ICSBT 2022 Abstracts


Area 1 - Business Intelligence

Full Papers
Paper Nr: 12
Title:

Lowering Big Data Project Barriers: Identifying System Architecture Templates for Standard Use Cases in Big Data

Authors:

Matthias Volk, Daniel Staegemann, Akanksha Saxena, Johannes Hintsch, Naoum Jamous and Klaus Turowski

Abstract: For almost a decade now, big data has become the foundation of today’s data-intensive systems used for various disciplines, such as data science or artificial intelligence. Although a certain level of maturity has been reached since then, not only in the domain itself but also in the engineering of interconnected systems, many problems still exist today. The number of available technologies and architectural concepts, whose application is often very use case-specific, makes the successful implementation of big data projects still a non-trivial undertaking. To overcome this problem and deliver support with the realization of a related project, existing standard use cases in this domain are analyzed, and architectural concepts are derived through the design science research methodology. By observing essential criteria, like use case descriptions as well as relevant requirements, decision-makers can harness architectural concepts and technology recommendations for their setup.
Download

Paper Nr: 16
Title:

HyperEstimator: Evolving Computationally Efficient CNN Models with Grammatical Evolution

Authors:

Gauri Vaidya, Luise Ilg, Meghana Kshirsagar, Enrique Naredo and Conor Ryan

Abstract: Deep learning (DL) networks have the dual benefits due to over parameterization and regularization rendering them more accurate than conventional Machine Learning (ML) models. However, they consume massive amounts of resources in training and thus are computationally expensive. A single experimental run consumes a lot of computational resources, in such a way that it could cost millions of dollars thereby dramatically leading to massive project costs. Some of the factors for vast expenses for DL models can be attributed to the computational costs incurred during training, massive storage requirements, along with specialized hardware such as Graphical Processing Unit (GPUs). This research seeks to address some of the challenges mentioned above. Our approach, HyperEstimator, estimates the optimal values of hyperparameters for a given Convolutional Neural Networks (CNN) model and dataset using a suite of Machine Learning algorithms. Our approach consists of three stages: (i) obtaining candidate values for hyperparameters with Grammatical Evolution; (ii) prediction of optimal values of hyperparameters with supervised ML techniques; (iii) training CNN model for object detection. As a case study, the CNN models are validated by using a real-time video dataset representing road traffic captured in some Indian cities. The results are also compared against CIFAR10 and CIFAR100 benchmark datasets.
Download

Paper Nr: 21
Title:

Meta-semantic Search Engine Method Proposition for Transparent Decision Auditing

Authors:

Lucas C. de Almeida, Francisco C. Filho, Fábio L. L. de Mendonça and Rafael D. Sousa Jr.

Abstract: The use of search tools in decision-making and investigation processes has been gaining more and more space in the forensic community. The ability to index various sources of information and to be able to filter specific snippets and ideas is one of the milestones in the history of forensic and investigative computing. However, the widespread use of these methods, such as semantic search engines based on deep learning and machine learning methods can generate impractical results for complex cases. That’s because the criteria these machines use to classify snippets of natural languages can be so complex that they’re no longer auditable. Therefore, if a machine produces results that cannot be verified and explained, it is producing inferences that are highly questionable or even worth nullifying. In this work, we explore the advantages of applying data enrichment before the search process, and the subsequent use of keyword search tools to present an indexing framework with more transparent criteria and more practical results for the defense of ideas based on the findings from the use of the tools.
Download

Short Papers
Paper Nr: 1
Title:

The Role of Digital Marketing in Increasing SMEs' Competitiveness

Authors:

Rui P. Silva, Henrique Mamede and Arnaldo Santos

Abstract: With the significant increase of technology-based newer competitors and the digital economy reshaping the global economic environment, it is undoubtful that the market is becoming aggressively more demanding for small and medium enterprises, which is a strong driver of their need to adopt new digital technologies and transform their businesses. Events such as the COVID-19 pandemic have accelerated the online engagement of consumers, and that also means that digital transformation might not only be about the digitalisation of internal processes and reshaping of business models but as well, and not least relevant, the Strategies used by SMEs to position themselves in the market and maximise the value of digital marketing to regain competitiveness and reposition their products.
Download

Paper Nr: 11
Title:

Advanced Analytics in Central Banks: Basic Assumptions and Preliminary Results of a Research Project

Authors:

Matthias Goeken and Leni Hirdes

Abstract: This position paper presents methodological considerations and ideas as well as preliminary results of a research project. We argue that integrating design science (DS) and review research is useful for developing artifacts that serve, for example, to share knowledge within a domain. Our project aims to support knowledge sharing in central banking by means of systematic reviews. Such a consolidated body of knowledge can also be considered an artifact in the sense of DS research. We demonstrate how such a review can be conducted and what results it yields. Since it is not clear whether such an application of systematic reviews is relevant and feasible, problem definition and objectives of the project are discussed.
Download

Paper Nr: 15
Title:

Effects of the Coronavirus Pandemic on Youth Mobility: A Case Study Analysis through Floating Car Data

Authors:

Simone Porru, Francesco E. Misso, Silvia Manca and Cino Repetto

Abstract: Among mobility data sources, Floating Car Data plays a very, and increasingly, significant role, and has been extensively used to obtain traffic information. In this study, FCD has been used to shed light upon the youth mobility changes occurred during the first two years of the coronavirus pandemic by focusing on five selected high schools in Modena Municipality (Italy). Mobility indicators computed within the areas under investigation show that two out of the three schools’ areas are not associated to a significant variation in the number of detected distinct private probe vehicles from November 2019 to November 2021 (-3% and +1%), whereas within the Modena Municipality results show a 8% decrease. However, one out of the three schools’ areas shows a significant decrease in 2021 when compared to 2019 (-11%), suggesting a noticeable decrease in private vehicles traffic density that could be due to an increased use of personal mobility vehicles, such as bikes. Moreover, results within the Modena Municipality suggest that in 2021, even if the number of detected vehicles was lower than in 2019, each vehicle not only covered a longer distance on average, but also the total distance covered by all the vehicles together was longer (14% increase).
Download

Paper Nr: 19
Title:

Predicting Customer Behavioural Patterns using a Virtual Credit Card Transactions Dataset

Authors:

Ayrton S. Azzopardi and Joel Azzopardi

Abstract: Nowadays, many businesses are resorting to data mining techniques on their data, to save costs and time, as well as to understand customers’ needs. Analysing such data can leader to higher profits and higher customer satisfaction. This paper presents a data mining study that is applied on millions of transactional records collected for a number of years, by a leading virtual credit card company based in Malta. In this study, 2 machine learning techniques, namely Artificial Neural Networks (ANN) and Gradient Boosting (GBM), are analysed to identify the best modelling framework that predicts the churning behaviour of this company’s customers. Apart from helping the marketing department of this firm by providing a model that predicts churning customers, we contribute to literature by identifying the minimum amount of customer activity needed to predict churn. In addition, we also analyse the “cold start” problem by performing a time-series experiment based on the few data available at the beginning of the customer purchase history.
Download

Paper Nr: 7
Title:

Adapting the (Big) Data Science Engineering Process to the Application of Test Driven Development

Authors:

Daniel Staegemann, Matthias Volk and Klaus Turowski

Abstract: Knowledge, information, and modern technologies have become some of the most influential drivers of today’s society, consequently leading to a high popularity of the concepts of big data (BD). However, their actual harnessing is a demanding task that is accompanied by many barriers and challenges. To facilitate the realization of the corresponding projects, the (big) data science engineering process (BDSEP) has been devised to support researchers and practitioners in the planning and implementation of data intensive projects by outlining the relevant steps. However, the BDSEP is only geared towards a test last development approach. With recent works suggesting the application of test driven development (TDD) in the big data domain, it appears reasonable to also provide a corresponding TDD focused equivalent to the BDSEP. Therefore, in the publication at hand, using the BDSEP as a foundation, the test driven big data science engineering process (TDBDSEP) is proposed, facilitating the application of TDD in the big data domain and further enriching the discourse on BD quality assurance.
Download

Paper Nr: 17
Title:

Investigation the Influence of Marketing-mix Efforts on Brand Equity in the Bangladesh Software Industry

Authors:

Md. T. Hasan, Mohasina Akter, Sakib I. Shuhrid, Tanvir A. Khan, Farzana Sadia and Mahady Hasan

Abstract: Brand equity is a vital metric for measuring a brand’s health, and monitoring it on a regular basis is an important part of efficient brand management. An already developed model is being used to examine the relationships among marketing-mix efforts (channel/place, price, promotion, and after-sales service), and three dimensions of brand equity (brand awareness, perceived quality, and brand loyalty). The goal of our research was to see how the marketing mix (pricing, product, place, promotion) and after-sales services affected three aspects of brand equity. The model is tested in the context of the Bangladesh software sector. The study focused more on the hypothesis that checks Bangladesh’s software industry perspective. It’s a descriptive survey in which the necessary information was gathered through a questionnaire. 70 responses were selected as sample data to analyze. The correlations between research variables have been investigated utilizing SPSS (correlation and regression) and Amos software. Structural equation modeling is used to test the model and research hypotheses. Cronbach’s alpha was used to confirm reliability. Perceived quality is placed as a mediator between the marketing mix efforts and brand equity. The results show that few of the marketing-mix efforts and threedimensions of brand equity have significant relationships with brand equity.
Download

Area 2 - Business Models and Business Processes

Full Papers
Paper Nr: 4
Title:

The Role of Marketplaces for the Transformation from Robotic Process Automation to Intelligent Process Automation

Authors:

Thomas Neifer, Paul Bossauer, Dennis Lawo, Robert Volkening and Andreas Gadatsch

Abstract: The corporate landscape is experiencing an increasing change in business models due to digitization. An increasing availability of data along the business processes enhance the opportunities for process automation. Technologies such as Robotic Process Automation (RPA) are widely used for business process optimization, but as a side effect an increase in stand-alone solutions and a lack of holistic approaches can be observed. Intelligent Process Automation (IPA) is said to support more complex processes and enable automated decision-making, but due to the lack of connectors makes the implementation difficult. RPA marketplaces can be a bridging technology to help companies implement Intelligent Process Automation. This paper explores the drivers and challenges for the adoption of RPA marketplaces to realize IPA. For this purpose, we conducted ten expert interviews with decision makers and IT staff from the process automation sector.
Download

Paper Nr: 14
Title:

Towards Security- and IIoT-Aware BPMN: A Systematic Literature Review

Authors:

Markus Hornsteiner, Christoph Stoiber and Stefan Schönig

Abstract: The Industrial Internet of Things (IIoT) paradigm constitutes the connection of uniquely identifiable things to the internet in an industrial context. Besides providing disruptive capabilities for companies, its connectivity and heterogeneous setup makes it vulnerable to external attacks. To properly implement security by design in the IIoT, the underlying business processes must be modelled both IIoT- and security-aware. Business Process Modeling and Notation (BPMN) is a suitable language for this purpose. In order to present the current state of research in this area, this study compares the requirements from practice and research on the basis of the EU security standard IEC62443 and reviews the current state of research in security- and IIoT-aware BPMN extensions. The findings contribute to the structured elaboration of this ambiguous research field while also elucidating the interplay of IIoT and security within BPMN. The derived research gaps constitute an agenda for further research and may guide further research endeavours in enhancing security within the IIoT.
Download

Paper Nr: 18
Title:

Diversity of Open Intellectual Capital Acquisition by SMEs of Different Branches

Authors:

Tomasz Sierotowicz

Abstract: Research studies on intellectual capital (IC) focus on its utilisation by mainly large enterprises and its effect on selected indicators. IC is subject to single-stream analyses as an internal enterprise resource. Because IC is used in the business operations of enterprises, it must be acquired. This paper presents the results of research conducted in an unexplored field of IC acquisition. This research focused on innovative small- and medium-sized enterprises (SMEs) belonging to the two branches of software and hardware development in Poland (2008–2019). Empirical data were obtained in time series form using dedicated statistical tools, including the dynamic rate. The main conclusion of a comparative analysis revealed that IC acquisition in the SMEs in this research should be described as a simultaneous dual-stream (internal and external) process, and IC acquisition differs significantly between compared branches. Thus, the open IC (OIC) concept should be used in IC acquisition research. Future research can focus on comparative analyses of enterprises belonged to different branches, thereby extending our knowledge of the importance of OIC in business.
Download

Short Papers
Paper Nr: 3
Title:

Collaborative Business Model Structures for a Digital Care Platform: Value Proposition, Partners, Customer Relations, and Revenues

Authors:

Jelena Bleja, Sara Neumann, Tim Krüger and Uwe Grossmann

Abstract: The shortage of skilled workers and complex challenges arising from the aging of society, emphasize the relevance of collaboration between stakeholders. Furthermore, a collaboration between interdisciplinary stakeholders gather expertise and practical knowledge to successfully establish a collaborative business model on the market. Especially in the care sector, this need becomes clear. For this, a digital care platform is developed to efficiently manage the shortage of skilled workers, connect people with assistant needs and service providers in a cost-efficient manner and distribute efficiency gains throughout the collaboration network. This makes a collaborative business model that presents the way collaboration is to be built necessary and shows financing as well as efficiency gains and revenue allocation possibilities between the stakeholders. Thus, collaborative business model structures are presented in this paper to show how a collaboration of stakeholders can be successful. The analyses show the many possibilities to finance a care platform depending on the chosen business model. Especially promising seems to be a combination of financing models. The identified further challenge is to emphasize the added value a care platform brings to service providers and users alike.
Download

Paper Nr: 20
Title:

What Do We Need to Collaborate? Transfer in Universities for Cross-organizational Collaboration

Authors:

Claudia Doering, Finn Reiche and Holger Timinger

Abstract: In addition to education and research, the Third Mission is one of the pillars of today’s universities. The third mission includes lifelong learning, transfer, and community engagement. It comes with new tasks and activities for dedicated resources. To fulfil these tasks, many universities are looking for cross-organizational cooperation. However, there is no standardized framework for such cooperation. In this paper, such a framework for support processes is presented. It aims to provide a standardized approach to building cross-organizational collaboration to accomplish the tasks associated with the third mission. The framework is derived by applying the Design Science research approach. An initial evaluation is carried out by expert reports. The framework has the potential to facilitate the establishment of new collaborations and structure their joint activities.
Download

Paper Nr: 23
Title:

Hybrid Approach to Business Software Development in Terms of Current Needs and Requirements

Authors:

Aneta Poniszewska-Marańda and Martyna Tyran

Abstract: Business traditional software development methods rely on a work plan to extract complete sets of documentation, architectural, and high-level project development and control requirements. Agile has gained immense popularity in the field of computer science in recent years, although it combines acceptable software engineering practices with the controversial ones. The software industry has finally come to the conclusion that specific project characteristics such as purpose, scope, requirements, resources, architecture and size determine the methodology that best fits the project realities. The paper presents hybrid approaches, combining the PRINCE2 methodology and the Scrum method, in order to take maximum advantage of the methodologies and minimize their disadvantages by using the strengths of one methodology on the weaknesses of the other.
Download

Paper Nr: 25
Title:

Toward a Context-aware Process Model Repository

Authors:

Hadjer Khider, Slimane Hammoudi and Abdelkrim Meziane

Abstract: Many challenges face the enterprises in constantly changing business environment. This requires them to continually consider the context(s) in which they operate to better respond to the challenges they face. Business Process Management (BPM) has become an important approach to create efficient business processes (BPs), which can evolve quickly to adapt to a rapidly changing business environment. The reuse of already designed BP models can improve the agility of defined BPs to address new issues that arise in today’s rapidly evolving business environment. Involving context into the current process model repositories is a real challenge. In this paper, we propose an architecture for context-aware process model repository to improve the reusability of the BP models and better meet the expectations of its stakeholders. We also present in this paper a comparative study of the different context-aware BPM approaches, in addition to the contextual factors that influence the reuse of BP models in the current process model repositories.
Download

Paper Nr: 2
Title:

Customer Data-driven Business Models: A Case Study in the Retail Industry

Authors:

Maider Elorza and Eduardo Castellano

Abstract: In today’s data era, the retail industry has increased the possibility of acquisition of a large volume of customer data, becoming more achievable its monetization. This paper develops a literature research and an empirical study identifying the different strategies that organizations perform and their instantiation by a concrete retailer. In each of these strategies, there have been identified the reasons for the case study to implement them as well as the specific instantiation performed. The research enriches the literature twofold; (1) by adding the Retail Media strategy as an indirect customer data monetization strategy; (2) by identifying relevant elements of the investment-cost-revenue structure for the different customer data monetization strategies.
Download

Area 3 - Technologies and Applications

Full Papers
Paper Nr: 8
Title:

An Intrinsic Human Physical Activity Recognition from Fused Motion Sensor Data using Bidirectional Gated Recurrent Neural Network in Healthcare

Authors:

Okeke Stephen, Samaneh Madanian and Minh Nguyen

Abstract: An intrinsic bi-directional gated recurrent neural network for recognising human physical activities from intelligent sensors is presented in this work. In-depth exploration of human activity data is significant for assisting different groups of people, including healthy, sick, and elderly populations in tracking and monitoring their level of healthcare status and general fitness. The major contributions of this work are the introduction of a bidirectional gated recurrent unit and a state-of-the-art nonlinearity function called rectified adaptive optimiser that boosts the performance accuracy of the proposed model for the classification of human activity signals. The bidirectional gated recurrent unit (Bi-GRU) eliminates the short-term memory problem when training the model with fewer tensor operations, and the nonlinear function, a variant of the classical Adam optimiser provides an instant dynamic adjustment to the adaptive models’ learning rate based on the keen observation of the impact of variance and momentum during training. A detailed comparative analysis of the proposed model performance was conducted with long-short-term-memory (LSTM), gated recurrent unit (GRU), and bi-directional LSTM. The proposed method achieved a remarkable landmark result of 99% accuracy on the test samples, outperforming the earlier architectures.
Download

Short Papers
Paper Nr: 10
Title:

In Pursuit of Preserving Namibian Languages: The Development of the Ndungika App, an Oshiwambo Children’s Android Application

Authors:

Setson P. Vatilifa, Victoria T. Hasheela-Mufeti and Lukas H. Julius

Abstract: Indigenous languages are often at risk of extinction, especially if they are not well preserved, and when their native speakers seldom practice it. Namibian indigenous languages are not spared from this risk, due to the fact that the children are most often from various tribes, especially in cities, and they normally communicate in English as the sole official language used in Namibia schools. As children grow, they tend to become resistant to using home languages and exhibit an increasing desire to conform to the majority language speakers. Many recent studies have focused on the importance of preserving languages through teaching of children songs, poems and stories. The purpose of this research was to collect Oshiwambo language children’s songs, poems and stories and to develop an android application to host them. This was a randomized study. Children from 3 to 15 years of age, fluent in speaking any of the 13 Oshiwambo dialects were eligible for participation. Participants were randomly selected and through structured interviews, they were asked to sing any song in any of Oshiwambo languages or tell the story or a poem, and they were audio/video recorded. The designed application is envisaged to help in the language’s preservation.
Download