http://dl.gi.de/handle/20.500.12116/39734 Thu, 23 Jul 2026 03:45:59 GMT 2026-07-23T03:45:59Z http://dl.gi.de/handle/20.500.12116/40227 Design Knowledge for Deep-Learning-Enabled Image-Based Decision Support Systems Landwehr, Julius Peter; Kühl, Niklas; Walk, Jannis; Gnädig, Mario With the ever-increasing societal dependence on electricity, one of the critical tasks in power supply is maintaining the power line infrastructure. In the process of making informed, cost-effective, and timely decisions, maintenance engineers must rely on human-created, heterogeneous, structured, and also largely unstructured information. The maturing research on vision-based power line inspection driven by advancements in deep learning offers first possibilities to move towards more holistic, automated, and safe decision-making. However, (current) research focuses solely on the extraction of information rather than its implementation in decision-making processes. The paper addresses this shortcoming by designing, instantiating, and evaluating a holistic deep-learning-enabled image-based decision support system artifact for power line maintenance at a German distribution system operator in southern Germany. Following the design science research paradigm, two main components of the artifact are designed: A deep-learning-based model component responsible for automatic fault detection of power line parts as well as a user-oriented interface responsible for presenting the captured information in a way that enables more informed decisions. As a basis for both components, preliminary design requirements are derived from literature and the application field. Drawing on justificatory knowledge from deep learning as well as decision support systems, tentative design principles are derived. Based on these design principles, a prototype of the artifact is implemented that allows for rigorous evaluation of the design knowledge in multiple evaluation episodes, covering different angles. Through a technical experiment the technical novelty of the artifact’s capability to capture selected faults (regarding insulators and safety pins) in unmanned aerial vehicle (UAV)-captured image data (model component) is validated. Subsequent interviews, surveys, and workshops in a natural environment confirm the usefulness of the model as well as the user interface component. The evaluation provides evidence that (1) the image processing approach manages to address the gap of power line component inspection and (2) that the proposed holistic design knowledge for image-based decision support systems enables more informed decision-making. The paper therefore contributes to research and practice in three ways. First, the technical feasibility to detect certain maintenance-intensive parts of power lines with the help of unique UAV image data is shown. Second, the distribution system operators’ specific problem is solved by supporting decisions in maintenance with the proposed image-based decision support system. Third, precise design knowledge for image-based decision support systems is formulated that can inform future system designs of a similar nature. Sat, 01 Jan 2022 00:00:00 GMT http://dl.gi.de/handle/20.500.12116/40227 2022-01-01T00:00:00Z http://dl.gi.de/handle/20.500.12116/40226 A Dark Side of Telework: A Social Comparison-Based Study from the Perspective of Office Workers Maier, Christian; Laumer, Sven; Weitzel, Tim Telework became a necessary work arrangement during the global COVID-19 pandemic. However, practical evidence even before the pandemic also suggests that telework can adversely affect teleworkers’ colleagues working in the office. Those regular office workers may experience negative emotions such as envy which, in turn, can impact work performance and turnover intention. In order to assess the adverse effects of telework on regular office workers, the study applies social comparison theory and suggests telework disparity as a new theoretical concept. From the perspective of regular office workers, perceived telework disparity is the extent to which they compare their office working situation with their colleagues’ teleworking situation and conclude that their teleworking colleagues are slightly better off than themselves. Based on social comparison theory, a model of how perceived disparity associated with telework causes negative emotions and adverse behaviors among regular office workers was developed. The data were collected in one organization with telework arrangements (N = 269). The results show that perceived telework disparity from the perspective of regular office workers increases their feelings of envy toward teleworkers and their job dissatisfaction, which is associated with higher turnover intentions and worse job performance. This study contributes to telework research by revealing a dark side of telework by conceptualizing telework disparity and its negative consequences for employees and organizations. For practice, the paper recommends making telework practices and policies as transparent as possible to realize the maximum benefits of telework. Sat, 01 Jan 2022 00:00:00 GMT http://dl.gi.de/handle/20.500.12116/40226 2022-01-01T00:00:00Z http://dl.gi.de/handle/20.500.12116/40223 BISE Student Sunyaev, Ali; Weinhardt, Christof; Aalst, Wil; Hinz, Oliver Sat, 01 Jan 2022 00:00:00 GMT http://dl.gi.de/handle/20.500.12116/40223 2022-01-01T00:00:00Z http://dl.gi.de/handle/20.500.12116/40222 Semi-Supervised Discovery of DNN-Based Outcome Predictors from Scarcely-Labeled Process Logs Folino, Francesco; Folino, Gianluigi; Guarascio, Massimo; Pontieri, Luigi Predicting the final outcome of an ongoing process instance is a key problem in many real-life contexts. This problem has been addressed mainly by discovering a prediction model by using traditional machine learning methods and, more recently, deep learning methods, exploiting the supervision coming from outcome-class labels associated with historical log traces. However, a supervised learning strategy is unsuitable for important application scenarios where the outcome labels are known only for a small fraction of log traces. In order to address these challenging scenarios, a semi-supervised learning approach is proposed here, which leverages a multi-target DNN model supporting both outcome prediction and the additional auxiliary task of next-activity prediction. The latter task helps the DNN model avoid spurious trace embeddings and overfitting behaviors. In extensive experimentation, this approach is shown to outperform both fully-supervised and semi-supervised discovery methods using similar DNN architectures across different real-life datasets and label-scarce settings. Sat, 01 Jan 2022 00:00:00 GMT http://dl.gi.de/handle/20.500.12116/40222 2022-01-01T00:00:00Z