApp platform were proposed. On the other hand, identifying users who spread fake news is another key aspect of mitigating misinformation dissemination effectively. However, features to describe users on the WhatsApp platform were not found in the literature. This paper proposes a set of 23 features and two approaches (a supervised and another unsupervised) to identify possible misinformation spreaders on WhatsApp. Our results indicate that the proposed features can be used to distinguish between potential misinformation spreaders and users who share credible information with a F1 Score of 0.923.
Download
Paper Nr: 177
Title:

A Multi-Perspective Framework for Smart Contract Search in Decentralised Applications Design
Authors:

Ada Bagozi, Devis Bianchini, Valeria De Antonellis, Massimiliano Garda and Michele Melchiori
Abstract: With the advent of blockchain technology, many interorganisational collaborative processes that demand trust requirements (e.g., food supply chain, smart grid energy distribution and clinical trials) are being implemented as decentralised applications (DApps). Indeed, blockchain technology provides decentralised control and immutable transaction history, thereby improving security and accountability between parties. In this vision paper, we consider cooperative processes where a subject, which acts as a regulator of the process, promotes the use of blockchain for increasing transparency, while reducing the burden in controlling trustworthiness among participants. To the scope, the regulator provides a registry of basic smart contracts, including both actual deployed ones and code templates, that can be used and extended by the process stakeholders (e.g., retailers, energy providers, researchers) to build up DApps. The adoption of a blockchain and the definition of the registry favour the compliance with best practices and obligations demanded by the regulator, as well as that all relevant information and documents cannot be tampered. To support semantic-based smart contract search in the registry, we propose a multi-perspective framework that, in addition to classification and technical characteristics of smart contracts, takes into account the past experience of developers who have used smart contracts of the registry to develop DApps.
Download
Paper Nr: 189
Title:

BATMAN: A Big Data Platform for Misinformation Monitoring
Authors:

Ivandro Claudino, Luciano Galic, Wellington Franco, Thiago Gadelha, José M. Monteiro and Javam Machado
Abstract: The large-scale dissemination of misinformation through social media has become a critical issue, harming social stability, democracy, and public health. The WhatsApp instant messaging application is very popular in Brazil, with more than 165 million users. On the other hand, in just one year, the proportion of smartphones with Telegram installed grew in Brazil from 45% to 60% in 2022. If on one hand, these platforms offer security and privacy to its users, on other hand they are spaces with little or no moderation. Consequently,they have been used to spread misinformation. In this context, we present BATMAN, a Big Data Platform for Misinformation Monitoring, a real-time platform for finding, gathering, analyzing, and visualizing misinformation in social networks, in particular, in instant message applications such as WhatsApp and Telegram. To evaluate the proposed platform, we used it to build two different messages datasets, concerning the Brazilian general elections campaign in 2022, obtained from public chat groups on WhatsApp and Telegram, respectively.
Download
Paper Nr: 194
Title:

GeoBlockchain: Geolocation Based Consensus Against 51% Attacks
Authors:

Franco Moloche-Garcia, Pedro Bustamante-Castro and Willy Ugarte
Abstract: Currently, Blockchain technology has been involved in various areas such as medicine, environment, finance, mining, etc., therefore, the rise of technology causes an increasing use among technology companies, developers and even malicious attackers. The latter, through 51% attacks, could have the ability to manipulate a Blockchain network. The present proposal consists of a consensus algorithm for Blockchain networks based on Proof-of-work (PoW) that, through the use of geolocation, aims to provide protection against 51% attacks. With enough computational power on one of these Blockchain networks, an attacker could reverse transactions and identification might be impossible. It is the mining pools, which together, could have the capacity to carry out these attacks. Using geolocation, it is intended to minimize the probability of generating mining pools, making their formation unfavorable. In our experiments, the algorithm reduces the probability of 51% attacks by an average of 29% compared to PoW, providing a new layer of protection when generating consensus between participating Blockchain nodes.
Download
Paper Nr: 210
Title:

Building Resilient Supply Chains with Information Systems: Key Lessons from Médecins Sans Frontières Logistique During the COVID-19 Crisis
Authors:

Sylvie Michel, Sylvie Gerbaix and Marc Bidan
Abstract: This research aims to analyze the resilience of humanitarian supply chains, with a focus on the role of information systems, through a case study of Médecins Sans Frontières Logistique during the COVID-19 pandemic. The empirical research methodology is based on a qualitative study, which includes semi-structured interviews with key actors and operators from the Médecins Sans Frontières Logistique during the COVID-19 crisis in 2020 and 2021. The paper highlights the crucial and inherent role of information systems on each of the four dimensions of humanitarian supply chain resilience: reorganization capacity, collaboration, flexibility, and humanitarian culture. Drawing on recent theoretical works on supply chain resilience as well as empirical results, the paper underscores the importance of information systems and proposes a conceptual model of the relationship between humanitarian supply chain resilience and the role of information systems. The value of this research is linked to its empirical and qualitative study of a Non-Governmental Organization logistics operation during an international crisis, which contributes not only to the literature on resilience, but also provides guidance for managers to target their actions responsively and proactively to enhance resilience over time..
Download
Paper Nr: 6
Title:

An Exploratory Analysis of the Use of ETL in Transparency Portals
Authors:

Marcus S. Poletti, Methanias Colaço Junior and André P. Nascimento
Abstract: Context: Government transparency portals are built based on ETL (Extract, Transform and Load) processes, which increase the quality and interoperability of data, making a critical subsystem for these applications, subject to evaluative research for improvements. Objective: To analyze publications on the use of ETL in transparency portals, in order to characterize them in relation to their scenarios, impacts, empirical methods and general bibliometric data. Method: Using the PICO strategy (Population, Intervention, Comparison and Outcome), a systematic mapping of the literature was performed. Summary of Results: In a total of 204 publications researched, 25 works were selected, of which 40% present, as the main impact for the portals, the availability of support for the construction of loads through a graphical interface, followed by the possibility of connectivity between bases of heterogeneous data (27%) and the ability to monitor loads (22%). Regarding the real automation of loads and their quality control, respectively, only 8% and 3% of the works discussed the impacts of these characteristics. Conclusion: The research showed that the use of ETLs in transparency portals still lacks comparative and feasibility studies. In this sense, an existing challenge is the lack of research that carries out replications to consolidate and validate the works already published, evidenced by the scarcity of controlled experiments in the area. Finally, analyzes on the quality control of loads was an important gap identified.
Download
Paper Nr: 28
Title:

Smart Placement of Routers in Agricultural Crop Areas
Authors:

P. G. Coelho, J. M. Amaral, K. P. Guimarães, E. N. Rocha and T. S. Souza
Abstract: The utilization of technologies in agriculture, which is called precision agriculture, is progressively necessary to optimize crop yields. The purpose of this paper is to present an optimized positioning of routers, seeking a robust topology of the network, in order to cover the sensor monitoring devices spread in an agricultural crop area, sending data such as temperature, soil humidity, incidence of luminosity, etc., which allows the farmer to make better decisions regarding the cultivation of his/her land. For this, genetic algorithms will be used to determine the location of routers in a network through evolutionary techniques associated with a fuzzy aggregation method. Typical application cases are presented and discussed to illustrate the proposal.
Download
Paper Nr: 31
Title:

INSIDE: Semantic Interoperability in Engineering Data Integration
Authors:

Vitor D. Almeida, Júlio G. Campos, Elvismary Molina de Armas, Geiza M. Hamazaki da Silva, Hugo Neves, Eduardo L. Corseuil and Fernando R. Gonzalez
Abstract: One of the critical problems in the industry is data integration. Data is generated continuously and on a large scale and is persisted using different formats, software, and terminologies. Integrating multiple databases belonging to different information systems can provide a unified data view and a better understanding of the data. With that in mind, this paper present INSIDE, a system that enables Semantic Interoperability for Engineering Data Integration. INSIDE represents queries to one or multiple databases through the concept of data services, where each service is defined using an ontology. Data services can conceptually represent the commitments and claims between service providers (databases) and service customers (users) along with the service lifecycle (the process of querying, integrating, and delivering data). The contributions of this paper are the following: (1) Use of formal mechanisms for semantic data representation with the connection with the international community; (2) A conceptual model for a distributed system based on ontologies for querying and manipulating data from multiple data sources; (3) An implementation of this model, called INSIDE, developed on top of Apache Spark; and (4) An experimental evaluation of the service composition strategy of INSIDE for data integration of multiple data sources using a real-world scenario.
Download
Paper Nr: 66
Title:

A Review of Blockchain Platforms Based on the Scalability, Security and Decentralization Trilemma
Authors:

Jan Werth, Mohammad H. Berenjestanaki, Hamid R. Barzegar, Nabil El Ioini and Claus Pahl
Abstract: As blockchains are more and more used to support information system architectures, the question of the suitability of a blockchain technology for a particular system arises. However, given the vast amount of existing blockchain platforms, this choice is difficult as each blockchain focuses on different aspects. The most critical ones are scalability, security, and decentralization, which make up the blockchain trilemma. We review a selection of the most popular blockchain platforms based on their blockchain trilemma properties and related aspects. Then, the platforms will be analyzed on the three aspects of the blockchain trilemma.
Download
Paper Nr: 77
Title:

A Predictive Model for Assessing Satisfaction with Online Learning for Higher Education Students During and After COVID-19 Using Data Mining and Machine Learning Techniques: A Case of Jordanian Institutions
Authors:

Hadeel Kakish and Dalia Al-Eisawi
Abstract: Higher education institutions confronted an escalating unexpected pressure to rapidly transform throughout and after the COVID-19 pandemic, by replacing most of the traditional teaching practices with online-based education. Such transformation required institutions to frequently strive for qualities that meet conceptual requirements of traditional education due to its agility and flexibility. The challenge of such electronic learning styles remains in their potential of bringing out many challenges, along with the advantages it has brought to the educational systems and students alike. This research came to shed the light on several factors presented as a predictive model and proposed to contribute to the success or failure in terms of students’ satisfaction with online learning. The study took the kingdom of Jordan as a case example country experiencing online education while and after the covid -19 intensive implementation. The study used a dataset collected from a sample of over “300” students using online questionnaires. The questionnaire included “25” attributes mined into the Knime analytics platform. The data was rigorously learned and evaluated by both the “Decision Tree” and “Naive Bayes” algorithms. Subsequently, results revealed that the decision tree classifier outperformed the naïve bayes in the prediction of student satisfaction, additionally, the existence of the sense of community while learning electronically among other reasons had the most contribution to the satisfaction.
Download
Paper Nr: 89
Title:

Investigating Aha Moment Through Process Mining
Authors:

Wan-Hsuan Chiang, Usman Ahmad, Shenghui Wang and Faiza A. Bukhsh
Abstract: Aha moment is when users realize the value of using the software product, which is a key to driving revenue, mainly for B2B SaaS vendors. According to the Acquisition-Activation-Retention-Referral-Revenue (AARRR) model, the aha moment can refer to activation, and the following customer phase is retention. This research aims to find customers’ ”aha moment” through process mining. Since the customers in retention are obligated to experience activation before, the research first identifies milestone actions in terms of product features and user roles to cluster the retention customers. Evaluation is performed through the data of the clustered customers from the time before they move to the retention phase. The event log analysis is discussed based on multiple dimensions: product solution, time, and user roles. The research mainly applies the process mining technique, heuristic miner, to discover the customer’s behavior patterns. Apart from marketing funnels, Moreover concept of human-computer interaction is focused on event classification and data cleaning, which is practical for cleaning UI logs. The discovered processes and aha moment can guide future product development and value proposition re-stratigizing.
Download
Paper Nr: 97
Title:

On the Use of Blockchain Technology to Improve the Reproducibility of Preclinical Research Experiments
Authors:

Eduardo C. Oliveira, Rafael Z. Frantz, Carlos Molina-Jiménez, Thiago Heck, Sandro Sawicki and Fabricia Roos-Frantz
Abstract: Preclinical research is crucial for the advancement of life sciences. The use of experimental animal models in basic health sciences historically helped humanity to understand the pathological mechanisms of diseases and to develop therapeutic strategies, medicines and vaccines. Progress in this direction depends, to a large degree, on experimentation. Therefore, it is highly desirable that research experiments conducted on preclinical research are reproducible. Regrettably, a large number of experiments are not reproducible. Factors leading to irreproducible research on preclinical studies fall into four major categories: Biological reagents and reference materials, study design, data analysis and reporting and laboratory protocols. The data analysis and reporting category concentrates 25.5% of the total factors. Is estimated that $7.19 billions of the total research budget is funding irreproducible experiments. It is widely acknowledged that sharing experimental data between different institutions and cooperative researchers worldwide helps in experiment reproducibility which results in science and technology acceleration and innovation. Data sharing involves several data operations: The researcher needs to collect the data, protect it to prevent accidental and malicious deletion and corruption and make it available to colleagues, possibly, to the general public. The execution of these operations is cumbersome and error prone unless appropriate technology is used. This paper suggests and explores the use of blockchain to improve the reproducibility of experiments.A blockchain is a decentralised database that offers several properties that can be used advantageously in the collection, storage and sharing of experimental data, for instance, it prevents deletion.
Download
Paper Nr: 99
Title:

A Computational Model for Predicting Cryptocurrencies Using Exogenous Variables
Authors:

Eduardo M. Gonçalves, Eduardo N. Borges, Bruno L. Dalmazo, Rafael A. Berri, Giancarlo Lucca and Vinicius M. de Oliveira
Abstract: The recent growth of cryptocurrencies caused worldwide interest due to capitalization power and geographic expansion. In this universe, Bitcoin is the main actor. Taking this into consideration, this paper aims to analyze the behavior of Bitcoin during the time. To do so, we use techniques already studied in the literature to perform the predictions and comparisons between methods jointly with exogenous variables to boost the results. An evaluation has been performed and the best results were achieved using the Long-Short-Term-Memory (LSTM) neural network model. Also, the experiments were carried out in different scenarios, using datasets with more than five years of daily records and exogenous variables to improve the performance of the models.
Download
Paper Nr: 100
Title:

Mammography Unit Location: Reconciling Maximum Coverage and Budgetary Constraints
Authors:

Rudivan P. Barbosa, Marcone F. Souza and Gilberto D. Miranda Junior
Abstract: This work addresses the Bi-objective Mammography Unit Location-Allocation Problem. This problem consists in allocating mammography units satisfying two objectives and respecting the constraints of device capacity for screenings and the maximum travel distance for the service. The first objective function maximizes the coverage of exams performed by the allocated mammography devices, while the second function minimizes the total amount of equipment used. We introduce a mixed-integer linear programming bi-objective model to represent the problem and apply the Weighted Sum and Epsilon-constraint methods to solve it. The Epsilon-constraint method was able to generate better Pareto fronts. The instances used for testing come from real data from two Brazilian states obtained from the Brazilian Health Ministry.
Download
Paper Nr: 126
Title:

An Online Deterministic Algorithm for Non-Metric Facility Leasing
Authors:

Christine Markarian and Claude Fachkha
Abstract: Leasing has become one of the most widely spread business models in almost all markets. The online algo- rithmic study of leasing was initiated in 2005. Unlike classical algorithms, online algorithms are not given the entire input sequence at once. A portion of the input sequence is revealed in each step and the online algorithm is required to react to each step while targeting the given optimization goal against the entire input sequence. In a leasing setting, resources are leased and expire once their lease duration is over. Many well- known optimization problems are defined and studied in the leasing setting. In this paper, we continue the online algorithmic study of leasing by addressing the so-called Online Non-metric Facility Leasing problem (ONFL), the leasing variant of the non-metric Online Facility Location problem (non-metric OFL). Given a collection of facility and client locations. Facilities can be leased using a fixed number of lease types, each characterized by length and price. Lease types respect the economy of scale, such that longer leases cost more but are cheaper per unit of time. In each step, a client appears. The algorithm needs to promptly connect it to a facility that is leased at the current time step. To this end, it needs to decide which facility locations to lease, the start of their lease, and the lease duration. Connecting a client to a facility incurs a cost equal to the distance between the facility and the client. The goal is to minimize the total connecting and facility leasing costs. In this work, we develop the first deterministic algorithm for ONFL and evaluate it using the notion of competitive analysis, a worst-case performance analysis in which the solution of the online algorithm is compared, over all instances of the given problem, to the optimal solution of the offline variant of the problem.
Download
Paper Nr: 140
Title:

Decentralised Autonomous Management of an Association Through Smart Contracts According to German Legislation
Authors:

Matthias Pohl, Rene Degenkolbe, Daniel G. Staegemann and Klaus Turowski
Abstract: A new emerging form of organisation, the decentralised autonomous organisation (DAO), built on blockchain technology and smart contracts, offers the potential for transforming social interaction. The basic regulations for running an association under German law indicate that transforming the traditional form of an association into a decentralised autonomous organisation is feasible. The main advantage comes from the automated execution of standard association management processes as well as the decentralised provision of IT infrastructure through a blockchain network. The advantages of the partially automated and decentralised administrative processes of an association are contrasted with further challenges of the social system of the future.
Download
Paper Nr: 191
Title:

Evaluation of Deep Learning Techniques for Entity Matching
Authors:

Paulo S. Lima, Douglas R. Santana, Wellington S. Martins and Leonardo A. Ribeiro
Abstract: Application data inevitably has inconsistencies that may cause malfunctioning in daily operations and com- promise analytical results. A particular type of inconsistency is the presence of duplicates, e.g., multiple and non-identical representations of the same information. Entity matching (EM) refers to the problem of de- termining whether two data instances are duplicates. Two deep learning solutions, DeepMatcher and Ditto, have recently achieved state-of-the-art results in EM. However, neither solution considered duplicates with character-level variations, which are pervasive in real-world databases. This paper presents a comparative evaluation between DeepMatcher and Ditto on datasets from a diverse array of domains with such variations and textual patterns that were previously ignored. The results showed that the two solutions experienced a considerable drop in accuracy, while Ditto was more robust than DeepMatcher.
Download
Paper Nr: 216
Title:

A Real-Time Platform to Monitoring Misinformation on Telegram
Authors:

Ivandro Claudino, Thiago Gadelha, Tiago Vinuto, José W. Franco, José M. Monteiro and Javam Machado
Abstract: The large-scale dissemination of misinformation through social media has become a critical issue, harming public health, social stability and democracy. In Brazil, 79.9% of the population uses social networks, and the Telegram is present in 65% of the country’s smartphones. Due to its popularization, many groups have used this instant messaging application to spread misinformation, especially as part of articulated political or ideological campaigns. Telegram provides two essential features that facilitate the spread of misinformation, public groups and channels. Through these resources, false information can deceive thousands of people in a short time. In this context, we present MST, a Real-Time platform to find, gather, analyze and visualize misinformation on Telegram. To evaluate the proposed platform, we built a dataset from the Brazilian general election campaign in 2022, obtained from Telegram public chat groups and channels.
Download
Paper Nr: 217
Title:

Developing and Evaluating a Tool to Support Predictive Tasks
Authors:

José A. Câmara, José M. Monteiro and Javam Machado
Abstract: Currently, professionals from the most diverse areas of knowledge need to explore their data repositories in order to extract knowledge and create new products or services. Several tools have been proposed in order to facilitate the tasks involved in the Data Science lifecycle. However, such tools require their users to have specific (and deep) knowledge in different areas of Computing and Statistics, making their use practically unfeasible for non-specialist professionals in data science. In this paper, we present the developing and evaluating of a tool called DSAdvisor, which aims to encourage non-expert users to build machine learning models to solve predictive tasks (regression and classification), extracting knowledge from their data repositories. To evaluate DSAdvisor, we applied the System Usability Scale (SUS) questionnaire to measure aspects of usability in accordance with the user’s subjective assessment and the Net Promoter Score (NPS) method to measure user satisfaction and willingness to recommend it to others. This study involved 20 respondents who were divided into two groups, namely experts and non-expert users. The SUS method had a score of 68.5 which means a “good” product, and the results of using NPS get a value of 55% which means “very good” NPS.
Download

Area 2 - Artificial Intelligence and Decision Support Systems

Full Papers
Paper Nr: 21
Title:

Improved ACO Rank-Based Algorithm for Use in Selecting Features for Classification Models
Authors:

Roberto A. Delamora, Bruno N. Coelho and Jodelson A. Sabino
Abstract: Attribute selection is a process by which the best subset of attributes in a given dataset is searched. In a world where decisions are increasingly based on data, it is essential to develop tools that allow this selection of attributes to be more efficiently performed, aiming to improve the final performance of the models. Ant colony optimization (ACO) is a well-known metaheuristic algorithm with several applications and recent versions developed for feature selection (FS). In this work, we propose an improvement in the general construction of ACO, with improvements and adjustments for subset evaluation in the original Rank-based version by BulInheimer et al. to increase overall efficiency. The proposed approach was evaluated on several real-life datasets taken from the UCI machine-learning repository, using various classifier models. The experimental results were compared with the recently published WFACOFS method by Ghosh et al., which shows that our method outperforms WFACOFS in most cases.
Download
Paper Nr: 22
Title:

Legal Information Retrieval Based on a Concept-Frequency Representation and Thesaurus
Authors:

Wagner M. Costa and Glauco V. Pedrosa
Abstract: The retrieval of legal information has become one of the main topics in the legal domain, which is characterized by a huge amount of digital documents with a peculiar language. This paper presents a novel approach, called BoLC-Th (Bag of Legal Concepts Based on Thesaurus), to represent legal texts based on the Bag-of-Concept (BoC) approach. The novel contribution of the BoLC-Th is to generate weighted histograms of concepts defined from the distance of the word to its respective similar term within a thesaurus. This approach allows to emphasize those words that have more significance for the context, thus generating more discriminative vectors. We performed experimental evaluations by comparing the proposed approach with the traditional Bag-of-Words (BoW), TF-IDF and BoC approaches, which are popular techniques for document representation. The proposed method obtained the best result among the evaluated techniques for retrieving judgments and jurisprudence documents. The BoLC-Th increased the mAP (mean Average Precision) compared to the traditional BoC approach, while being faster than the traditional BoW and TF-IDF representations. The proposed approach contributes to enrich a domain area with peculiar characteristics, providing a resource for retrieving textual information more accurately and quickly than other techniques based on natural language processing.
Download
Paper Nr: 30
Title:

Towards a Novel Edge AI System for Particle Size Detection in Mineral Processing Plants
Authors:

Flávio W. Cardoso, Mateus C. Silva, Natália C. Meira, Ricardo R. Oliveira and Andrea C. Bianchi
Abstract: Monitoring and controlling the particle size is essential to reducing the variability and optimizing energy efficiency in mineral process plants. The industry standard utilizes laboratory processes for particle size characterization; the problems that arise here are obtaining representative sample from the bulk and finding a rapid method of particle size assessment. We propose a machine vision concept based on Edge AI architecture and deep convolutional neural algorithms to enable a real-time analysis of particle size, as an alternative to offline laboratory process. The present paper is part of this proposed concept and aims exclusively to validate a deep convolutional neural network algorithm trained from synthetic datasets. The proposed model reached a mean Average Precision (mAP) of 0.96 and processing times of less than 1s. The results demonstrate the feasibility of deep convolutional neural networks for real-time particle size segmentation and establishes the first step towards a novel Edge AI system for particle size measurement in mineral processing plants.
Download
Paper Nr: 32
Title:

CrudeBERT: Applying Economic Theory Towards Fine-Tuning Transformer-Based Sentiment Analysis Models to the Crude Oil Market
Authors:

Himmet Kaplan, Ralf-Peter Mundani, Heiko Rölke and Albert Weichselbraun
Abstract: Predicting market movements based on the sentiment of news media has a long tradition in data analysis. With advances in natural language processing, transformer architectures have emerged that enable contextually aware sentiment classification. Nevertheless, current methods built for the general financial market such as FinBERT cannot distinguish asset-specific value-driving factors. This paper addresses this shortcoming by presenting a method that identifies and classifies events that impact supply and demand in the crude oil markets within a large corpus of relevant news headlines. We then introduce CrudeBERT, a new sentiment analysis model that draws upon these events to contextualize and fine-tune FinBERT, thereby yielding improved sentiment classifications for headlines related to the crude oil futures market. An extensive evaluation demonstrates that CrudeBERT outperforms proprietary and open-source solutions in the domain of crude oil.
Download
Paper Nr: 46
Title:

A Decision Support System for Multi-Trip Vehicle Routing Problems
Authors:

Mirko Cavecchia, Thiago Alves de Queiroz, Manuel Iori, Riccardo Lancellotti and Giorgio Zucchi
Abstract: Emerging trends, driven by industry 4.0 and Big Data, are pushing to combine optimization techniques with Decision Support Systems (DSS). The use of DSS can reduce the risk of uncertainty of the decision-maker regarding the economic feasibility of a project and the technical design. Designing a DSS can be very hard, due to the inherent complexity of these types of systems. Therefore, monolithic software architectures are not a viable solution. This paper describes the DSS developed for an Italian company based on a micro-services architecture. In particular, the services handle geo-referenced information to solve a multi-trip vehicle routing problem with time windows. To face the problem, we follow a two-step approach. First, we generate a set of routes solving a vehicle routing problem with time windows using a metaheuristic algorithm. Second, we calculate the interval in which each route can start and end, and then combine the routes together, with an integer linear programming model, to minimize the number of used vehicles. Computational tests are conducted on real and random instances and prove the efficiency of the approach.
Download
Paper Nr: 57
Title:

Learning Deep Fake-News Detectors from Scarcely-Labelled News Corpora
Authors:

P. Zicari, M. Guarascio, L. Pontieri and G. Folino
Abstract: Nowadays, news can be rapidly published and shared through several different channels (e.g., Twitter, Facebook, Instagram, etc.) and reach every person worldwide. However, this information is typically unverified and/or interpreted according to the point of view of the publisher. Consequently, malicious users can leverage these unofficial channels to share misleading or false news to manipulate the opinion of the readers and make fake news viral. In this scenario, early detection of this malicious information is challenging as it requires coping with several issues (e.g., scarcity of labelled data, unbalanced class distribution, and efficient handling of raw data). To address all these issues, in this work, we propose a Semi-Supervised Deep Learning based approach that allows for discovering accurate and effective Fake News Detection models. By embedding a BERT model in a pseudo-labelling procedure, the approach can yield reliable detection models also when a limited number of examples are available. Extensive experimentation on two benchmark datasets demonstrates the quality of the proposed solution.
Download
Paper Nr: 70
Title:

Classification of H&E Images via CNN Models with XAI Approaches, DeepDream Representations and Multiple Classifiers
Authors:

Leandro A. Neves, João C. Martinez, Leonardo C. Longo, Guilherme F. Roberto, Thaína A. Tosta, Paulo R. de Faria, Adriano M. Loyola, Sérgio V. Cardoso, Adriano B. Silva, Marcelo Z. do Nascimento and Guilherme B. Rozendo
Abstract: The study of diseases via histological images with machine learning techniques has provided important advances for diagnostic support systems. In this project, a study was developed to classify patterns in histological images, based on the association of convolutional neural networks, explainable artificial intelligence techniques, DeepDream representations and multiple classifiers. The images under investigation were representatives of breast cancer, colorectal cancer, liver tissue, and oral dysplasia. The most relevant features were associated by applying the Relief algorithm. The classifiers used were Rotation Forest, Multilayer Perceptron, Logistic, Random Forest, Decorate, IBk, K*, and SVM. The main results were areas under the ROC curve ranging from 0.994 to 1, achieved with a maximum of 100 features. The collected information allows for expanding the use of consolidated techniques in the area of classification and pattern recognition, in addition to supporting future applications in computer-aided diagnosis.
Download
Paper Nr: 90
Title:

Automated Decision Support Framework for IoT: Towards a Cyber Physical Recommendation System
Authors:

Mohammad Choaib, Moncef Garouani, Mourad Bouneffa, Nicolas Waldhoff, Adeel Ahmad and Yasser Mohanna
Abstract: Among the key factors of Industry 4.0 are the intensive use of Cyber Physical Systems (CPSs). These systems can be implemented at many application levels for various application domains. Each application requires a personalized CPS architecture concerning the Physical sensors as well as the management of Cyber systems. Furthermore, it requires also the maintenance of the communications among these different sub-systems. However, researchers and engineers may lack the essential knowledge to design and build an autonomous CPS. In this paper, we propose the concept of a novel Cyber Physical Recommendation System (CPRS) in order to address this open challenge. The proposed approach is subjected to assist the competencies of researchers and engineers to design and build more efficient CPS according to the given objective, domain, and input application scenarios. In this regard, CPRS recommend the components of the desired CPS, based on a novel architecture model of the components, connections, and tasks of the CPSs. The proposed system is eventually intended to aide the progress in leading factories towards the maturity of fourth industrial revolution.
Download
Paper Nr: 98
Title:

Using Multilingual Approach in Cross-Lingual Transfer Learning to Improve Hate Speech Detection
Authors:

Aillkeen B. de Oliveira, Cláudio S. Baptista, Anderson A. Firmino and Anselmo C. de Paiva
Abstract: In the Internet age people are increasingly connected. They have complete freedom of speech, being able to share their opinions with the society on social media. However, freedom of speech is often used to spread hate speech. This type of behavior can lead to criminality and may result in negative psychological effects. Therefore, the use of computer technology is very useful for detecting and consequently mitigating this kind of cyber attacks. Thus, this paper proposes the use of a state-of-the-art model for detecting political-related hate speech on social media. We used three datasets with a significant lexical distance between them. The datasets are in English, Italian, and Filipino languages. To detect hate speech, we propose the use of a PreTrained Language Model (PTLM) with Cross-Lingual Learning (CLL) along with techniques such as ZeroShot (ZST), Joint Learning (JL), Cascade Learning (CL), and CL/JL+. We achieved 94.3% in the F-Score metric using CL/JL+ strategy with the Italian and Filipino datasets as the source language and the English dataset as the target language.
Download
Paper Nr: 105
Title:

Fuzzy Logic Based Edge Detection Methods: A Systematic Literature Review
Authors:

Miquéias S. Silva, Gracaliz Dimuro, Eduardo Borges, Giancarlo Lucca and Cedric Marco-Detchart
Abstract: Edge detection, or the detection of the maximum limit between two regions with different properties, is one of the classic problems in the area of computer vision. The uncertainty associated with the nature of this detection, such as the characteristic fuzzy transition zone resulting from the image discretization processes, or even noise and illumination variations, justifies an approach based on fuzzy logic theory. In order to understand the state of the art in edge detection techniques using fuzzy logic-based methods, this work proposes a systematic review considering two bibliographic sources of scientific literature, Scopus and Web Of Science. In total, 34 works were selected through a systematic literature review, and their methods were summarized and reported in this research. From this analysis, it could be concluded that, in recent years, fuzzy logic has been employed in hybrid methods in order to improve the performance of existing techniques or reduce computational complexity. Studies with interval fuzzy logic of higher order have been employed for its greater flexibility in dealing with the uncertainty associated with the edge detection task.
Download
Paper Nr: 151
Title:

Towards a Business-Oriented Approach to Visualization-Supported Interpretability of Prediction Results in Process Mining
Authors:

Ana Rocio C. Cárdenas Maita, ANA MAITA, ANA M. Marques Peres and Fabrizio M. Maggi
Abstract: The majority of the state-of-the-art predictive process monitoring approaches are based on machine learning techniques. However, many machine learning techniques do not inherently provide explanations to business process analysts to interpret the results of the predictions provided about the outcome of a process case and to understand the rationale behind such predictions. In this paper, we introduce a business-oriented approach to visually support the interpretability of the results in predictive process monitoring. We take as input the results produced by the SP-LIME interpreter and we project them onto a process model. The resulting enriched model shows which features contribute to what degree to the predicted result. We exemplify the proposed approach by visually interpreting the results of a classifier to predict the output of a claim management process, whose claims can be accepted or rejected.
Download
Paper Nr: 154
Title:

Multiscale Context Features for Geological Image Classification
Authors:

Matheus V. Todescato, Luan F. Garcia, Dennis G. Balreira and Joel L. Carbonera
Abstract: Dealing with image retrieval in corporate systems becomes challenging when the dataset is small and the images present features in multiple scales. In this paper, we propose the notion of multiscale context features, in order to decrease information loss and improve the classification of images in such scenarios. We propose a preprocessing approach that splits the image into a set of patches, computes their features using a pre-trained model, and computes the context feature representing the whole image as an aggregation of the features extracted from individual patches. Besides that, we apply this approach in different scales of the image, generating context features of different scales, and we aggregate them to generate a multiscale representation of the image, which is used as the classifier input. We evaluated our method in a geological images dataset and in a publicly available dataset. We evaluate our approach with three efficient pre-trained models as feature extractors. The experiments show that our approach achieves better results than the conventional approaches for this task.
Download
Paper Nr: 199
Title:

SDRank: A Deep Learning Approach for Similarity Ranking of Data Sources to Support User-Centric Data Analysis
Authors:

Michael Behringer, Dennis Treder-Tschechlov, Julius Voggesberger, Pascal Hirmer and Bernhard Mitschang
Abstract: Today, data analytics is widely used throughout many domains to identify new trends, opportunities, or risks and improve decision-making. By doing so, various heterogeneous data sources must be selected to form the foundation for knowledge discovery driven by data analytics. However, discovering and selecting the suitable and valuable data sources to improve the analytics results is a great challenge. Domain experts can easily become overwhelmed in the data selection process due to a large amount of available data sources that might contain similar kinds of information. Supporting domain experts in discovering and selecting the best suitable data sources can save time, costs and significantly increase the quality of the analytics results. In this paper, we introduce a novel approach – SDRank – which provides a Deep Learning approach to rank data sources based on their similarity to already selected data sources. We implemented SDRank, trained various models on 4 860 datasets, and measured the achieved precision for evaluation purposes. By doing so, we showed that SDRank is able to highly improve the workflow of domain experts to select beneficial data sources.
Download
Short Papers
Paper Nr: 24
Title:

A Classifier-Based Approach to Predict the Approval of Legislative Propositions
Authors:

Ilo D. Cabral and Glauco V. Pedrosa
Abstract: This paper presents a data mining-based approach to predict the approval of Legislative Propositions (LPs) based on textual documents. We developed a framework using machine learning and natural language processing algorithms for automatic text classification to predict whether or not a proposition would be approved in the legislative houses based on previous legislative proposals. The major contribution of this work is a novel kNN-based classifier less sensitive to imbalanced data and a time-wise factor to weight similar documents that are distant in time. This temporal factor aims to penalize the approval of LPs with subjects that are far from current political, social and cultural trends. The results obtained show that the proposed classifier increased the F1-score by 30% when compared to other traditional classifiers, demonstrating the potential of the proposed framework to assist political agents in the legislative process.
Download
Paper Nr: 44
Title:

A User-Centered Approach to Analyze Public Service Apps Based on Reviews
Authors:

Glauco V. Pedrosa, John C. Gardenghi, Pollyanna O. Dias, Ludimila Felix, Ariel L. Serafim, Lucas H. Horinouchi and Rejane C. Figueiredo
Abstract: User reviews often contain complaints or suggestions which are valuable for app developers to improve user experience and satisfaction. In this paper, we introduce the Br-APPS (Brazilian Analytics of Public Posts in App Stores), an automated framework for mining opinions from user reviews of mobile apps. The purpose of Br-APPS is to assist developers by identifying the causes of negative user reviews in three levels of detail. As it is not possible to accurately estimate the number of active users of the app, Br-APPS adopts two indicators based on the number of issues reported by users and the number of app downloads. This approach allows estimating the proportion of causes of complaints, so it is possible to prioritize the issues most complained about. The performance of Br-APPS was evaluated on the gov.br app, which is the most accessed mobile application in the Brazilian government. The use of Br-APPS made it possible to quickly identify the main causes of user complaints and made it easier for developers to direct efforts to improve the app. Interviews with stakeholders of the gov.br service reported that the technique proposed is a valuable asset to ensure that government agencies can drive the creation of public services using a user-centered support technique.
Download
Paper Nr: 71
Title:

A Concept for Optimal Warehouse Allocation Using Contextual Multi-Arm Bandits
Authors:

Giulia Siciliano, David Braun, Korbinian Zöls and Johannes Fottner
Abstract: This paper presents and demonstrates a conceptual approach for applying the Linear Upper Confidence Bound algorithm, a contextual Multi-arm Bandit agent, for optimal warehouse storage allocation. To minimize the cost of picking customer orders, an agent is trained to identify optimal storage locations for incoming products based on information about remaining storage capacity, product type and packaging, turnover frequency, and product synergy. To facilitate the decision-making of the agent for large-scale warehouses, the action selection is performed for a low-dimensional, spatially-clustered representation of the warehouse. The capability of the agent to suggest storage locations for incoming products is demonstrated for an exemplary warehouse with 4,650 storage locations and 30 product types. In the case study considered, the performance of the agent matches that of a conventional ABC-analysis-based allocation strategy, while outperforming it in regards to exploiting inter-categorical product synergies.
Download
Paper Nr: 78
Title:

ESG Data Collection with Adaptive AI
Authors:

Francesco Visalli, Antonio Patrizio, Antonio Lanza, Prospero Papaleo, Anupam Nautiyal, Mariella Pupo, Umberto Scilinguo, Ermelinda Oro and Massimo Ruffolo
Abstract: The European Commission defines the sustainable finance as the process of taking Environmental, Social and Governance (ESG) considerations into account when making investment decisions, leading to more long-term investments in sustainable economic activities and projects. Banks, and other financial institutions, are increasingly incorporating data about ESG performances, with particular reference to risks posed by climate change, into their credit and investment portfolios evaluation methods. However, collecting the data related to ESG performances of corporate and businesses is still a difficult task. There exist no single source from which we can extract all the data. Furthermore, most important ESG data is in unstructured format, hence collecting it poses many technological and methodological challenges. In this paper we propose a method that addresses the ESG data collection problem based on AI-based approaches. We also present the implementation of the proposed method and discuss some experiments carried out on real world documents.
Download
Paper Nr: 109
Title:

Forecasting Residential Energy Consumption: A Case Study for Greece
Authors:

Dimitra Kouvara and Dimitrios Vogiatzis
Abstract: Residential energy consumption forecasting has immense value in energy efficiency and sustainability. In the current work we tried to forecast energy consumption on residences in Athens, Greece. As a proof of concept, smart sensors were installed into two residences that recorded energy consumption, as well as indoors environmental variables (humidity and temperature). It should be noted that the data set was collected during the COVID-19 pandemic. Moreover, we integrated weather data from a public weather site. A dashboard was designed to facilitate monitoring of the sensors’ data. We addressed various issues related to data quality and then we tried different models to forecast daily energy consumption. In particular, LSTM neural networks, ARIMA, SARIMA, SARIMAX and Facebook (FB) Prophet were tested. Overall SARIMA and FB Prophet had the best performance.
Download
Paper Nr: 115
Title:

An Unsupervised Approach for Study of the Relationship Between Behavioral Profile and Facial Expressions in Video Interviews
Authors:

Ana C. Conceição de Jesus, Richard R. Mariano, Alessandro G. Vieira, Jéssica D. Almeida de Lima, Giulia Zanon de Castro and Wladmir C. Brandão
Abstract: The use of Behavior Mapping (BM) questionnaires to analyze the Behavioral Profile (BP) of employees can lead to biased responses, incompleteness, and inaccuracies, especially when information such as reactions, facial expressions, and body language cannot be captured. Thus, methods with the ability to recognize and characterize BP automatically and without direct inference of bias can minimize the impact of erroneous assessments. Intensity clustering of Facial Action Units (AUs) from the Facial Action Coding System (FACS), extracted from video interviews of PACE BPs, was proposed. Features were extracted from 500 videos and effort was targeted to profiles whose probability was equal to or greater than 40% of the individual belonging to the profile. An analysis of the relationship between BPs and intensities throughout the video was presented, which can be used to support the expert’s decision in the BM.
Download
Paper Nr: 116
Title:

Natural Language Processing Approach for Classification of Archetypes Using Text on Business Environments
Authors:

Richard R. Mariano, Ana C. Conceição de Jesus, Alessandro G. Vieira, Jessica D. Almeida de Lima, Giulia Zanon de Castro and Wladmir C. Brandão
Abstract: Organizations increasingly offer resources to improve performance, minimize costs, and achieve better results. An organization is the individuals who work or provide services in it. Therefore, good organizational performance directly results from the good work of its collaborators. Identifying the archetype in the business environment can combine individuals with companies, which can improve the organizational environment and enhance the development of the individual. A person leaves traces of his behavior in what he produces, such as videos and texts. Some studies point to the possibility of identifying a behavioral profile from a textual production. In this work, we seek to identify the archetype of individuals within the business environment based on their curriculum texts. We combine the behavioral profile assessment (BPA) archetypes (Planner, Analyst, Communicator, and Executor) with 26,636 curriculum to apply machine learning models. For this task, we used classification and regression approaches. The main algorithm used for the approaches was the SVM. The results suggest that the archetypes are better modeled using regression techniques, obtaining an MSE of 4.49 in the best case. We also provide a visual explanation example to understand the model outputs.
Download
Paper Nr: 118
Title:

Labor Accidents Classification Using Machine Learning
Authors:

Enádio S. Barbosa, Yandre G. Costa, Juliano H. Foleis and Diego Bertolini
Abstract: The application of artificial intelligence is increasingly growing in all public and private industry fields. In this work, we propose applying machine learning techniques to perform work accident classification according to Brazilian laws. The type of accident is part of the communication of occupational accidents (CAT) database held by the National Institute of Social Security. In Brazil, that communication can come from different sources. Because of this, some of them lack the type of work accident. This information is crucial to allow labor authorities to understand better the circumstances surrounding the accidents and to help plan and create more specific strategies to prevent them. In this sense, we perform data cleaning, and we use feature engineering techniques to treat data from CAT database. Following, we use machine learning algorithms aiming to perform the classification according to the type of accident. For this, we investigate a strategy to identify the type of labor accident when this information is missing using algorithms based on trees or gradient boosting trees. Preliminary results showed promising performance, where the algorithms achieved the following weighted average F1-score for labor accident types classification: XGboost 0.94, CAtboost 0.94, Lightgbm 0.94, and Random Forest 0.91. As far as we know, work accident type classification using machine learning, considering Brazilian labor legislation and a huge governmental dataset is addressed for the first time in this work.
Download
Paper Nr: 119
Title:

Mobile Robot Navigation Strategies Through Behavioral Cloning and Generative Adversarial Imitation Learning
Authors:

Kevin M. Silva and Rodrigo Calvo
Abstract: The conception of robots able to navigate autonomously through several environments remains one of the main challenges to be overcome in the robotics research. The wide use of machine learning techniques as imitation learning has obtained efficient performance in this research field. The autonomous navigation is essential to carry out many kinds of task, which it can reduce the time and computational cust. One of the mechanisms to a robot be autonomous is observe the behavior of the other. Therefore, it is proposed in this research the development of a strategy of navigation based on Generative Adversarial Imitation Learning (GAIL) for the learning of the navigational behaviors of distinct mobile robots with different locomotion strategies. The CoppeliaSim simulator is used to build virtual scenarios and execute experiments to gather samples for the strategy training. Another strategy will be developed based on the behavioral cloning, which will also be trained in some environments with the same samples used in GAIL. Regression error metrics in addition with the comparison of the paths generated by the strategies in each scenario will be considered as evaluation methods. The obtained results are then discussed along with the potential future works.
Download
Paper Nr: 125
Title:

On the Adoption of Federated Machine Learning: Roles, Activities and Process Life Cycle
Authors:

Tobias Müller, Milena Zahn and Florian Matthes
Abstract: Federated Machine Learning is a promising approach for training machine learning models on decentralized data without the need for data centralization. Through a model-to-data approach, Federated Machine Learning yields huge potential from privacy by design to heavily reducing communication costs and offline usage. However, the implementation and management of Federated Machine Learning projects can be challenging, as it involves coordinating multiple parties across different stages of the project life cycle. We observed that Federated Machine Learning is missing clarity over the individual involved roles including their activities, interactions, dependencies, and responsibilities which are needed to establish governance and help practitioners operationalize Federated Machine Learning projects. We argue that a process model, which is closely aligned with established MLOps principles can provide this clarification. In this position paper, we make a case for the necessity of a role model to structure distinct roles, an activity model to understand the involvement and operations of each role, and an artifact model to demonstrate how artifacts are used and structured. Additionally, we argue, that a process model is needed to capture the dependencies and interactions between the roles, activities, and artifacts across the different stages of the life cycle. Furthermore, we describe our research approach and the current status of our ongoing research toward this goal. We believe that our proposed process model will provide a foundation for the governance of Federated Machine Learning projects, and enable practitioners to leverage the benefits of decentralized data computation.
Download
Paper Nr: 128
Title:

“How to Make Them Stay?”: Diverse Counterfactual Explanations of Employee Attrition
Authors:

André Artelt and Andreas Gregoriades
Abstract: Employee attrition is an important and complex problem that can directly affect an organisation’s competitive- ness and performance. Explaining the reasons why employees leave an organisation is a key human resource management challenge due to the high costs and time required to attract and keep talented employees. Busi- nesses therefore aim to increase employee retention rates to minimise their costs and maximise their perfor- mance. Machine learning (ML) has been applied in various aspects of human resource management including attrition prediction to provide businesses with insights on proactive measures on how to prevent talented em- ployees from quitting. Among these ML methods, the best performance has been reported by ensemble or deep neural networks, which by nature constitute black box techniques and thus cannot be easily interpreted. To enable the understanding of these models’ reasoning several explainability frameworks have been proposed to either explain individual cases using local interpretation approaches or provide global explanations describ- ing the overall logic of the predictive model. Counterfactual explanation methods have attracted considerable attention in recent years since they can be used to explain and recommend actions to be performed to obtain the desired outcome. However current counterfactual explanations methods focus on optimising the changes to be made on individual cases to achieve the desired outcome. In the attrition problem it is important to be able to foresee what would be the effect of an organisation’s action to a group of employees where the goal is to prevent them from leaving the company. Therefore, in this paper we propose the use of counterfactual ex- planations focusing on multiple attrition cases from historical data, to identify the optimum interventions that an organisation needs to make to its practices/policies to prevent or minimise attrition probability for these cases. The proposed technique is applied on an employee attrition dataset, used to train binary classifiers. Counterfactual explanations are generated based on multiple attrition cases, thus, providing recommendations to the human resource department on how to prevent attrition.
Download
Paper Nr: 138
Title:

Multi-Modal Artificial Intelligence in Additive Manufacturing: Combining Thermal and Camera Images for 3D-Print Quality Monitoring
Authors:

Markus Bauer, Benjamin Uhrich, Martin Schäfer, Oliver Theile, Christoph Augenstein and Erhard Rahm
Abstract: With emerging technologies such as high-precision Laser Powder Bed Fusion (LPBF), rapid prototyping has gained remarkable importance in metal manufacturing. Furthermore, cloud computing and easy-to-integrate sensors have boosted the development of digital twins. Such digital twins use data from sensors on physical objects, to improve the understanding of manufacturing processes as a whole or of certain production parameters. That way, digital twins can demonstrate the impact of design changes, usage scenarios, environmental conditions or similar variables. One important application of such digital twins lies in early detection of manufacturing faults, such that real prototypes need to be used less. This reduces development times and allows products to be individually, affordable, powerful, robust and environmentally friendly. While typically simple USB-camera setups or melt-pool imaging are used for this task, most solutions are difficult to integrate into existing processes and hard to calibrate and evaluate. We propose a digital-twin-based solution, that leverages information from camera-images in a self-supervised fashion, and creates a heat transfer based AI quality monitoring. For that purpose, artificially generated labels and physics simulation were combined with a multisensor setup and supervised learning. Our model detects printing issues at more than 91% accuracy.
Download
Paper Nr: 142
Title:

An Automatic Ant Counting and Distribution Estimation System Using Convolutional Neural Networks
Authors:

Mateus C. Silva, Breno H. Felisberto, Mateus C. Batista, Andrea C. Bianchi, Servio P. Ribeiro and Ricardo R. Oliveira
Abstract: A relevant challenge to be tackled in ecology is comprehending collective insect behaviors. This understanding significantly impacts the understanding of nature, as some of these flocks are the most extensive cooperative units in nature. A part of the difficulty in tackling this challenge comes from reliable data sampling. This work presents a novel method to understand the quantities and distribution of ants in colonies based on convolutional neural networks. As this tool is unique, we created an application to create the marked dataset, created the first version of the dataset, and tested the solution with different backbones. Our results suggest that the proposed approach is feasible to solve the proposed issue. The average coefficient of determination R 2 with the ground truth counting was 0.9783 using the MobileNet as the backbone and 0.9792 using the EfficientNet V2B0 as the backbone. The global average for the semi-quantitive classification of each image region was 86% for the MobileNet and 88% for the EfficientNet V2-B0. There was no statistically significant difference between both cases’ average and median errors. The coefficient of determination was close to the statistical significance threshold (p = 0.065). The application using the MobileNet as its backbone performed the task faster than the version using the EfficientNet V2-B0, with statistical significance (p < 0.05).
Download
Paper Nr: 152
Title:

Tuning Analog PID Controllers by Multi-Objective Genetic Algorithms with Fuzzy Aggregation
Authors:

P. G. Coelho, J. F. M. Amaral, Y. C. Bacelar, E. N. Rocha, M. Bentes and T. S. Souza
Abstract: This paper deals with a procedure for adjusting the gains of a Proportional-Integral-Derivative (PID) controller. Multi-objective genetic algorithms with fuzzy aggregation are used for tuning this controller. To that end, the component values of a known topology of analog PID controller circuit are evolved by a genetic algorithm to yield acceptable performance specifications. A fuzzy aggregator allows multi-objective evaluation for the genetic algorithm. Three objectives regarding the PID reference input signal specifications were considered: overshoot, rise time and settling time. Minimizing these objectives approximates the PID controller output to the reference signal and leads the genetic algorithm to find the best controller gains. A case study is presented to illustrate the procedure.
Download
Paper Nr: 163
Title:

Explaining Meta-Features Importance in Meta-Learning Through Shapley Values
Authors:

Moncef Garouani, Adeel Ahmad and Mourad Bouneffa
Abstract: Meta-learning, or the ability of a machine learning model to adapt and improve on a wide range of tasks, has gained significant attention in recent years. A crucial aspect of meta-learning is the use of meta-features, which are high-level characteristics of the data that can guide the learning process. However, it is a challenging task to determine the importance of different meta-features in a specific context. In this paper, we propose the use of Shapley values as a method for explaining the importance of meta-features in meta-learning process. Whereas, Shapley values is a well-established method in game theory. It has been used for fair distribution of payouts among a group of individuals, based on the separate contribution of meta-features to the overall payout. Recently, these have been also applied to machine learning to understand the contribution of different features in a model’s prediction. We observe that a better understanding of meta-features, using the Shapely values, can be gained to evaluate their importance. In the context of meta-learning it may aid to improve the performance of the model. Our results demonstrate that Shapley values can provide insight into the relative importance of different meta-features and how they interact in the learning process. This can fairly optimize the meta-learning models, resulting in more accurate and effective predictions. Overall, this work conclude that Shapley values can be a useful tool in guiding the design of meta-features and these can be used to improve the performance of the meta-learning algorithms.
Download
Paper Nr: 167
Title:

Predicting Moisture Content on Wood Using Machine Learning Classification Methods
Authors:

Vítor M. Magalhães, Giancarlo Lucca, Alessandro L. Bicho and Eduardo N. Borges
Abstract: The growing demand for wood in several industry segments and for its economical value increased illegal deforestation in several countries. As a direct consequence, climate changes across the planet have been aggravated, which further increases the prominence and concern about the issue of deforestation. So that these potentially catastrophic effects can be mitigated, it is necessary to better use wood in production processes. In this sense, a key point is the variation of the moisture content of the wood as a function of storage time, since, as the wood logs are stored outdoors, they gradually begin to lose water. Dry wood usually cracks, which makes most of its use unfeasible – depending on the purpose – which can even lead to the disposal of the log. Considering that there is a direct relationship between moisture content and wood weight, this work aims to develop different possible solutions for this problem using explainable machine learning methods, contributing to the effectiveness in controlling the variation in moisture content and, consequently, to a better use in the production processes in which wood is used as a raw material.
Download
Paper Nr: 168
Title:

Towards the Automatic Creation of Optimized Classifier Ensembles
Authors:

Julius Voggesberger, Peter Reimann and Bernhard Mitschang
Abstract: Classifier ensemble algorithms allow for the creation of combined machine learning models that are more accurate and generalizable than individual classifiers. However, creating such an ensemble is complex, as several requirements must be fulfilled. An expert has to select multiple classifiers that are both accurate and diverse. In addition, a decision fusion algorithm must be selected to combine the predictions of these classifiers into a consensus decision. Satisfying these requirements is challenging even for experts, as it requires a lot of time and knowledge. In this position paper, we propose to automate the creation of classifier ensembles. While there already exist several frameworks that automatically create multiple classifiers, none of them meet all requirements to build optimized ensembles based on these individual classifiers. Hence, we introduce and compare three basic approaches that tackle this challenge. Based on the comparison results, we propose one of the approaches that best meets the requirements to lay the foundation for future work.
Download
Paper Nr: 176
Title:

Natural Language Processing Applied in the Context of Economic Defense: A Case Study in a Brazilian Federal Public Administration Agency
Authors:

Vanessa C. Ribeiro, Jeanne L. Emygdio, Guilherme P. Paiva, Bruno G. Praciano, Valério A. Martins, Edna D. Canedo, Fábio L. Mendonça, Rafael D. Sousa Júnior and Ricardo S. Puttini
Abstract: Natural Language Processing (NLP) and Machine Learning (ML) resources can be used in Jurisprudence to deal more accurately with the large volume of documents and data in this context to provide speed to the execution of processes and greater accuracy to judicial decisions. This article aims to present applied research with a qualitative approach and exploratory objective, technically characterized as a case study. The research was conducted in a Brazilian federal public administration agency to verify the existence of antitrust practices in the pharmaceutical field and the monitoring of such practices by the institution. To this end, a methodological path was established based on three stages: building the corpus, running the NLP pipeline and consultation of the results in the Jurisprudence Search System (BJ System). In compliance with the objective of the case study, it was possible to identify the performance of the agency around the domain elicited, as well as indications of the existence of antitrust practices, since the 276 documents retrieved from the BJ system relate directly to routine processes executed by the agency, either in the sense of investigation, trial or analysis of the business practices.
Download
Paper Nr: 182
Title:

Using Deep Learning with Attention to Detect Data Exfiltration by POS Malware
Authors:

Gabriele Martino, Federico A. Galatolo, Mario A. Cimino and Christian Callegari
Abstract: In recent years, electronic payment through Point-of-Sale (POS) systems has become popular. For this reason, POS devices are becoming more targeted by cyber attacks. In particular, RAM scraping malware is the most dangerous threat: the card data is extracted from the process memory, during the transaction and before the encryption, and sent to the attacker. This paper focuses on the possibility to detect this kind of malware through anomaly detection based on Deep Learning with attention, using the network traffic with data exfiltration occurrences. To show the effectiveness of the proposed approach, real POS transaction traffic has been used, together with real malware traffic extracted from a collection of RAM scrapers. Early results show the high potential of the proposed approach, encouraging further comparative research. To foster further development, the data and source code have been publicly released.
Download
Paper Nr: 185
Title:

Generating Synthetic Faces for Data Augmentation with StyleGAN2-ADA
Authors:

Natália C. Meira, Mateus C. Silva, Andrea C. Bianchi and Ricardo R. Oliveira
Abstract: Generative deep learning models based on Autoencoders and Generative Adversarial Networks (GANs) have enabled increasingly realistic face-swapping tasks. The generation of representative synthetic datasets is an example of this application. These datasets need to encompass ethnic, racial, gender, and age range diversity so that deep learning models can avoid biases and discrimination against certain groups of individuals, reproducing implicit biases in poorly constructed datasets. In this work, we implement a StyleGAN2-ADA to generate representative synthetic data from the FFHQ dataset. This work consists of step 1 of a face-swap pipeline using synthetic facial data in videos to augment data in artificial intelligence model problems. We were able to generate synthetic facial data but found limitations due to the presence of artifacts in most images.
Download
Paper Nr: 195
Title:

Artificial Intelligence-Powered Decisions Support System for Circular Economy Business Models
Authors:

Julius S. Mboli, Dhavalkumar Thakker and Jyoti Mishra
Abstract: The circular economy (CE) is preferred to linear economy (LE) as it aims to keep resources in use for as long as possible, extracting maximum value before recovering and regenerating them. This reduces the need to extract new raw materials and reduces waste, leading to more sustainable economic growth. Contrarily, LE also known as a ”take, make, use, dispose” model, is based on resources extraction, products creation, and waste disposal, which can lead to depletion of resources, environmental degradation and several other hazards. Several barriers are delaying the switching to CE. Artificial Intelligence (AI) and emerging technologies can play significant roles in the implementation of CE. In this work, A novel AI-powered model that can serve as a Decisions Support System (DSS) for CE models is proposed and demonstrated. Product life extension is created via reuse, repair, remanufacture, recycle and cascade loop. The result of the model outperformed the LE model. The study demonstrates that technologies can enable smart monitoring, tracking, and analysis of products to support decision-making (DM). AI-powered sensors and devices can monitor the use of resources in real-time, allowing for more accurate tracking and reporting of resource use.
Download
Paper Nr: 212
Title:

An Investigation of Deep-Learned Features for Classifying Radiographic Images of COVID-19
Authors:

Pedro L. Miguel, Adriano M. Cansian, Guilherme B. Rozendo, Giuliano C. Medalha, Marcelo Zanchetta do Nascimento and Leandro A. Neves
Abstract: In this proposal, a study based on deep-learned features via transfer learning was developed to obtain a set of features and techniques for pattern recognition in the context of COVID-19 images. The proposal was based on the ResNet-50, DenseNet-201 and EfficientNet-b0 deep-learning models. In this work, the chosen layer for analysis was the avg pool layer from each model, with 2048 features from the ResNet-50, 1920 features from the DenseNet0201 and 1280 obtained features from the EfficientNet-b0. The most relevant descriptors were defined for the classification process, applying the ReliefF algorithm and two classification strategies: individually applied classifiers and employed an ensemble of classifiers using the score-level fusion approach. Thus, the two best combinations were identified, both using the DenseNet-201 model with the same subset of features. The first combination was defined via the SMO classifier (accuracy of 98.38%) and the second via the ensemble strategy (accuracy of 97.89%). The feature subset was composed of only 210 descriptors, representing only 10% of the original set. The strategies and information presented here are relevant contributions for the specialists interested in the study and development of computer-aided diagnosis in COVID-19 images.
Download
Paper Nr: 213
Title:

Assessing the Effects of Extreme Events on Machine Learning Models for Electricity Price Forecasting
Authors:

João Borges, Rui Maia and Sérgio Guerreiro
Abstract: Forecasting electricity prices in the face of extreme events, including natural disasters or abrupt shifts in demand, is a difficult challenge given the volatility and unpredictability of the energy market. Traditional methods of price forecasting may not be able to accurately predict prices under such conditions. In these situations, machine learning algorithms can be used to forecast electricity prices more precisely. By training a machine learning model on historical data, including data from extreme events, it is possible to make more accurate predictions about future prices. This can assist in ensuring the stability and dependability of the electricity market by assisting electricity producers and customers in making educated decisions regarding their energy usage and generation. Accurate price forecasting can also lessen the likelihood of financial losses for both producers and consumers during extreme events. In this paper, we propose to study the effects of machine learning algorithms in electricity price forecasting, as well as develop a forecasting model that excels in accurately predicting said variable under the volatile conditions of extreme events.
Download
Paper Nr: 23
Title:

An Evaluation of Malware Triage Similarity Hashes
Authors:

Haoping Liu, Josiah Hagen, Muqeet Ali and Jonathan Oliver
Abstract: Detection of polymorphic malware variants is crucial in cyber security. Searching and clustering are crucial tools for security analysts and SOC operators in malware analysis and hunting. Similarity hashing generates similarity digests based on binary files, allowing for the calculation of similarity scores, saving time and resources in malware triage operations. In this paper, we compare the accuracy and run time of TLSH and LZJD algorithms, both based on windows-based malware samples. TLSH is widely used in industry, while LZJD is newly developed and released in academia. TLSH hashes skip-n-grams into a histogram, providing distance scores based on histogram similarity, while LZJD converts byte strings into sub-strings, providing similarity scores between the sets. Our experiments show that TLSH performs slightly better than LZJD in detection rate, but vastly outperforms LZJD in index and search time.
Download
Paper Nr: 33
Title:

A Framework for a Data Quality Module in Decision Support Systems: An Application with Smart Grid Time Series
Authors:

Giulia Rinaldi, Fernando Crema Garcia, Oscar M. Agudelo, Thijs Becker, Koen Vanthournout, Willem Mestdagh and Bart De Moor
Abstract: Data quality (DQ) measures data status based on different dimensions. This broad topic was brought to the fore in the ’80s when it was first discussed and studied. A high-quality dataset correlates with good performance in artificial intelligence (AI) algorithms and decision-making processes. Therefore, checking the quality of the data inside a decision support system (DSS) is an essential pre-processing step and is beneficial for improving further analysis. In this paper, a theoretical framework for a DQ module for a DSS is proposed. The framework evaluates the quality status in three stages: as based on the European guidelines, as based on DQ metrics, and as based on checking a subset of data cleaning (DC) problems. Additionally, the framework supports the user in identifying and fixing the DC problems, which speeds up the process. As output, the user receives a DQ report and the DC pipeline to execute to improve the dataset’s quality. An implementation of the framework is illustrated in a proof-of-concept (POC) for an industrial use case. In the POC, an example of the execution of the various framework phases was shown using a public time series dataset containing quarter-hourly consumption profiles of residential electricity customers in Belgium for the year 2016.
Download
Paper Nr: 95
Title:

Fuzzy Logic for Diabetes Predictions: A Literature Review
Authors:

Alice G. Pintanel, Graçaliz P. Dimuro, Eduardo N. Borges, Giancarlo Lucca and Camila G. Barcelos
Abstract: The use of methodologies based on machine learning is being increasingly used in health systems today, addressing different areas such as food, society, health and others. In terms of health, different techniques were applied to classify different diseases. In this sense, diabetes is an important and silent disease that deserves special attention and care. Individuals often do not know they have it, and, therefore, seeking alternatives to predict this disease is an important contribution to the health area. Thinking about it, in this work we present a systematic review of the literature with the objective of observing which strategies are currently being used to predict and classify diseases using fuzzy logic, in particular, diabetes. For this, 6 works were selected and analyzed, where the technique for obtaining the considered information is the blood test, in order to understand the current state of the art.
Download
Paper Nr: 147
Title:

Towards Autonomous Mobile Inspection Robots Using Edge AI
Authors:

Ricardo M. Santos, Mateus C. Silva, Rodrigo L. Santos, Emerson Klippel and Ricardo R. Oliveira
Abstract: Recent technological advances have made possible what we call industry 4.0 in which the industrial environment is increasingly filled with advanced technologies such as artificial intelligence and robotics. Defective products increase the cost of production and in such a dynamic environment manual methods of equipment inspection have low efficiency. In this work we present a robot that can be applied in this scenario performing tasks that require automatic displacement to specific points of the industrial plant. In this robot we use the concept of Edge AI using artificial intelligence in a edge computing device. To perform its locomotion the robot uses computer vision with the brand new YOLOv7 CNN and feedback control. As hardware this robot uses a Jetson Xavier NX, Raspberry Pi 4, a camera and a LIDAR. We also performed a complete performance analysis of the object detection method measuring FPS, consumption of CPU, GPU and RAM.
Download
Paper Nr: 155
Title:

Analyzing BERT’s Performance Compared to Traditional Text Classification Models
Authors:

Bihi Sabiri, Amal Khtira, Bouchra El Asri and Maryem Rhanoui
Abstract: Text classification is a task in natural language processing (NLP) in which text data is classified into one or more predefined categories or labels. Various techniques, including machine learning algorithms like SVMs, decision trees, and neural networks, can be used to perform this task. Other approaches involve a new model Bidirectional Encoder Representations from Transformers (BERT) which caused controversy in the machine learning community by presenting state-of-the-art results on various NLP tasks. We conducted an experiment to compare the performance of different natural language processing (NLP) pipelines and analysis models (traditional and new) of classification on two datasets. This study could shed significant light on improving the accuracy during text classification. We found that using lemmatization and knowledge-based n-gram features with LinearSVC classifier and BERT resulted in the high accuracies of 98% and 97% respectively surpassing other classification models used in the same corpus. This means that BERT, TF-IDF vectorization and LinearSVC classification model used Text categorization scores to get the best performance, with an advantage in favor of BERT, allowing the improvement of accuracy by increasing the number of epochs.
Download
Paper Nr: 157
Title:

A Proposal for an Ontology Metrics Selection Process
Authors:

Achim Reiz and Kurt Sandkuhl
Abstract: Ontologies are the glue for the semantic web, knowledge graphs, and rule-based intelligence in general. They build on description logic, and their development is a non-trivial task. The underlying complexity emphasizes the need for quality control, and one way to measure ontologies is through ontology metrics. For a long time, the calculation of ontology metrics was merely a theoretical proposal: While there was no shortage of proposed ontology metrics, actual applications were mostly missing. That changed with the creation of NEOntometrics, a tool that implemented the majority of ontology metrics proposed in the literature. While it is now possible to calculate large amounts of ontology metrics, it also revealed that the calculation alone does not make the metrics useful (yet). In NEOntometrics alone, there are over 160 ontology metrics – a careful selection for the given use case is crucial. This position paper argues for a selection process for ontology metrics. It first presents core questions for identifying the underlying ontology requirements and then guides users to identify the correct attributes and their associated measures.
Download
Paper Nr: 164
Title:

Human-AI Collaboration Types and Standard Tasks for Decision Support: Production System Configuration Use Case
Authors:

Alexander Smirnov, Tatiana Levashova and Nikolay Shilov
Abstract: Production systems can be considered as variable systems with dynamic structures and their efficient configuration requires support by AI. Human-AI collaborative systems seem to be a reasonable way of organizing such support. The paper studies collaborative decision support systems that can be considered as an implementation of the human-AI collaboration. It specifies collaboration and interaction types in decision support systems. Two collaboration types (namely, hybrid intelligence and operational collaboration) are considered in detail applied to the structural and dynamic production system configuration scenarios. Standard tasks for collaborative decision support that have to be solved in human-AI collaboration systems are defined based on these scenarios.
Download
Paper Nr: 170
Title:

Digital Image Processing in the Diagnosis of Cracks in Steel Sheet
Authors:

Taynara M. Gonçalves, Andrea C. Bianchi and Glauco G. Yared
Abstract: The railway is an essential part of the marketing chain. If it is considered efficient, safe, and competitive, on the other hand, the railways suffer from the enormous difficulty of maintenance due not only to their great extension, dispersion and lack of financial investments. Initiatives for automatic maintenance inspection, mostly done manually, require development and consolidation. Therefore, this work presents a method for identifying defects in sleepers based on analyzing images. We will use digital image processing techniques that will allow us to extract the contours of the sleepers and therefore analyze their curvature. The development is carried out with images from laboratory tests, not previously classified but subject to noise. The method is validated through analysis with an image bank with about 20 images of defective and flawless sleepers, with an average assertiveness of 94.24%. The detection, classification, and localization of faults in train tracks are then investigated and discussed.
Download
Paper Nr: 201
Title:

A Report on Work: Cardiac MRI CBIR for Pathologies Detetion
Authors:

Tomasz Michno and Michal Jelonek
Abstract: The early detection of pathologies in the cardiovascular system is very important. One of the most accurate imaging examinations of human tissues is magnetic resonance imaging (MRI), which is a very precise yet non-invasive test. In order to process MRI images to detect pathologies, one of the most promising methods is Content Based Image Retrieval (CBIR). This paper presents a report on the research on that topic as a result of the Miniatura 5 Grant. The main contributions of the paper are: a review of the state-of-the-art methods, a selection of the most promising image features that may be used to identify pathologies, a description of the proposed system for preparing suggestions for doctors, which takes into consideration also methods for presenting the results, which are most often omitted in other researches. The next step will be incorporating full 3D MRI information into the pipeline.
Download
Paper Nr: 215
Title:

Towards Developing a Metaverse Authentication Model for Mobile Features
Authors:

Ibrahim F. Ibrahim, Mohammed M. Morsey, Abeer M. Mahmoud and El-Sayed M. El-Horbaty
Abstract: The Metaverse is essentially a virtual attractive world that attempts to merge (physical and recently digital) reality. The core components, for building a metaverse model, are the recent trendy technologies, artificial intelligence, and the blockchain. The metaverse application in all domains drew the attention of variant individual’s behaviours and accordingly the security issues became wider and uncontrolled by organization. Hence, there is an urgent demand for a comprehensive finding of Metaverse security authentication methods using the machine learning and the recent deep learning techniques. In this paper we present a survey of the recent techniques relevant to the mentioned research topic and formulate the problem statement and the main objectives of our model. The intended model should be able to analyse data and detect attacks of different levels of severity.
Download
Paper Nr: 219
Title:

Decision Support System for Adherence to the White Tariff
Authors:

Paloma S. Dias, Yago A. Marino, Luis M. Mendes, Sofia C. de Oliveira, Elvis M. Nicolau, Iuri W. Pereira, Vinicius B. Grilo, Lucas T. Pimentel, Igor L. Queiroz, Arthur R. Alves, Rafael J. F. de Sá, Glaucia N. C. de Oliveira, Lindolpho D. A. Junior, Ângelo R. de Oliveira and Gabriella C. Dalpra
Abstract: The existence of different tariff modalities for charging the electricity sector in Brazil, if applied assertively in the user’s consumption reality, can mitigate the negative effects that energy charges have on everyday life. Thus, the proposed work deals with the development of an intelligent measurement system for the consumption of energy by the consumer’s home appliances and he will have access to his pattern of energy use throughout the day, through a web network and mobile platform. According to the tariff values available by ANEEL (National Electric Energy Agency), the user will be able to define, based on his consumption history, the adoption of the conventional tariff or the white tariff. It is important to consider that the white tariff has differentiated prices at certain times of the day, having its highest rate at peak times. These hours represent a range of hours in which the highest energy consumption occurs during the day, usually set to three hours per day and not valid on weekends and holidays. Please note that peak times vary by region. In this way, the system will act in parallel with the energy concessionaires and will take into account the interests of energy users.
Download

Area 3 - Information Systems Analysis and Specification

Full Papers
Paper Nr: 11
Title:

Identification of Interface Related Factors Between Safety Management System and Cybersecurity Management System for Highly Automated Driving Vehicles
Authors:

Marzana Khatun, Florence Wagner, Rolf Jung and Michael Glaß
Abstract: Functional safety and cybersecurity are essential parts of the development of automated vehicles to ensure vehicle safety. Highly automated driving (HAD) vehicles require safe and secure development and communication processes that have to be monitored, maintained and improved through management processes. Hence, interface management systems are required to confirm HAD vehicle safety. The acceptance level of the interface between functional safety and cybersecurity in management systems is crucial for the development of Highly Automated Driving (HAD) vehicles. The Safety Management System (SMS) needs to consider the aspect of cybersecurity to ensure the overall safety of the vehicles or vice-versa. However, the interface methods of SMS and Cybersecurity Management System (CSMS) is challenging given the complexity of the system development and constraints from the company culture. The objective of this study is to present an interface approach in between management systems with a set of interface specifications including communication adaption processes. The main contributions of the paper are, (i) Illustrating the interface areas of the SMS and CSMS by identifying the management factors, (ii) Presenting the degree of influence of the management factors based on the survey results, and (iii) Providing a support to deal with SMS and CSMS interface for HAD vehicle development. A list of interface-related management factors is presented in this paper based on the literature study and findings from other disciplines. Additionally, the degree of influence of the management factors is presented as a result of this research based on the survey results from functional safety and cybersecurity experts.
Download
Paper Nr: 18
Title:

Automated Input Data Management for Discrete Event Simulation Models of Emergency Departments
Authors:

Juan D. Mogollon, Virginie Goepp, Oscar Avila and Roland de Guio
Abstract: Emergency Department (ED) overcrowding, that relates to congestion due to the high number of patients, has a negative effect on patient waiting time. The analysis of the flow of patients through Discrete Event Simulation (DES), that models the operation of a system through a sequence of events, is a relevant approach to find a solution to such problem. This technique relies on high-quality input data which needs to be previously managed in a complete process known as Input Data Management (IDM). The objective of this research is to propose a tool to automate the IDM process required for DES models of ED. To do so, we used a case with real data in order to contextualize the problem, evaluate required statistical methods, and gather specific requirements. Based on these results, a prototype was designed and developed by using web and cloud application development tools.
Download
Paper Nr: 45
Title:

On the Automatic Generation of Knowledge Connections
Authors:

Felipe A. Fraga, Marcus Poggi, Marco A. Casanova and Luiz P. Leme
Abstract: Recently, the topic of Personal Knowledge Management (PKM) has seen a surge in popularity. This is illustrated by the accelerated growth of apps such as Notion, Obsidian, and Roam Research, as well as the appearance of books like “How to Take Smart Notes” and “Building a Second Brain.” However, the area of PKM has not seen much integration with Natural Language Processing (NLP). This opens up an interesting opportunity to apply NLP techniques to operating with knowledge. This paper proposes a methodology that uses NLP and networked note-taking apps to transform a siloed text collection into an interconnected and inter-navigable text collection. The navigation mechanisms are based on shared concepts and semantic relatedness between texts. The paper proposes a methodology, presents demonstrations using examples, and describes an evaluation to determine if the system functions correctly and whether the proposed connections are coherent.
Download
Paper Nr: 85
Title:

Investigating Bug Report Changes in Bugzilla
Authors:

Felipe O. Calixto, Franklin Ramalho, Tiago Massoni and José M. Ferreira
Abstract: Bug report change behavior in bug tracking systems may help pinpoint negligence or misunderstanding when submitters fill in bug report information. This study investigates bug report changes in several projects within Mozilla’s Bugzilla to identify which fields in a report change the most, which bug profiles receive more changes and the relationship between these changes. We found that the most changed fields are flagtypes.name and cc. Reports are often modified when they indicate a valid bug, with medium to high priority and severity. Moreover, there are moderate to high correlations between changes in the following field pairs: product-component, priority-severity, and platform-op sys. We believe these results are relevant to indicate which submitter’s skills must be enhanced to improve the bug-tracking process.
Download
Paper Nr: 86
Title:

Architecture Design Decisions in Distributed Teams: An Assessment of Tool Support
Authors:

Mahum Adil, Ilenia Fronza, Outi Sieve-Korte and Claus Pahl
Abstract: Background. Global Software Engineering (GSE) teams develop software artifacts across multiple locations. Designing and maintaining software in such a setting requires continuous collaboration to record design decisions between distributed teams. The literature presents different architecture design decision (ADD) tools to support design thinking and decision-making. However, recent studies highlight the challenges of managing ADDs in a distributed environment. Aim. This study aims to present a list of assessment metrics to evaluate whether existing ADD tools support distributed collaborative design (DCD) in the GSE environment. Method. We used Goal-Question-Metric (GQM) method and expert survey to define and validate the assessment metrics. Result. Six assessment metrics are presented to evaluate ADD tool support for DCD in the GSE environment. Conclusion. The tool analysis based on assessment metrics provides insights into the current practices used for ADD process and its conformance to the distributed environment.
Download
Paper Nr: 101
Title:

Analyzing Software Architecture Documentation Models According to Agile Characteristics
Authors:

Leonardo Barreto and Tayana Conte
Abstract: Background: Software companies that use agile practices and methods usually postpone architecture design activities in favor of accelerated development and idea validation, especially in uncertain and dynamic contexts. However, this attitude leads to the accumulation of different types of technical debt, including architectural and documentation debt. As the company evolves, the architecture created during development becomes complex and hard to maintain, affecting the company’s performance, the product’s quality, and the knowledge transfer. Aim: Support the software architecture planning and documentation by verifying the feasibility of software architecture description approaches in the context of agile development. Method: We evaluated six approaches using the DESMET Feature Analysis method, with features related to implementation cost, flexibility, adaptation to dynamic requirements, usefulness, description consistency, decision analysis, and system modularity. Results: Two approaches had the best scores, with a minor percentage difference between them. These results are due to the low implementation cost of the two approaches, the factor that most influenced the score. Conclusions: The results provide evidence about the feasibility of applying the studied approaches, in agile contexts, besides reducing the number of possible alternatives for conducting experimental studies in this context.
Download
Paper Nr: 137
Title:

Characterizing Security-Related Commits of JavaScript Engines
Authors:

Bruno Gonçalves de Oliveira, Andre T. Endo and Silvia R. Vergilio
Abstract: JavaScript engines are security-critical components of Web browsers. Their different features bring challenges for practitioners that intend to detect and remove vulnerabilities. As these JavaScript engines are open-source projects, security insights could be drawn by analyzing the changes performed by developers. This paper aims to characterize security-related commits of open-source JavaScript engines. We identified and analyzed commits that involve some security aspects; they were selected from the widely used engines: V8, ChakraCore, JavaScriptCore, and Hermes. We compared the security-related commits with other commits using source code metrics and assessed how security-related commits modify specific modules of JavaScript engines. Finally, we classified a subset of commits and related them to potential vulnerabilities. The results showed that only six out of 44 metrics adopted in the literature are statistically different when comparing security-related commits to the others, for all engines. We also observed what files and, consequently, the modules, are more security-related modified. Certain vulnerabilities are more connected to security-related commits, such as Generic Crash, Type Confusion, Generic Leak, and Out-of-Bounds. The obtained results may help to advance vulnerability prediction and fuzzing of JavaScript engines, augmenting the security of the Internet.
Download
Short Papers
Paper Nr: 16
Title:

DTGov: Digital Transformation of Government Processes
Authors:

Nuno Marques and André Vasconcelos
Abstract: Today, companies cannot rely on outdated systems, governments being no exception. There are multiple benefits when performing the digital transformation (DT) of its processes, but also several downsides such as costs. This paper presents first the main use cases: resolve a procedure, send a notification by hand, reclassify a procedure, and create a request, and then the reference solution divided into 3 components. First, the Domain Model and Lifecycles related to the main entities. Second, the Reference Architecture adds the remaining projects’ modules (Roles,...), and also the dependencies between them. Third, the Implementation presents how to implement the information in a real-world case using “low-code” technology, especially useful to mitigate several issues. Lastly, an evaluation of the proposed solution is also presented.
Download
Paper Nr: 50
Title:

Bringing Distributed Collaborative Design and Team Collaboration to the Table: A Conceptual Framework
Authors:

Mahum Adil, Ilenia Fronza and Claus Pahl
Abstract: Background. The recent rise of software organizations shifting towards distributed environments increased the feed for distributed collaborative design (DCD), which requires dedicated design thinking and decision strategies to provide a clear architecture plan for distributed teams. Aim. This study aims to provide effective support for distributed development teams to enhance the transparency of architecture design decisions and contribute towards clear documentation of the decision rationales. Method. Using an action research model, we propose a conceptual framework for distributed Scrum software development teams to manage distributed collaborative design. Results. The proposed framework consists of two phases in which the team performs activities to decrease collaboration barriers in design thinking and decision-making. Conclusions. The illustrating example concretely shows the proposed conceptual framework’s potential and effectiveness in supporting DCD for team collaboration. Further empirical evaluation and validation of the framework are needed in real-time environments.
Download
Paper Nr: 73
Title:

Optimization of SNP Search Based on Masks Using Graphics Processing Unit
Authors:

Álvaro M. Nogueira da Cruz, Vitoria Z. Gomes, Matheus C. Andrade, Anderson R. Amorim, Carlos R. Valêncio, Gilberto Vaughan and Geraldo D. Zafalon
Abstract: In the context of bioinformatics one of the most important problems to be solved is the search for simple nu- cleotide polymorphism (SNP). When we perform the analysis of the files from the next generation sequencing (NGS) the search task for SNPs becomes more prohibitive due to the millions of sequences present on them. CPU multithreaded approaches are not enough when millions of sequences as considered. Then, the use of graphics processing units (GPUs) is a better alternative, because it can operate with hundreds of arithmetic logic units while CPU with no more than tens. Thus, in this work we developed a method to detect SNPs using a mask approach under GPU architecture. In the tests, a speedup of up to 5175.86 was obtained when com- pared to the multithreaded CPU approach, evaluating from 100,000 to 800,000 sequences using five masks to detect the occurrence of SNPs.
Download
Paper Nr: 88
Title:

Semantic Representation of Key Performance Indicators Categories for Prioritization
Authors:

Tarique Khan, Alex Mircoli, Domenico Potena and Claudia Diamantini
Abstract: Key Performance Indicators (KPIs) are crucial tools that are remarkably used to evaluate business performance. Recently, the management of KPIs has fascinated the focus of both academic and business professionals, and that lead to the development of research on various methods dealing with issues such as modeling, maintenance, and expressiveness of KPIs. As a need for organizations and processes to adapt to continuously changing demands, the KPIs used to measure their effectiveness evolve too. In order to make KPI management easier, this research aims to define the best sequence of KPIs evaluation based on semantic relations. After an extensive analysis of the literature on KPIs ontologies, it proposes the idea of KPIs prioritization on the basis of relations among different categories of kpis established by a KPIs ontology. Our approach can be used independently from the particular KPI’s management strategy being employed.
Download
Paper Nr: 106
Title:

Expectation vs Reality: Analyzing the Competencies of Software Testing Teams
Authors:

Nayane Maia, Ana C. Oran and Bruno Gadelha
Abstract: Process and product quality are essential to maintain competitiveness in the software industry. Software testing is one of the activities to assess product quality, and its process permeates all phases of the development process lifecycle. However, this requires software testing professionals to master different technical skills and general skills. To reduce the skills gap required for the testing team, it is necessary to conduct a skills assessment of all team members. Given this, the objective of this research is to present the results of a competence assessment based on a competence mapping model aimed at software testing teams. To support this research, a questionnaire was applied to 25 industry professionals from a development company to assess the general and technical skills of all roles in the software testing process. As a result, we identified which competencies managers desire for their testing teams. In addition, we identified how professionals see themselves through a self-assessment based on this competence mapping model. After the evaluation, it was possible to identify which competencies need to be developed to reach the required levels for each role and increase the productivity and quality of the process and the product.
Download
Paper Nr: 159
Title:

An Ontology-based Knowledge Management Model on Information Governance
Authors:

Cataldo Mega
Abstract: Information is a strategic asset to enterprises and subject to Information Governance (IG) as mandated by corporate and regulatory compliance. Overall governance goals are the management and control of business relevant data such to minimize legal risks and reduce operational cost. Recent surveys show that around 40% of companies have insufficient IG practices in place and are exposed to higher compliance risks. Where there exists an IG Strategy, its implementation is typically homegrown, difficult to integrate and error prone. Our investigation shows that a major impediment to implementation and interoperability is the lack of a common language. One that defines what information governance consists of in technical and operational terms. In addition, the many existing frameworks in this domain make the exploitation of the available knowledge and definition of standardized IG specific services very difficult, often leading to costly one-off implementations. A solution to this problem is the availability of a common and unambiguous domain vocabulary as a pre-requisite to a commonly accepted ontology on information governance. This paper suggests an ontology-based framework (IGONTO) that supports the creation of a knowledge store that facilitates access of domain knowledge through semantic search.
Download
Paper Nr: 161
Title:

People Management Problems and Practices in Software Development Projects: A Systematic Literature Review
Authors:

Marcelo F. Burkard and Lisandra M. Fontoura
Abstract: In the literature related to software engineering, it is possible to observe a large volume of work related to technology and processes. Comparatively, little has been done in people management, making it difficult for project managers to manage teams effectively and solve people-related problems. This study conducts a systematic literature review (SLR) to survey the people management problems faced in software development. In addition, we identify the solutions to these problems. We searched four major bibliographic databases and identified 2736 primary studies between 2016 and 2022, resulting in 35 selected articles. So, we have grouped problems and solutions by similarity to facilitate analysis. We identified 9 groups of problems and 11 groups of solutions. Communication, motivation, technical skills, and knowledge problems are most frequently reported. Regarding the solutions, the most cited are team building, feedback, and training practices. The problems and practices identified consolidate the knowledge and experience obtained in several software projects and can help managers in people management activities in software projects.
Download
Paper Nr: 180
Title:

Interaction Room for Cloud Migration (IR:CM): A Systematic Approach
Authors:

Murad Huseynli, Attila Papp, Udo Bub and Michael C. Ogbuachi
Abstract: Cloud migration is by now an established discipline that is dominated by different methods and frameworks from vendors of commercial offerings. However, it may be hard for teams to discern the inherent risks of such offerings, which may appear as biased tool support, and design processes that cannot be tailored to the needs of the enterprise (and rather have to fit the requirements of the cloud provider). We analyzed these solutions and propose a new method that combines the strong points of the existing designs while overcoming their weaknesses. Our method design results in adaptation of the proven interaction room method to the field of cloud migration (IR:CM). We focus on communication among all stakeholders, identifying risks and chal- lenges, defining scope, and prioritizing requirements, to guide teams while designing cloud-native solutions that are flexible to the changing needs of the business. The new method itself has been developed following the Design Science Research paradigm.
Download
Paper Nr: 206
Title:

Value Co-Creation in the IT Service Ecosystem
Authors:

Maryam Heidari, Geraldine Torrisi and Sebastian Binnewies
Abstract: Despite extensive efforts to demonstrate the capabilities of the IT service to create value, existing frameworks only partially address the complex nature of IT value creation. Most research in the IT service area focuses on individual and micro-level interactions and practices and overlooks the importance of a holistic and systematic view of understanding value co-creation. This research addresses this gap by exploring IT service value co-creation from a “service ecosystem” perspective, considering value co-creation, co-destruction and service well-being. This research-in-progress paper presents the preliminary literature review and elaborates on the study design and research setting. In the future, we will conduct an interpretive case study with a grounded theory approach to investigate how value can be co-created in a multi-level IT service ecosystem that has barely been explored.
Download
Paper Nr: 26
Title:

A Systematic Mapping Study on Quantum Circuits Design Patterns
Authors:

Sergio Jiménez-Fernández, José A. Cruz-Lemus and Mario Piattini
Abstract: Introduction. In order to study quantum software’s quality, the use of patterns for designing quantum circuits is quite an unexplored field whereas a promising one too. Method. This work aims to discover the current state of the art of quantum circuits design patterns by searching the literature via a Systematic Mapping Study. Results. The search space was formed by 1327 studies in three different databases for a final result of 15 primary studies. Conclusions. These studies include a taxonomy for different design patterns over quantum circuits.
Download
Paper Nr: 48
Title:

Remote and Collaborative Software Development Projects: A Requirements Elicitation Exploratory Study
Authors:

Alexandre Grotta and Edmir V. Prado
Abstract: Remote and collaborative software development (RCSD) projects are gaining more relevance in the actual information technology (IT) industry. RCSD projects may carry many benefits, such as economic, velocity, and flexibility impacts to an IS project. Anyhow, RCSD might be complex, due to the team’s geographic distribution, the issues of remote interactions, and other issues that might impact RCSD projects. One of the first aspects to be affected in RCSD is the software requirements given they are often at the project beginning. In this context, this research aims to analyse the factors that impact functional and non-functional requirements in RCSD projects. For this objective, we choose a case study with 59 participants that formed 11 teams of software development. As result, we find that, in this research context, three factors of those six had a positive association with the quality of RE. They are skills in software development, techniques of software development, and tools (adequate selection and usage). These finds are in line with the literature based on the triad People-Process-Tools. Our finds aim to contribute to the project management and software engineering theoretical bases relevant parts, mainly RE success factors, team management, and projects.
Download
Paper Nr: 132
Title:

FAIR Data by Design: A Case of the DiVA Portal
Authors:

Phub Namgay and Joshua C. Nwokeji
Abstract: FAIR Data Principles is a guideline for making data and other digital objects findable, accessible, interoperable, and reusable. Thus far, the traction and uptake of the principle are primarily in the domain of bio and natural sciences. The knowledge gap is the application of the FAIR Data Principles in designing data repositories for FAIR data in the academic data ecosystem. This paper provides a critical insight into how the principle can be utilised as a paradigm to design data that embodies the tenets of FAIR Data Principles. We conducted a case study of the DiVA portal, an information repository and finding tool in Sweden, to explicate FAIR data by design. The portal scored high in a qualitative assessment against the 15 facets of FAIR Data Principles, as illustrated by the high density of green cells in the traffic light rating matrix (see Table 1). It indicates the robustness of data in the portal that is easy to share, find, and reuse. This study suggests practitioners operationalise FAIR Data Principles in their data repositories by design through systems and policies underpinned by the principle. It would enrich data governance and management for the back office and data experiences for end users. The study also advances the knowledge base on data management through a granular exposition of FAIR data by design.
Download
Paper Nr: 166
Title:

SysIoTML: A Technique for Modeling Applications in the Context of IoT
Authors:

Rodrigo Nascimento, Vinicius Santos, Bruno Carvalho, Jone Correia, Luis Rivero, Rodrigo Santos, Francisco Silva, Ariel Teles and Davi Viana
Abstract: The Internet of Things (IoT) is a concept that connects smart objects equipped with sensors, networks, and processing technologies that work together to provide an environment in which smart services are brought to users. Systems modeling should be conducted to create IoT Systems and ensure the implementation of a good system. IoT increases the complexity of systems modeling due to novel concepts that need to be addressed. However, there are no established techniques for systems modeling for this specific context. This paper presents the development of a new technique for IoT systems modeling, the SysIoTML, an extension of SysML. Such techniques consider specific aspects of IoT Systems (behavior and interactivity). We proposed the SysIoTML and conducted a concept-proof to analyze the technical feasibility. The developed technique proved useful, and the participants were able to model the proposed problem. The main contribution is to advance IS modeling through a new technique.
Download
Paper Nr: 174
Title:

Parallelism in the Generation of Concepts Through the Formal Context Object Partitioning Using the In-Close 4 Algorithm
Authors:

André Alves, Luis Zarate, Henrique Freitas and Mark Song
Abstract: Formal Concept Analysis (FCA) usage for information extraction has been increasingly recurrent, using algorithms already developed for this purpose. However, the computational effort involved in analyzing and extracting information can drastically increase in the case of dense and high-dimensionality databases. The main goal of this work is to present a parallel approach to solving this problem. We propose parallelizing In-Close 4 with C++ and OpenMP to generate formal concepts in multiple threads. Our approach is based on the subdivision of formal contexts into subcontexts grouped by a single set of objects. In addition, we propose a set of operations to obtain the original formal concepts from the quasi-concepts, concepts generated from the subcontexts. Our results show a speedup of up to 1.4116x with an efficiency of 70.48% for 100,000 objects, 50 attributes, and a density of 50%.
Download
Paper Nr: 184
Title:

Engineering of Digital Innovation in Edge Computing and Industry 4.0: An Experience Report
Authors:

Michael C. Ogbuachi, Murad Huseynli and Udo Bub
Abstract: This paper illustrates the use of an innovative process model that represents a systematic and scientific ap- proach, using well-established methodologies and techniques from the field of Information Systems and telecommunications. Organizations in the field are pushing for innovation and proposing new technologies and standards, but these proposals often have fundamental differences and tend to primarily target industrial consumers, which have use cases that require reliable and stable systems and methodologies. Despite the known potential benefits of Edge Computing in industrial settings, there is still a lack of scientific rigor in related research and development processes. We contribute to the field by addressing this shortcoming, and by providing a scientific evaluation and a tailored version of a pre-existing method, which allowed us to build a practical solution that tackles the needs of industrial partners, while following a scientific approach. As a result, we managed to build an innovative design for a large industrial company operating in Edge Computing, while thoroughly assessing the progress from idea formulation to the complete solution.
Download

Area 4 - Software Agents and Internet Computing

Full Papers
Paper Nr: 83
Title:

Counteracting Popularity-Bias and Improving Diversity Through Calibrated Recommendations
Authors:

Andre Sacilotti, Rodrigo F. Souza and Marcelo G. Manzato
Abstract: Calibration is one approach to dealing with unfairness and popularity bias in recommender systems. While popularity bias can shift users towards consuming more mainstream items, unfairness can harm certain users by not recommending items according to their preferences. However, most state-of-art works on calibration focus only on providing fairer recommendations to users, not considering the popularity bias, which can amplify the long tail effect. To fill the research gap, in this work, we propose a calibration approach that aims to meet users’ interests according to different levels of the items’ popularity. In addition, the system seeks to reduce popularity bias and increase the diversity of recommended items. The proposed method works in a post-processing step and was evaluated through metrics that analyze aspects of fairness, popularity, and accuracy through an offline experiment with two different datasets. The system’s efficiency was validated and evaluated with three different recommendation algorithms, verifying which behaves better and comparing the performance with four other state-of-the-art calibration approaches. As a result, the proposed technique reduced popularity bias and increased diversity and fairness in the two datasets considered.
Download
Paper Nr: 130
Title:

GOTE: An Edge Computing Architecture for Mobile Gaming
Authors:

Gabriel Robaina and Adriano Fiorese
Abstract: The mobile games market has grown in relevancy compared to traditional gaming platforms. The standard architecture for these games requires the processing of game logic and graphics using the device’s own hardware. Alternatively, cloud based architectures for remote gaming on smartphones present high game input delay at a high cost for the service provider. This poses a limitation to the variety and complexity of games that target these platforms as well as constraining user QoE. To address that limitation, this work proposes the Gaming On The Edge (GOTE) architecture, that aims to enable complex games to be played on smartphone devices while leveraging edge computing infrastructure into graphics processing and content distribution systems. A GOTE architecture’s proof of concept is developed and tested using WebRTC with an RTP streaming pipeline that exploits NVENC for achieving low latency video encoding. Experimental results show that GOTE architecture is a viable alternative to cloud based remote gaming on smartphones at the advantage of lowering latency of video and game input. An open source implementation of the architecture is provided in order to assist further research in this area.
Download
Short Papers
Paper Nr: 54
Title:

An Architecture for a Large-Scale IoT e-Mobility Solution
Authors:

Marek Beránek, George Feuerlicht, Ondřej Kučera and Vladimír Kovář
Abstract: The recent rapid uptake of electric vehicles is driving demand for charging infrastructure that must support the operation of the various stakeholders of the e-mobility ecosystem. The scale and complexity of the e-mobility domain that involves different types IoT devices and a plethora of connectivity standards makes developing a comprehensive solution challenging. E-mobility solutions and their integration into the wider context of smart city standards and technologies are the subject of extensive current research and rapid evolution, but at present there are not many comprehensive solutions that deliver the required functionality and reliability at scale. In this paper we present the Unicorn ChargeUp e-mobility solution designed to support the operation of e-mobility Service Providers, Charge Point Operators and Electric Vehicles drivers, and describe the ChargeUp software architecture that support reliable and scalable operation of thousands of users and IoT devices. We describe the underlying Unicorn Architecture and show how it supports the functional and non-functional requirements of the ChargeUp e-mobility solution.
Download
Paper Nr: 153
Title:

Enhancing Interoperability of Digital Twins Based on Digital Twins Definition Language
Authors:

Salvatore Cavalieri and Salvatore Gambadoro
Abstract: The Industry 4.0 is featured by a continuously-evolving digital transformation, aiming to automate all the traditional industrial practices. Digital Twin is one of the most important solutions to reach this aim. Among the standards currently available to realize Digital Twins there is the Digital Twins Definition Language. Digital Twin requires exchange of data with the real system it models and with other applications which use the digital replica of the system. In the context of Industry 4.0, a reference standard for an interoperable exchange of information between applications, is Open Platform Communications Unified Architecture. The idea behind the paper is to exploit this standard to allow a Digital Twin based on Digital Twins Definition Language to exchange data with any applications compliant to the Open Platform Communications Unified Architecture. A proposal about the mapping from Digital Twins Definition Language to Open Platform Communications Unified Architecture will be presented and discussed in this paper.
Download
Paper Nr: 169
Title:

Ontology-Driven IoT System for Monitoring Hypertension
Authors:

Pedro Lopes de Souza, Wanderley Lopes de Souza, Luís Ferreira Pires, João R. Moreira, Ronitti S. Rodrigues and Ricardo R. Ciferri
Abstract: Hypertension is a noncommunicable disease (NCD) that causes global concern, high costs and a high number of deaths. Internet of Things, Ubiquitous Computing, and Cloud Computing enable the development of systems for remote and real-time monitoring of patients affected with NCDs like hypertension. This paper reports on a system for monitoring hypertension patients that was built by employing these techniques. This system allows the vital signs of a patient (blood pressure, heart rate, body temperature) to be captured via sensors built in a wearable device similar to a wristwatch. These signals are transmitted to the patient’s mobile device for processing, and the generated clinical data are sent to the cloud to be properly presented and analysed by the health professionals responsible for the patient. To deal with semantic interoperability issues that arise when multiple different devices and system components must interoperate, a semantic model was conceived for this system in terms of ontologies for diseases and devices. This paper also presents the semantic module that we developed and implemented in the cloud to perform reasoning based on this model, demonstrating the potential benefits of incorporating semantic technologies in our system.
Download
Paper Nr: 190
Title:

Achieving Private Verification in Multi-stakeholder Environment and Application to Stable Matching
Authors:

Toru Nakamura, Hiroki Okada, Kazuhide Fukushima and Takamasa Isohara
Abstract: Services to support decision-making, such as resource allocation and recommendations, are becoming popular and essential. This paper focuses on two-sided matching as a form of decision-making support. The stable marriage problem has been thoroughly studied as an exciting research topic related to two-sided matching. Stability is a property in which there is no man and woman who would agree to leave their assigned partner, and this property is recognized as an ideal condition for participants. This paper assumes a system where participants provide their preference orders to an assignee, and the assignee provides them with a stable matching. When considering a multi-stakeholder environment, not only the participants’ requirements but also the assignee’s intention should be respected. That is, the assignee should be given the discretion to select the matching which is the best for the assignee among all the stable matchings. However, there is a possibility that if the assignee is malicious, he/she falsifies and provides an unstable matching in order to maximize his/her benefit with ignoring the participants’ requirements. It is difficult for the participants to detect it if they want to keep their preference orders secret from others. This paper proposes a solution of protocol including a private verification algorithm to judge whether the received matching is stable while keeping their preference orders private. The proposed protocol is based on fully homomorphic encryption (FHE) and assumes the use of a semi-honest third-party server. This paper also proposes a general solution that does not limit to specific requirements from participants.
Download
Paper Nr: 165
Title:

Adapting a Generic Smart Service Platform Architecture to the Road-Based Physical Internet
Authors:

Jonah Windolph, Steffen Kaup, Robert Wehlitz, Bogdan Franczyk and André Ludwig
Abstract: Global trade will lead to more than a doubling of transport demand by 2050 in comparison to 2020. At the same time, the impact of pollutant emissions on the global climate is leading to increasingly stringent legislation regarding the environmental friendliness of transportation. Against this background, the transport and logistics industry has to undergo a major transformation in the coming years. Hence, transport efficiency will become more and more important. This will inevitably lead to a rethink in the industry about completely new transport and logistics concepts, such as the Physical Internet (PI). Here, transport efficiency and thus more environmental sustainability are supposed to be achieved by organizing the freight traffic like the data traffic on the digital Internet, with the highest expected potential through a road-based Physical Internet (RBPI). However, the realization of the RBPI depends on the existence of intelligent RBPI services enabled by suitable smart service platforms. In this paper, we propose to adapt a generic architecture for smart service platforms to the RBPI as a cornerstone for its technical implementation. This food for thought may serve as a starting point for further discussions and detailed development in the future.
Download

Area 5 - Human-Computer Interaction

Full Papers
Paper Nr: 13
Title:

Performance Analysis for Upper Limb Rehabilitation in Non-Immersive and Immersive Scenarios
Authors:

Vanesa Herrera, Ana Reyes-Guzmán, David Vallejo, José Castro-Schez, Dorothy N. Monekosso, Carlos González-Morcillo and Javier Albusac
Abstract: In recent years, new technologies have contributed to an improvement in the upper limb rehabilitation process as a complement to the conventional therapy received by patients. In this context, technologies should facilitate accurate monitoring of the hands and serve to collect data on patient performance during functional tasks in order to objectively assess the patient’s potential evolution. Mechanical and wearable devices provide greater accuracy in measurements. However, the physical limitations of patients requires the use of hands-free solutions. This article investigates controller-free hand technologies for accurate hand tracking in the Box and Block test (BBT) benchmarked against the real test, validated and standardized in the context of the Hospital Nacional de Parapléjicos (Toledo, Spain). In particular, the performance in the execution of therapeutic exercises is analyzed in three different scenarios: i) physical environment without the use of technologies, ii) non-immersive virtual environment and, finally, iii) fully immersive virtual environment. The results demonstrate the similarity between therapies developed in physical scenarios without the use of technologies, and those carried out in virtual reality-based scenarios.
Download
Paper Nr: 36
Title:

Comprehensive Differentiation of Partitional Clusterings
Authors:

Lars Schütz, Korinna Bade and Andreas Nürnberger
Abstract: Clustering data is a major task in machine learning. From a user’s perspective, one particular challenge in this area is the differentiation of at least two clusterings. This is especially true when users have to compare clusterings down to the smallest detail. In this paper, we focus on the identification of such clustering differences. We propose a novel clustering difference model for partitional clusterings. It allows the computational detection of differences between partitional clusterings by keeping a full description of changes in input, output, and model parameters. For this purpose, we also introduce a complete and flexible partitional clustering representation. Both the partitional clustering representation and the partitional clustering difference model can be applied to unsupervised and semi-supervised learning scenarios. Finally, we demonstrate the usefulness of the proposed partitional clustering difference model through its application to real-world use cases in planning and decision processes of the e-participation domain.
Download
Paper Nr: 58
Title:

The Usability of Hidden Functional Elements in Mobile User Interfaces
Authors:

Mubashar Munir and Pietro Murano
Abstract: The trend of maximizing mobile screen real estate by hiding user interface features has been in use for some time. However, there is a lack of empirical knowledge concerning the real usability issues of using this strategy. In this paper, we present novel and statistically significant evidence to suggest that hiding user interface elements decreases usability in terms of performance and user experience. We conducted a within-users experiment comparing identical user interfaces, where the only differences between them were that one version hid the user interface elements and the other version had all the user interface elements visible to the user. We recorded task times, errors and user satisfaction for a series of tasks. We also discuss our results in light of existing user interface design guidelines and show that our results are in harmony with existing guidelines.
Download
Paper Nr: 87
Title:

Engagement, Participation, and Liveness: Understanding Audience Interaction in Technology-Based Events
Authors:

Genildo Gomes, Tayana Conte, Thaís Castro and Bruno Gadelha
Abstract: Technologies have been changing how the audience participates in different events. This participation is distinct in each type of event. For example, in educational settings, polls with clickers and word clouds are usually used to involve the audience. For music festivals and other musical performances, organizers opt out of providing led sticks, necklaces and wristbands. Different uses for the smartphones, such as using them as lanterns aiming at obtaining crowd effect, are other ordinary and spontaneous ways of interaction. Recently, more research has been published in journals and scientific conferences discussing the use of these technologies, with techniques for fostering interaction and collaboration. Therefore, we conducted a literature review using forward and backward snowballing, looking for articles about how researchers use new technologies to increase audience experience in different contexts of events and what concepts are raised from that perspective. As a result, we propose a taxonomy of those concepts related to audience experience through three lenses: engagement, participation, and liveness.
Download
Paper Nr: 197
Title:

Unobtrusive Integration of Data Quality in Interactive Explorative Data Analysis
Authors:

Michael Behringer, Pascal Hirmer, Alejandro Villanueva, Jannis Rapp and Bernhard Mitschang
Abstract: The volume of data to be analyzed has increased tremendously in recent years. To extract knowledge from this data, domain experts gain new insights using graphical analysis tools for explorative analyses. Hereby, the reliability and trustworthiness of an explorative analysis are determined by the quality of the underlying data. Existing approaches require a manual inspection to ensure data quality. This inspection is frequently neglected, partly because domain experts often lack the necessary technical knowledge. Moreover, they might need many different tools for this purpose. In this paper, we present a novel interactive approach to integrate data quality into explorative data analysis in an unobtrusive manner. Our approach efficiently combines the strength of different experts, which is currently not supported by state-of-the-art tools, thereby allowing domain-specific adaptation. We implemented a fully working prototype to demonstrate the ability of our approach to support domain experts in explorative data analysis.
Download
Short Papers
Paper Nr: 91
Title:

An Experience in the Gather.town: Factors That Promote Immersion in Systems for the Metaverse
Authors:

Jose C. Duarte, Leonardo Marques, Bruno Gadelha and Tayana Conte
Abstract: As UX becomes important in future digital technologies, Immersion is considered an essential UX aspect in emerging technologies, including Metaverse. Big tech companies have been interested in Metaverse platforms and services. Because the Metaverse has only recently begun to be studied, We are still on the way to exploring it, although its concept has been proposed for more than 30 years. We present an investigation into the factors that promote Immersion in Metaverse platforms using Gather.town. We promote an immersive experience on the Gather.town platform and then conduct a focus group to capture participants’ perceptions. We performed a qualitative analysis to identify the factors that most contributed to the Immersion in the experience. Our findings provide implications for how the Metaverse platforms should be designed and what factors should be emphasized to promote a good user experience in terms of Immersion.
Download
Paper Nr: 133
Title:

Supporting Small Businesses and Local Economies Through Virtual Reality Shopping and Artificial Intelligence: A Position Paper
Authors:

Rubén Grande, Santiago Sánchez-Sobrino, David Vallejo, José J. Castro-Schez and Javier A. Albusac
Abstract: The rise of e-commerce and online sales has had a detrimental effect on small businesses that lacked an online presence in recent years, with negative consequences for local services and economies. Despite attempts to digitize businesses, large corporations continue to hold a privileged position that allows them to capture the majority of sales. Small businesses may regain a competitive edge against large platforms by anticipating and adapting to the next phases of commercial evolution, which are likely to be heavily reliant on Virtual Reality shopping and Artificial Intelligence. In this article, we propose a platform that combines these two technologies and enables local businesses to join forces and overcome physical barriers, thereby providing a virtual world of unrestricted retail spaces. The system also proposes retail collection points and develops attractive leisure plans around these points through the outcomes of a recommender system, thereby promoting city activity and bolstering local economies.
Download
Paper Nr: 179
Title:

A Problem Analysis in Game-Based Student Response System from UX Elements Perspective
Authors:

Brendo Campos, Jose C. Duarte, Genildo Gomes, Leonardo Marques, Bruno Gadelha and Tayana Conte
Abstract: Game-Based Student Response Systems (GBSRS) are tools for improving learning through student interaction and participation. Promoting a good user experience in GBSRS is essential in adopting such tools in the educational context. In this sense, it is necessary to design GBSRS by thinking about how to provide the best experience for users. This paper presents an investigation of UX problems in two GBSRS tools, Kahoot! and Quizizz, to verify whether we could avoid UX problems even in the initial stages of product design. For that, we performed a rapid review, and from the selected articles, we cataloged and classified general problems in the tools from the perspective of the UX elements defined by Garret’s framework. Our results showed that the problems identified in our analysis could be avoided if we applied UX principles in the tool design phase.
Download
Paper Nr: 183
Title:

UXNator: A Tool for Recommending UX Evaluation Methods
Authors:

Solano Oliveira, Alexandre Cristo, Miguel Geovane, André Xavier, Roseno Silva, Sabrina Rocha, Leonardo Marques, Genildo Gomes, Bruno Gadelha and Tayana Conte
Abstract: UX assessment plays a key role in the development of user-quality software systems. Due to the growing interest, much research has been carried out to propose different UX evaluation methods. However, despite many methods, quantity is an aspect that makes it challenging to choose which one to use in UX evaluation. In this paper, we present UXNator, a tool for recommending UX methods based on filters that collect the responses of interested stakeholders in the evaluation. We conducted a feasibility study to evaluate UXNator’s initial proposal, collecting the participants’ perceptions of use. We qualitatively analyzed the reports and identified improvement categories in UXNator. The result presents the positive perception of participants about UXNator’s goal of recommending UX methods. We intend to improve UXNator based on participant feedback, looking forward it will become a standard option for queries and recommendations of UX methods.
Download
Paper Nr: 29
Title:

Process Mining and Perceived Privacy Violations: A Pilot-Study
Authors:

Evelyn Zuidema-Tempel, Faiza A. Bukhsh, Robin Effing and Jos van Hillegersberg
Abstract: Despite the existence of various methods and abstraction techniques to reduce the privacy risk of process models generated by process mining algorithms, it is unclear how process mining stakeholders perceive privacy violations. In this pilot-study various process model visualisations were shown to 6 stakeholders of a travel expense claim process. While changing the abstraction levels of these visualisations, the stakeholders were asked whether they perceived a violation of their privacy. The results show that there are differences in how individual stakeholders perceive privacy violations of process models generated via process mining algorithms. Results differ per type of visualization, type of privacy risk reducing methods, changes of abstraction level and stakeholder role. To reduce the privacy risk, the interviewees suggested to include an authorization table in the process mining tool, communicate the goal of the analysis with all stakeholders, and validate the analysis with a privacy officer. It is suggested that future research focuses on discussing and validating process visualisations and privacy risk reducing methods and techniques with various process mining stakeholders in organisations. This is expected to reduce perceived violations and prevents developing techniques that are aimed at reducing privacy risk but are not considered as such by stakeholders.
Download
Paper Nr: 64
Title:

Factors Affecting Employees’ Acceptance of Blockchain in the Higher Education Institutions
Authors:

Mohammed Alhumayzi, Luciano Batista and Vladlena Benson
Abstract: Blockchain technology is a distributed digital ledger that boosts decentralised applications. This technology has many potential applications in the Higher Education Institutions (HEIs) industry. Yet, blockchain technology adoption is still low in HEIs. Within the adoption process, neglecting employees’ acceptance of blockchain technology might cause a failure in adopting blockchain. To address the blockchain acceptance problem, this study aims to determine the factors that impact employees’ acceptance of blockchain technology within HEIs. To accomplish this aim, this paper proposes a framework that extends the unified theory of acceptance and use of technology (UTAUT) with blockchain characteristics to determine the factors that affect blockchain acceptance among HEIs’ employees. Specifically, the proposed model includes UTAUT constructs: effort expectance, performed expectancy, social influence, facilitating conditions, behavioural intention and technology use, and blockchain characteristics, including security and trust. Also, this study investigates HEIs employees’ awareness as a moderator of UTAUT factors. This paper contributes to academia as it proposes a new theoretical framework that contains factors that might facilitate or hinder the implementation of blockchain technology applications among employees. The present paper also contributes to practitioners in HEIs as it informs decision-makers about potential factors concerning employees’ acceptance of the blockchain technology.
Download
Paper Nr: 135
Title:

Hypermediation Functionalities in Digital Platforms for Collaborative and Social Interaction
Authors:

Eliza R. Oliveira, Oksana Tymoshchuck, Eveline R. Sacramento, André C. Branco, Daniel Carvalho, Luis Pedro, Maria Antunes, Ana Almeida and Fernando Ramos
Abstract: The purpose of this article is to identify how Mobile Apps/Platforms have promoted Hypermediation Processes, establishing functionalities that enhance hypermediation. This determines how it improves interactions and audience engagement with online media content, allowing the user to not only be a passive spectator but also actively participate through the interaction provided by the system. Considering that the hypermediation concept is still not widely established, a theoretical introduction is presented, aiming to define it. To map the hypermediation traits, we conducted a systematic literature review to identify functionalities that enhance hypermediation in current mobile apps/platforms. It comprises articles from Scopus and Web of Science databases, published between 2016 and 2021. Further, the research strategy used keywords in English and Spanish, and it was made in accordance with the PRISMA Statement. A total of 29 articles were analysed to identify hypermediation functionalities that play a relevant role in fostering communication and engagement in collaborative and social interaction contexts. Simultaneously, this article discusses how hypermediation can be understood in the CeNTER platform scope as an example of a digital platform for community-led initiatives. This study’s results made it possible to identify the functionalities of hypermediation that are essential to promote community initiatives and local development.
Download

Area 6 - Enterprise Architecture

Full Papers
Paper Nr: 56
Title:

The Digital Transformation of Corporate Entrepreneurship: The Role of Digital Skills and Digital Champions
Authors:

Stefano D’Angelo, Antonio Ghezzi, Angelo Cavallo, Andrea Rangone and Giulia Murani
Abstract: Digital transformation is perhaps the most pervasive managerial challenge for incumbent firms of the last and coming decades. Digital possibilities need to come together with skilled employees and executives to reveal the transformative power of digital technologies. Despite the contemporary significance, extant literature lacks guidance for digital competence enhancement - i.e., assess digital competencies and carry out effective initiatives to bridge the identified and measured digital competence gaps. Moreover, existing literature on digital skills focuses mainly on the educational context while leaving less explored the corporate context. And more, there is still little evidence on how digital skills can affect entrepreneurship in incumbent organizations. Thus, this study explores how incumbents assess and develop digital skills within their organizations through an in-depth, longitudinal case study of a utility company. We shed light on how incumbents can integrate digital skills in their organizations to embrace digital transformation and initiate corporate entrepreneurship initiatives that leverage the usage of digital technologies. Based on the findings of this study, we contribute to digital skills, digital transformation, and corporate entrepreneurship literature and we offer practical implications for incumbents.
Download
Paper Nr: 75
Title:

Towards a Transition Matrix-Based Concept Drift Approach: Experiments on the Detection Task
Authors:

Antonio M. Neto, Rafael Gaspar de Sousa, Marcelo Fantinato and Sarajane M. Peres
Abstract: Contemporary process mining techniques commonly assume business processes are in a steady state. However, business processes are prone to change and evolution in response to various factors, which can happen at any time, in a planned or unplanned way. This phenomenon of business process evolution and change is known as concept drift, and identifying and understanding is of paramount relevance for business process management, so that organizations can respond and adapt to the new challenges they face. The goal of this paper is to introduce the use of transformed transition matrices as a data structure to support the treatment of concept drifts in process mining, given its efficiency, simplicity, and expandability. The proposed data structure allows to handle different concept drift aspects in an integrated way. Three concept drift detection methods are first adapted to work on transformed transition matrices. The results obtained in the experiments are compared with a state-of-the-art method (baseline), and the three methods used achieved good results, showing an encouraging potential for future planned work.
Download
Paper Nr: 79
Title:

The Analysis of Data-Flow and Control-Flow in Workflow Processes Using Maude
Authors:

Oana O. Captarencu
Abstract: A business process consists of coordinated tasks that take place inside an organization in order to achieve a specific business objective. The process also involves data, that can be used/produced by tasks or used to control the execution of tasks. A workflow is the automation of a business process. Verification of workflow correctness usually focuses on the control-flow of workflows (which regards the tasks and their order of execution). Data anomalies can prevent the correct execution of the process, even if it is correct at the control-flow level, or can produce undesired results. Thus, data information plays an important role in workflow analysis. In this paper we propose an analysis technique for workflows with data, based on Petri nets and on the rewriting logic based language Maude: we use a special class of Petri nets, workflow nets with data, to model workflow processes with data and propose a translation of workflow nets with data into rewrite theories in Maude. This will allow the application of model checking techniques to detect data errors, verify specific properties regarding data and verify the correctness of the workflow.
Download
Paper Nr: 81
Title:

A Next-Generation Digital Procurement Workspace Focusing on Information Integration, Automation, Analytics, and Sustainability
Authors:

Jan-David Stütz, Oliver Karras, Allard Oelen and Sören Auer
Abstract: Recent events such as wars, sanctions, pandemics, and climate change have shown the importance of proper supply network management. A key step in managing supply networks is procurement. We present an approach for realizing a next-generation procurement workspace that aims to facilitate resilience and sustainability. To achieve this, the approach encompasses a novel way of information integration, automation tools as well as analytical techniques. As a result, the procurement can be viewed from the perspective of the environmental impact, comprising and aggregating sustainability scores along the supply chain. We suggest and present an implementation of our approach, which is meanwhile used in a global Fortune 500 company. We further present the results of an empirical evaluation study, where we performed in-depth interviews with the stakeholders of the novel procurement platform to validate its adequacy, usability, and innovativeness.
Download
Paper Nr: 92
Title:

The Impact of Blockchain on Business Model: A Literature Review
Authors:

Giacomo Vella, Luca Gastaldi and Antonio Ghezzi
Abstract: Blockchain is becoming an increasingly relevant topic and companies are beginning to build business solution using this technology. Despite the relevance of the changes that blockchain could bring to business and management, current research is still predominantly focused on technological aspects and practical applications. Knowledge is lacking also both for academics and practitioners who, still struggle to have a clear understanding of the potential impacts of blockchain. Moreover, scientific literature addressing the business adoption of blockchain does not seem to consider the increasing differentiation of blockchain real-world applications This study hence aims to start filling this gap by investigating the existing body of knowledge systematically through a review in which the potential impacts of blockchain are presented and future avenues of research are set out. The review is based on 61 scientific articles published between January 2008 and January 2020. The review has been structured considering two frameworks: the business model elements of value creation, delivery, and capture and the different stages of evolution of blockchain applications. The results provide evidence and future direction for research that are valuable for both academics and managers.
Download
Paper Nr: 117
Title:

Scenario-Based Model Checking of Declarative Process Models
Authors:

Nicolai Schützenmeier, Martin Käppel, Myriel Fichtner and Stefan Jablonski
Abstract: Modeling processes with declarative process models, i.e. sets of constraints which have to be satisfied throughout the whole process execution, allows for a great degree of flexibility in process execution. However, having a process specified by means of symbolic, textual or formal constraints comes along with the problem that it is often hard for humans to understand complicated interactions of constraints and overlook the entire process model without unintentionally neglecting important process details. Caused by these reasons, standard questions regarding process models, e.g. ”Can a running process instance still be completed successfully?”, can often only be answered with great computational and temporal effort or even not at all. In this paper we present an efficient scenario-based approach for declarative process models, which supports process modelers in checking process models for important and common scenarios which regularly occur when modeling declarative processes. We implement our approach and show that the solutions for the scenarios can be computed within milliseconds even for real-life event logs. Furthermore, a user study conducted demonstrates that the error rate in understanding declarative process models is enormously reduced by using our implementation.
Download
Paper Nr: 120
Title:

The Future of Commerce: Linking Modern Retailing Characteristics with Cloud Computing Capabilities
Authors:

Christian Daase, Matthias Volk, Daniel Staegemann and Klaus Turowski
Abstract: The future of retail will be shaped by the rapidly evolving digital landscape. New technologies such as big data analytics, artificial intelligence, virtual reality, and cloud computing are expected to play a crucial role in advertising products, making personalized offers tailored precisely to customers’ needs, and thus meeting rising expectations in connection with the general improvement in living standards. In this paper, the characteristics of modern retailing and e-commerce in particular are examined in detail. Based on a systematic literature review, the nature of current and future retail business models is analyzed step by step, starting from more conceptual aspects to concrete underlying technological capabilities with the ultimate goal of leveraging cloud computing tools to realize them. Common proven practices are categorized, described, and assessed to provide a comprehensive overview of opportunities, challenges, and consequences in this area. Finally, the identified technological capabilities are aligned with adequate cloud services, exemplarily presented with tools of the Google Cloud.
Download
Paper Nr: 218
Title:

Recommender Systems in Business Process Management: A Systematic Literature Review
Authors:

Sebastian Petter and Stefan Jablonski
Abstract: Recommender systems have the potential to enhance decision-making and to improve business process exe- cution in the domain of Business Process Management (BPM). By analyzing data and providing personalized recommendations, these systems can assist users in making profound decisions and so foster the achievement of their business goals. In our study that is based on the PRISMA (Preferred Reporting Items for Systematic reviews and Meta-Analyses) methodology, we examine the usage of recommender systems in BPM, focusing on the objectives, methods, and input data utilized. We searched eight databases and included papers that focus on process execution and recommendation methods while excluding those that are not digitally available, not in English, patents, miscellany, or proceedings, or focused solely on business process modeling. This results in 33 papers, addressing the research questions, that are analysed in detail. The discussion highlights research gaps related to user preferences and input data, suggesting that further investigation is needed to enhance the effectiveness of recommender systems in business process management.
Download
Short Papers
Paper Nr: 4
Title:

Towards a Better Evaluation of Disaster Management Solutions
Authors:

Ovidiu Noran and Peter Bernus
Abstract: Worldwide, disaster management endeavours are confronted with a rising number of calamitous events triggered by climate change, pandemics and armed conflicts. The increasing rate and complexity of such occurrences has determined governments worldwide to attempt improving the disaster management effort by adopting various specialised artefacts, among which disaster management frameworks feature prominently. It appears however, that such artefacts display shortcomings such as lack of directly applicable guidance, ambiguity and a lack of agility in the face of constant change inherent to disaster events. This situation poses a conundrum to disaster management decision-makers who need to select such frameworks in the knowledge that they have the necessary qualities, employ a suitable architecture and contain the required elements to effectively guide the typically trans-disciplinary and cross-organisational disaster management effort. This paper seeks to assist in this regard by providing a novel, multi-pronged appraisal approach for candidate disaster management frameworks.
Download
Paper Nr: 10
Title:

Towards a Multi-Level Model of Enterprise Architecture Modeling Notations
Authors:

Ahmed Hussein and Simon Hacks
Abstract: Over the past few decades, the field of enterprise architecture (EA) has grown, and many EA modeling notations have been proposed. In order to support the different needs, the different notations vary in the element types that they provide in their metamodel. This abundance of elements makes it difficult for the end-user to differentiate between the various elements and complicates the model transformation between different EA model notations. Therefore, this research analyzes existing EA frameworks and their modeling notations and extracts common properties. First, we performed a literature review to identify common EA frameworks and their modeling notations. Second, based on the found notations’ concepts, we create a taxonomy based on their similarities that leads to a multi-level model of EA notations. Our results showed that The Open Group Architecture Framework, ArchiMate, Department of Defense Architecture Framework, and Integrated Architecture Framework are the most used EA frameworks. Those frameworks served as input for a multi-level model comprising the common concepts of the different modeling notations.
Download
Paper Nr: 12
Title:

A Recommender Plug-in for Enterprise Architecture Models
Authors:

Sashikanth Raavikanti, Simon Hacks and Sotirios Katsikeas
Abstract: IT has evolved over the decades, where its role and impact have transitioned from being a tactical tool to a more strategic one for driving business strategies to transform organizations. The right alignment between IT strategy and business has become a compelling factor for Chief Information Officers and Enterprise Architecture (EA) in practice is one of the approaches where this alignment can be achieved. Enterprise Modeling complements EA with models that are composed of enterprise components and relationships, that are stored in a repository. Over time, the repository grows which opens up research avenues to provide data intelligence. Recommender Systems is a field that can take different forms in the modeling domain and each form of recommendation can be enhanced with sophisticated models over time. Within this work, we focus on the latter problem by providing a recommender architecture framework eases the integration of different Recommender Systems. Thus, researchers can easily compare the performance of different recommender systems for EA models. The framework is developed as a distributed plugin for Archi, a widely used modeling tool to create EA models in the ArchiMate notation.
Download
Paper Nr: 51
Title:

Digital Transformation of Public Services from the Perception of ICT Practitioners in a Startup-Based Environment
Authors:

George Marsicano, Edna D. Canedo, Glauco V. Pedrosa, Cristiane S. Ramos and Rejane C. Figueiredo
Abstract: In 2021, the Brazilian government created the StartUp GOV.BR program to accelerate the digital transformation of the public sector in Brazil. Inspired by the business’s culture of startups, this program gathers ICT practitioners with multiple competencies dedicated to the planning, development and delivery of digital transformation projects. This article aims to investigate and understand the perception of these ICT practitioners about the StartUps GOV.BR program in order to identify possibilities for improvement. For this, we conducted 23 focus groups with up to 12 people, totaling 175 participants. Then, we fully transcribed and qualitatively analyzed the data from each of the focus groups based on the Grounded Theory. The results were organized and structured through the construction of models of relationships between categories, along with narratives that help to explain and understand the members’ perception of the StartUp GOV.BR program. As results, we present 34 improvement points and 62 actions to be carried out towards program improvement. The results achieved in this work can contribute to delineate growth strategies, as well as the assets and capabilities required in order to successfully transform digitally public services not only in Brazil but also in governments around the world.
Download
Paper Nr: 55
Title:

Effectual Behavior and Corporate Entrepreneurship in the Digital Age
Authors:

Stefano D’Angelo, Antonio Ghezzi, Angelo Cavallo, Andrea Rangone and Luca Marchetti
Abstract: While most studies have viewed effectuation as a tool to manage resources in the context of new ventures, few of them have directly investigated the effects of effectuation as a tool for Absorptive Capacity (AC) in the context of incumbent firms. Specifically, the relationship between the usage of an effectual logic and its impact on the knowledge and learning abilities of individuals, remains underexplored in Corporate Entrepreneurship (CE) context. We reframe effectuation as a concrete activity that enhances knowledge absorption and enlarges the scope of opportunities and in turn fosters entrepreneurial actions in organizations. Hypotheses are thus developed to examine the relationship between effectuation and Entrepreneurial Orientation (EO) as well as the mediating role of AC. Moreover, as digital skills can support the learning and knowledge absorption process, digital skills are proposed as a moderator that influences the positive effects of effectuation on AC. We test these hypotheses using the survey data from employees of an incumbent firm. The empirical results generally support our hypotheses by showing that (i) effectuation positively influences AC, and (ii) digital skills have a positive moderating effect on the relationship between effectuation and AC. No significant results emerged concerning hypothesis (iii) AC mediates the relationship between effectuation and EO. These findings contribute to our understanding of the role of effectuation in the context of CE in the digital era. Implications for managers are also included.
Download
Paper Nr: 60
Title:

A Systematic Literature Review on the Business Implications of 5G
Authors:

Mattia Magnaghi, Antonio Ghezzi and Andrea Rangone
Abstract: In a fast-changing environment as nowadays, fostered by cutting-edge digital technologies, opportunities may emerge and then disappear abruptly, for this reason, companies must be able to seek them to remain competitive. By looking at very relevant and recent technology, the 5G connectivity, how companies could leverage it experiencing a technology shift is still unclear, both from a practitioner and theoretical perspective. If on one hand, the 5G is a hotly discussed topic in non-social sciences, on the other hand, the managerial literature appears ambiguous and fragmented in the way it is presented. Such absence recalls for research whose purpose is to try to position the 5G search thread also in the business and management stream. The work aims to systematize previous knowledge and identify potential directions related to 5G technology in the above-mentioned literature.
Download
Paper Nr: 62
Title:

Modelling Digital Maturity for SMEs
Authors:

Niccolò Ulderico Re, Antonio Ghezzi, Raffaello Balocco and Andrea Rangone
Abstract: SMEs still suffer from a significant delay in digitalization compared to their larger counterparts. In order to develop effective public policies and digitization strategies, it is necessary to have tools that make it possible to assess the state of digitization of SMEs: digital maturity models. Literature review reveals a preponderance of tools developed for large firms or manufacturing SMEs. Applying multiple case study research, the present study models the behavior of the SMEs into a comprehensive maturity model. The contribution of this work is twofold. On one hand it confirms dimensions already considered as the subject of analysis by other researchers, strengthening their positions and completing them with some additional details. On the other hand, keeping in mind SMEs’ inherent variety, the originality of this study lies in the quest for a tailor-made assessment of the digitalization of SMEs.
Download
Paper Nr: 63
Title:

Emerging Technologies as Enabler of Sustainable Business Model Innovation: Evidence from Space Tech New Ventures
Authors:

Jacopo Manotti, Antonio Ghezzi, Andrea Rangone and Raffaello Balocco
Abstract: The growing humanitarian and environmental challenges our planet and society are facing today made the United Nations ratify the so-called 2030 Agenda for Sustainable Development, which encapsulates 17 Sustainable Development Goals (SDGs) with the aim of promoting social, environmental, and economic objectives. For commercial companies, embarking into sustainability is not an easy task, because of different tensions between profit and impact that make it difficult to fully align the commercial activities with the sustainability ones within the company’s business model. By mean of a multiple-case study analyzing 11 startups in the New Space Economy domain, this research sheds light on the use of the emerging satellite technology as enabler of sustainable business model innovation, adopting a technology-perspective in the mitigation of the so-called transaction obstacles to sustainability, making it clear how emerging technologies’ features may represent a solution to embed SDGs in firms’ business model.
Download
Paper Nr: 68
Title:

Towards a Reference Architecture for a Business Continuity
Authors:

Rūta Pirta-Dreimane and Jānis Grabis
Abstract: During turbulent times, enterprises need to find ways how to adapt, become resilient and strengthen abilities to cope with emerging threats. Business continuity management (BCM) is an enterprise strategic managerial capability. The recent global pandemic increased BCM maturity in many enterprises, still the importance of the capability is underestimated, and the enterprises are facing challenges to design and implement it across different enterprise architecture (EA) dimensions. In this paper, a business continuity (BC) framework for BCM capability development is proposed. The framework aims to provide guidance on design of BCM along different EA dimensions. It summarizes BC architecture principles and conceptualizes BC knowledge from related research as a reference architecture. The paper highlights challenges faced in BCM implementation, presents conceptual design of the BC Framework and its components. The application of the framework is demonstrated using an example from a target EA development project at a public sector institution.
Download
Paper Nr: 103
Title:

Towards a Governance Framework for Data Platform Ecosystems in the Construction Industry
Authors:

Samaneh Bagheri
Abstract: In today’s digital economy, the potential of using data platforms for secure and trusted business data exchange between distinct user groups within a data ecosystem becomes extremely significant. The construction industry is not exempted from the potential benefits of data platform ecosystems (DPEs). While for the effective orchestration of DPEs, appropriate governance is required, due to specific features of the construction industry, existing insights on the governance of DPEs may not be directly applicable to the data platforms in this industry. In this paper, we contribute to our understanding of this phenomenon by developing a governance framework for DPEs in the construction industry. To this end, we develop a governance framework by identifying governance mechanisms from the platform literature and investigating if and why these mechanisms are relevant in the construction industry by conducting a case study. The proposed framework offers an outline for the analysis of data platform governance and provides first insights about governance mechanisms that practitioners of the construction industry need to consider especially during the early stage of the DPEs development.
Download
Paper Nr: 107
Title:

A Situating Method for Improving the Utility of Information Products
Authors:

Anders W. Tell
Abstract: Information is driving enterprises and ecosystems forward. The availability of relevant, useful and timely information is important for discussions, decision-making, and action. Enterprise architecture is a field that provides frameworks, methods and stakeholder-oriented models as information enablers. However, stakeholder-based frameworks and methods may not identify and capture sufficient details about stakeholders’ work practices, pains and relationships between stakeholders. This paper presents a work-oriented approach with method parts and constructs that aim to improve the design, documentation, relevance, enactment, intention to use, use, and evaluation of information products, particularly in enterprise architecture. The explicit incorporation of detailed situational factors, relationships and roles, and actors’ work practices can improve relevance, effectiveness and other use-qualities of information products such as enterprise models. The method parts are designed to extend and be infused into enterprise architecture methods and frameworks, which can be ISO 42010-based.
Download
Paper Nr: 134
Title:

Towards Agile IT/Business Alignment at BizDevOps
Authors:

Guillermo Fuentes-Quijada, Francisco Ruiz-González and Angélica Caro
Abstract: BizDevOps extends DevOps with an additional business cycle that incorporates non-IT stakeholders. This additional cycle focuses on IT/Business alignment to better respond to the needs of organizations, but, so far, does not consider the challenge of agility. This can lead to a bottleneck in the software lifecycle, causing agility to be lost in the overall software lifecycle, even though the development and operations cycles, typical of DevOps, are agile. This position paper sets out a discussion of the problem and its relevance, the associated difficulties and possible approaches to a solution proposal. The difficulties identified correspond to four dimensions: stakeholders, processes, information, and resources. Among the most promising proposals to address the problem is Enterprise Architecture, but including agile practices, as included in the recent version 10 of the industry standard TOGAF.
Download
Paper Nr: 139
Title:

A Practical Method to Plan Co-Evolution of Business and Information Technology
Authors:

Sara Nodehi, Tim Huygh, Laury Bollen and Joost Visser
Abstract: In our fast-changing digital world, Business-IT alignment is not about reaching an end state where business and IT are aligned but about continuously adapting both IT and business to remain aligned with each other. Currently, managerial instruments for doing so are lacking or disconnected. We aim to provide a light-weight and easy-to-use managerial tool for regular re-alignment and co-evolution of organisational goals and software assets for technical and business-oriented stakeholders. Using a Design Science Research approach, we designed our planning method by conducting exploratory interviews to establish its requirements, reviewing pre-existing instruments, expanding upon them, and integrating them into a single planning process. As a result, we created a 5-step method for collaboratively creating, sharing, and monitoring so-called “evolution plans” and evaluated it in an educational pilot and through confirmatory expert interviews. Our method contributes to emerging research that complements established theoretical models of business-IT alignment with its practical operationalisation.
Download
Paper Nr: 145
Title:

A Process for Evaluating the Prudence of Enterprise Architecture Debts
Authors:

Ada Slupczynski, Peter Alexander and Horst Lichter
Abstract: Enterprise architecture (EA) debt represents a situation involving the declining quality of an EA in return for gains in other aspects. It accumulates through the sub-optimal architecture decisions made by the projects contributing to the EA. To avoid the reckless accumulation of EA debt, the impact of an architectural decision on EA debt and its prudence needs evaluation. However, as the scope of an EA debt issue tends to cover a wide range of systems and stakeholders, there may be different views on its prudence depending on the evaluation context. Failing to consider all relevant contexts may lead to reckless estimates and justifications for the EA debt. The analysis of prudence and recklessness exists in related fields of study (e.g., technical debt and financial debt). However, research has yet to explore the way to apply these concepts in EA debt management practices. Therefore, this study proposes a process for evaluating the prudence of EA debts, which we developed based on current insights about prudence and recklessness in related fields of study. Furthermore, we discuss some open questions and propose future research directions in this context.
Download
Paper Nr: 146
Title:

IT Service Well-Being: A Service Ecosystem Approach
Authors:

Maryam Heidari, Geraldine Torrisi and Sebastian Binnewies
Abstract: This research aims to explore the complex and dynamic nature of IT service well-being from a multi-level perspective of the service ecosystem. Most research in the IT service area focuses on individual and micro-level interactions and practices and overlooks the importance of a holistic and systematic view of understanding service well-being. This research addresses these limitations by exploring IT service well-being from a “service ecosystem” perspective. The research follows an interpretive approach to build a middle-range theory based on a case study and grounded theory technique in an educational institution. The findings reveal well-being drivers, determinants, and outcomes at the micro, meso and macro levels of the IT service ecosystem. This study contributes to research on well-being in the context of IT service by providing the wellbeing characteristics and conceptualisation in the IT service context, which has been barely investigated. This research is in progress.
Download
Paper Nr: 205
Title:

Towards an Ontology to Enforce Enterprise Architecture Mining
Authors:

Carlos R. Pinheiro, Sérgio Guerreiro and Henrique S. Mamede
Abstract: Enterprise Architecture (EA) is a coherent set of principles, methods, and models that express the structure of an enterprise and its IT landscape. EA mining uses data mining techniques to automate EA modelling tasks. Ontologies help to define concepts and the relationships among these concepts to describe a domain of interest. This work presents an extensible ontology for EA mining focused on extracting architectural models that use logs from an API gateway as the data source. The proposed ontology was developed using the OntoUML language to ensure its quality and avoid anti-patterns through ontology rule checks. Then, a hypothesized scenario using data structures close to the real is used to simulate the ontology application and validate its theoretical feasibility as well as its contribution to the Enterprise Architecture Management field.
Download
Paper Nr: 9
Title:

Modelling of Advanced Dependencies Between the Start and the End of Activities in Business Processes
Authors:

Thomas Bauer
Abstract: The control-flow of a business process (BP) defines the allowed execution orders of its activities. Until now, only whole activities can be used to define such orders. This shall be extended: Additional execution orders are enabled by allowing to use the start and the end events of activities at control flow modelling. For example, defining that the end of Act. A must happen before the end of Act. B, increases the flexibility since Act. B can be started earlier as with a classic sequence edge. This paper presents corresponding examples from practice and derives the resulting requirements for BP modelling. Furthermore, possibilities for a BP modelling tool are discussed, to visualize such dependencies graphically.
Download
Paper Nr: 17
Title:

Exploring the Role of Technological Change in the Relationship Between Strategic Innovation and Business Model Innovation: Evidence from a Cross-Industry Multiple Case Study
Authors:

Antonio Ghezzi, Jacopo Manotti, Andrea Rangone and Raffaello Balocco
Abstract: Business Model Innovation (BMI) has recently caught the eye of academics and practitioners in the broad fields of Strategy and Technology Management. However, the relationship between BMI and Strategic Innovation (SI) remains an open issue. Thus, this study aims at investigating the relationship between SI and BMI, focusing on the role technological change plays in it. To this end, we first propose a classification of Technological Change types according to three dimensions: trajectory, intent and effect. Second, based on this classification, we conduct a cross-industry multiple case study with 16 companies to understand how the relationship between SI and BMI is mediated or triggered by the nature of Technological Change taking place, giving rise to eight “innovation paths”. We also shed light on the key role played by different actors – top, middle and low management and key employees – in SI and BMI, according to their level of “technological change empowerment.
Download
Paper Nr: 53
Title:

Experimentation in Corporate Entrepreneurship: An Exploratory Multiple Case Study
Authors:

Stefano D’Angelo, Antonio Ghezzi, Angelo Cavallo, Andrea Rangone and Salvatore Annunziata
Abstract: Experimentation has become one the most influential approaches to entrepreneurship revolutionizing the way new businesses are launched and enabling entrepreneurs to test their business model through rigorous experiments. While there is a growing body of research investigating experimentation in a startup context, there is no corresponding literature exploring the role of experimentation in corporate entrepreneurship activities despite the increasing interest in experimentation among managers and the growing practitioner literature urging incumbent organizations to adopt experimentation. Recently, the ideas developed around experimentation have been taken up by incumbent organizations, with the promise that this approach can benefit corporate entrepreneurship activities by accelerating them, reducing resource expenditure, and increasing the chances of success. This is more relevant in the current context where companies have to face fast-changing customer needs and market trends, as well as the design of complex value propositions. Drawing on an exploratory multiple case study, this study explores how experimentation is conducted in incumbent organizations and used as a tool to support corporate entrepreneurship. Based on the findings of this study, we provide contributions to research and practice on experimentation in corporate entrepreneurship.
Download
Paper Nr: 59
Title:

Digital Corporate Entrepreneurship: How Digital Technologies Are Reshaping Entrepreneurship in Incumbents
Authors:

Stefano D’Angelo, Antonio Ghezzi, Angelo Cavallo, Andrea Rangone and Maria Gatti
Abstract: Digital technologies make new opportunities possible for entrepreneurship in incumbent organizations while making some of the older practices obsolete, thereby generating potential disruption for established firms. The digital entrepreneurship research field elucidates the potential implications of digital technologies for entrepreneurship. Despite its contemporary significance, however, existing research has largely neglected the role of digital technologies in corporate entrepreneurship, i.e., entrepreneurship in incumbent organizations. Through an exploratory multiple case study, our study helps to address this gap by providing a framework shading light on how incumbents can leverage the enabling role of digital technologies at organizational level (i.e., increasing the number and heterogeneity of inputs; increasing visibility of actors and resources involved in the project management) and project level (i.e., increasing innovations’ adoption rate in an existing corporate environment while managing their structural barriers. Based on the findings of this study, we contribute to corporate entrepreneurship research and practice.
Download
Paper Nr: 61
Title:

Digital Maturity Models for SMEs: A Systematic Literature Review
Authors:

Niccolò Ulderico Re, Antonio Ghezzi, Raffaello Balocco and Andrea Rangone
Abstract: In recent years widespread digitalization is pushing enterprises to enhance their products and services and their value propositions. Digital transition requires companies to adapt their organization. Small and medium-sized enterprises (SMEs) lag behind larger firms when it comes to digitalization. Digital maturity models are a valuable tool for policymakers and academia to understand the state of the art of digitalisation of SMEs. However, these models too often have focused on large firms and manufacturing firms and have often adopted a narrow field of investigation. This study, through a systematic analysis of the literature, highlights the main contributions to the literature on digital maturity models of SMEs and proposes a framework for the analysis and classification of the main variables analyzed, in order to allow future research to build models of holistic digital maturity for SMEs.
Download
Paper Nr: 104
Title:

Introduction to BASE Enterprise Architecture Framework for Holistic Strategic Alignment of the Complex Enterprise
Authors:

Ivka Ivas
Abstract: There are many enterprise architecture frameworks on the market, but despite being heavily promoted with promises of their expected benefits, in practice they have not proved to deliver expected value. The main reason for this is IT-oriented controlled reductionist approach inapplicable for a complex enterprise. In parallel with IT-oriented enterprise architecture business architecture was developed to support business strategy. But, as a pure business discipline, business architecture also did not prove to deliver expected value because, in a complex enterprise with business, which is highly dependent on IT, it is impossible to decouple business from IT because your business is your IT. This paper will, therefore, introduce the new Business Architecture-based Strategy-driven Enterprise architecture framework (BASE) for improving holistic strategic alignment of the complex enterprise by supporting both formulation and implementation of the enterprise strategy. As foundation of the BASE framework, which will be further explored in future work, this paper will present a business architecture-based enterprise architecture model for managing the complex enterprise, based on business architecture also providing business-adjusted IT insights, and holistic initiative footprinting methodology which will illustrate how to leverage business architecture and proposed EA model to properly scope strategic initiatives already early in the process.
Download
Paper Nr: 112
Title:

Improving Czech Digital Government Based on Quantified Maturity Model of Enterprise Architecture
Authors:

Martin Rod and Jiri Vomlel
Abstract: One of the current drivers for transitioning from the traditional E-Government to the digital government is the ability to create and share new services in the governmental ICT landscape. The government must effectively communicate and offer its services to itself (G2G) and outside, be it an end-consumer or business (G2C, G2B). Since the government is internally divided, there is a need to measure its parts’ performance for effective management. However, conventional maturity models cannot address and explain the cause of the differences, and thus typically respond to symptoms and show just winners and losers of the given benchmark. From this position, a study and a deeper analysis of the maturity model used in the public administration of Czechia are provided. Further analysis was undertaken via Bayesian networks to answer the question: How do project management and prioritization affect service level management? Or how the enterprise architecture as a method is linked to the overall organization’s performance? Significant relationships were identified, and the use of the Bayesian network as a prediction model was proposed. Further evaluation steps and research opportunities were discussed.
Download
Paper Nr: 160
Title:

A Literature Review of Evaluation Approaches for Cyber-Physical Production Systems
Authors:

Hector Hostos, Oscar Avila and Virginie Goepp
Abstract: The role of Cyber-physical production systems (CPPSs) as Industry 4.0 enablers has raised the interest to upgrade legacy production systems. However, manufacturers face uncertainty when assessing if the transformation process is worth it. In this context, the aim of this study is to review the works in the existing literature that approach the evaluation of CPPSs in a context of production systems’ transformation. To do so, we adopted a systematic literature review process that comprises the development of a framework of six review questions that help us to analyze and characterize the literature found. From the literature review, this paper presents a conceptual model that aims at establishing the basis for a complete approach for CPPS evaluation.
Download
Paper Nr: 187
Title:

BPM in the Era of Industry 4.0: A Bibliometric Analysis
Authors:

Hadjer Khider, Slimane Hammoudi, Abdelkrim Meziane and Alfredo Cuzzocrea
Abstract: In the age of today's technological development, with the advancement of the digitization of organizations, Industry 4.0 (I4.0) has evolved as a consequence of the fourth industrial revolution, leading industry to face a digital transformation (DT). This transformation is based on the use of cyber-physical systems (CPS) and information and communication technologies (ICT), in particular artificial intelligence (AI) and the Internet of Things (IoT). This new paradigm has brought changes in various areas of the functioning of the organization through a DT that holistically affects business processes, products, relationships and competencies which is a major challenge for organizations. This paper is dedicated to analyze the literature on BPM in the digital industry era through a bibliometric analysis, in order to analyze the impact of the I4.0 concepts and their associated technologies on the BPM, which will allow to determine the main BPM issues.
Download
Paper Nr: 207
Title:

An Exploratory of Factors Influencing of Digital Technology Adoption in Thai Maritime Industry: Perspective of Thai Shipowners
Authors:

Atcharaporn Janmethakulwat and Bundit Thanasopon
Abstract: This study addresses a literature gap in the maritime sector concerning the slow adoption of digital technology by Thai shipowners to drive sustainable organizational development. Understanding the determinants of digital technology adoption is crucial. Thus, this study examines the adoption process of digital technology in Thai shipowners at the firm-level, specifically focusing on the perceived influence of technology, organization, and environment. The study employs an exploratory approach and utilizes in-depth case studies to build theory. The findings suggest that factors such as improved organizational efficacy, reduced operational expenses, enhanced internal and external communication, top management support and commitment, plan maintenance monitoring, documentation, compliance with legal, regulatory, and policy requirements, and social pressure positively influence the adoption of digital technology in Thai shipowners.
Download