Connor Clarkson, Michael Edwards, Xianghua Xie

Defect detection has achieved state-of-the-art results in both localisation and classification of various types of defects, manufacturing domains is no exception to this. Just like in many areas of computer vision there is an assume of very high-quality datasets that have been verif ied by domain experts, however labelling such data has become an increasing problem as we require greater quantities of it. Within defect detection the variability and composite nature of defect characteristics makes this a time-consuming and interaction-heavy task with great amount of expert effort. We propose a new acquisition function based on the similarity of defect properties for refining labels over time by showing the expert only the most required to be labelled. We also explore different ways in which the exp ert labels defects and how we should feed these new refinements back into the model for utilising new kno wledge in an effortful way. We achieve this with a graphical interface that provides additional inform ation as data gets refined into a dense segmentation, allowing for decision-making with uncertain areas of the image.

Maximilian Helms, Audris Umel, Julia Bosbach, Pia Gebbing, Christoph Lattemann

Digital transformation (DT) is changing work contexts and conditions at large. Employees must adapt to new work modes and organizationa l structures, while learning no vel tools and skills. Such changes are impacting employees’ well-being, which in turn affects company success. However, how DT changes the workplace and employee well-being depends on the characteristic s of the work, e.g. knowledge/office work versus field/task work. Additionally, perceptions on how DT affects well-being, particularly physical health and psychological needs, differ among employees depending on socio-demographic factors like age and parental status. Hence, this study investigates the impact of DT on well-being on two levels of analysis: industry and employee. Using sel f-determination theory and a qu alitative approach, this study applied surveys and focus groups with 36 experts from craftsmanship and from consulting. Results show different effects on various dimensions of well-being in the two industri es. Further, the effects depend on the life stages of employees and their work domains. This research offer s insights for further exploration of DT impacts and strategies for practical implementation.

Bo Song, Wanting Ma, Zuhua Jiang, Ping Fang

Knowledge graphs have been widely used in recent years to build recommendation systems. However, in related research, the main focus has been on improving recommen dation algorithms, with less attention paid to the type of knowledge graph that is more conducive to k nowledge recommendations. This paper addresses knowledge recommendati on systems in the shipbuilding domain by constructing knowledge graphs in two ways and comparing their performance in knowledge recommendation. One type of knowledge graph is built based on classification tags of knowle dge documents, characterized by its simplicity and sparsity; the other is constructed automatically using machine learning, linking knowledge documents together based on concepts and relationships extracted by the algorithm, featuring complexity and density. To recommend shipbu ilding knowledge, a context-awa re mechanism was employed, gathering information from the user's task environment and linking it to the knowledge graph. Then, using RippleNet, the system spreads the user's interests within the k nowledge graph and infers the required knowledge documents. Experimental results show that the sparse knowledge graph achieved better recommendation results. We believe this is due to the human exp ert experience relied upon during the construction of the sparse knowle dge graph, namely a knowledge classification system oriented towards knowledge applications.

Jean-Christophe Sakdavong, Pierre Puigpinos, Nicolas Loiseau, Adrien Bruni

This paper explores the concept of self-efficacy and its impact on help seeking and individual performance on a mobile learning application. Self-efficacy refers to one's belief in their ability to achieve their goals and is a key factor in everyday life. Help-seeking while learning is an important part of the learning. This article will focus on the typol ogy differentiating choosing ins trumental help or executive help. As to investigate the relationship between self-efficacy, help-seekin g type and performance, we conducted an experiment with 104 participants, which consisted of two parts. First, we evaluated their self-efficacy levels using a survey designed to assess their perceived self-efficacy levels before and after their learning. Second, we asked participants to learn to pilot a drone in a virtual environment providing instrumental and executive helps that they can choose. Our findings demonstrate that if self-efficacy increases, the individual learning performance will also increase. We also confirmed that the use of instrumental helps has a positive influence on the learning performance, and that the use of executive help has the opposite effect.

Simon Pfenning, Raul C. Sîmpetru, Niklas Pollak, Alessandro Del Vecchio, Dietmar Fey1 1Chair of Computer Architecture, Friedrich-Alexander-Universität Erlangen-Nürnberg, Erlangen Researcher

The advancements in deep neural network design have led to a significant increase in the possibilities and functioning of AI-assisted medical hardware. To make use of thi s progress in the field of mobile applications or even as wearable devices, a suitable hardware-s oftware ecosystem must be identified to meet the high computation and memory demands of neural networks with minimal energy consumption. In this paper, we analyze an up-to-date heterogenous embedded platform employing a deep convolutional network for hand position recognition through electromyography signals. Our evaluation aimed to determine the optimization efforts required for the architectur e to function as a human wearable device and identify the most suitable accelerators on the given platform for this task.

Mikhail David Edwards, Hanlie Smuts

Business model innovation (BMI) hol ds significant importance in today's digital landscape, empowering enterprises to leverage disruptive technology for value creation and competitive advantage. However, the rapid evolution of these technologies presents various challenges, including uncertain market conditions, potential financial risks during the initial phases, employee resistance, and the risk of distraction from core responsibilities. This research aimed to identify the character istics essential for the successful implementation of BMI through effe ctive utilization of disrupti ve technologies. This was accomplished through a thorough review of existing literature, organizing critical success factors into the business model canvas framework, and applying a framework for identifying and classifying digital technologies based on demand. The findings underscored the importance of trust, efficiency, and adaptability across various BMI components. Technologies like Artificial Intelligence enhance objective alignment and personalized client experiences, while blockchain te chnology fosters trust and tran sparency. Cloud computing, on the other hand, enhances resource accessibility and flexibility. To achieve optimal BMI in today's digital landscape, it is important for organisations to proactively integrate thes e technologies into their operations, while fostering adaptability and engaging stakeholders.

Maximilian Rosenberg, Bettina Schneider, Christopher Scherb, Petra Maria Asprion

The topic of cybersecurity is becoming increasingly important as the number of cyberattacks continues to grow; it is no longer just a matter of protecting, but rather o f detecting cyberattacks at an early stage and responding accordingly. Detecting cyberattacks in organisations is an increasingly difficult task, since the ability of malware to hide from Anti-Virus systems has massively improved. Therefore, more sophisticated security measures are required, to protect complex information systems from cyberthreats. One of the state-of-the-art solutions is a ´Security Information and Event Management´ (SIEM) system, which collects all security related information and events on a centr al location. Thus, it is possible to correlate and better analyse security-rel ated events, detect, and defend sophisticated threats. The deployment of a SIEM system (SIEMS) is a process where all devices in the network need to be registered and integrated. There is no generic model for the evaluation, deployment, and operation of a sufficient SIEMS that can be applied independently of the dedicated vendor. Usually, vendors provide deployment guides for their SIEMS; however, these are product-specific and not scientifically evaluated. Applying Design Science as methodological approach, the goal of this research was to devel op and scientifically validate a generic model called ´EDO4SIEM´ for the vendor-neutral evaluation, deployment, and operation of a SIEMS in organisations. As desire for future research, the model should be applied in various organisations to confirm its applicability and to further develop it.

Richard Dabels, Marvin Davieds, Frank Russow, Thomas Mundt

The Internet of Things (IoT) is fragmented into many different smart environments, each requiring specific technical solutions for their use cases. This is a problem that has worsened over the years as new standards and technologies are constantly being developed. The term “horizontal integration” is used in literature to describe the attempt to reunite this fragmented IoT landscape. Abstract (in the sense of the OSI model) solutions are often proposed for this. However, the limitations of the underlying technologies are rarely sufficiently pointed out. This paper examines the integration of two smart environments as examples – the Smart Home and the Smart City. More specifically, it takes a theoretical look at how technologies can be connected between two Smart Home systems with the help of a Sma rt City technology and the problems that arise with it. ZigBee and LoRa are used for this purpose as exemplary technologies. Various possible application scenarios are shown to carry out a qualitative asse ssment of the feasibility of such a solution. The resulting problems of such an integration are shown and possible solutions for these are discussed.

Hanlie Smuts, Paul Louw, Danie Smit, Ingo Waechter, Vanessa Sardinha-da Silva

Software development, integration, deployment, and operational management necessitate a diverse array of complex skills. Additionally, t here is a growing demand for organizations to expedite the delivery of product-based applications and services compared to traditional software development methods, all while adhering to specific cost, speed , and quality criteria. To addr ess these challenges, IT organizations adopt a DevOps approach, structuring their software teams to integrate development and operations seamlessly. As the complexity varies acro ss different product lines, determ ining the ideal mix of DevOps workforce becomes important. In this case study, we formulated a generic DevOps workforce profile for product line delivery using stratified systems theory, which considers weighted factors influencing the workforce mix. We then compared this profile with actual workforce data to identify the optimal alignment. Furthermore, qualitative data from 17 product line owners within the organiz ation delineated their key considerations when allocating workforce to DevOps teams. By conducting a them atic analysis of these considerations, we refined the workforce allocation method and proposed a set o f systematic guidelines to help organizations better grasp the distribution of DevOps workforce mix, thereby enabling them to staff teams with an optimal balance of expertise, delivery quality, and ope rational efficiency. This enhanced understanding can further inform talent development and allocation strategies.

Pedro Isaías

Editorial preface for Volume 19, Issue 1 of the IADIS International Journal on Computer Science and Information Systems (IJCSIS). This issue brings together peer-reviewed original research contributions covering the wide spectrum of Information Systems, Artificial Intelligence, Software Engineering, and Digital Transformation.