Scopus
Permanent URI for this collection
Browse
Browsing Scopus by Department "Fraunhofer-Institut für Angewandte Informationstechnik FIT"
Results Per Page
Sort Options
-
PublicationA Deep Learning-Based Approach for the Detection of Infested Soybean Leaves( 2023)
;Farah, Niklas ;Drack, Nicolas ;Dawel, HannahBüttner, RicardoWe address the soybean leaves infestation problem by proposing a robust classification model that can reliably detect infests by Diabrotica speciosa and caterpillars. Our transfer-learning based model uses a VGG19 convolutional neural network to classify the soybean leaves and we achieve balanced accuracies between 93.71% and 94.16% on unseen testing data. This sets a new benchmark and outperforms previous work using the same dataset. Our work has theoretical and practical implications. The soybean plays a crucial role in the agricultural industry. Infestation of soybeans leads to enormous economic and environmental losses. With our model presented here, an early and accurate detection to control the spread of plant pests is possible, which reduces economic and ecological damages. -
PublicationA Deep Learning-Based Model for Automated Quality Control in the Pharmaceutical Industry( 2022)
;Raab, Dominik ;Fezer, Eric ;Breitenbach, Johannes ;Baumgartl, Hermann ;Sauter, DanielBüttner, RicardoFor highly sensitive products such as pharmaceuticals, quality is a decisive factor in ensuring the therapeutic benefit that consumers expect and not jeopardizing consumers' health. So far, the quality control of pharmaceuticals is largely performed manually by qualified individuals. However, this is a time-consuming, repetitive, and error-prone process subject to natural performance fluctuations. To contribute to addressing this issue, we present an automated quality control approach for pharmaceutical capsules using a transfer learning-based convolutional neural network with a balanced accuracy of 97.27%, outperforming all current benchmarks. To increase trust in the model predictions, we incorporated two explainable artificial intelligence (XAI) methods into our approach. -
PublicationA Framework for Automated Abstraction Class Detection for Event Abstraction( 2023)
;Li, Chiao-YunAalst, Wil M.P. van derProcess mining enables companies to extract insights into the process execution from event data. Event data that are stored in information systems are often too fine-grained. When process mining techniques are applied to such system-level event data, the outcomes are often overly complex for human analysts to interpret. To address this issue, numerous (semi-)automated event abstraction techniques that "lift" event data to a higher level have been proposed. However, most of these techniques are supervised, i.e., the knowledge of which low-level event data or activities need to be abstracted into a high-level instance or concept is explicitly given. In this paper, we propose a fully unsupervised event abstraction framework for partially ordered event data, which further enables arbitrary levels of abstraction. The evaluation shows that the proposed framework is scalable and allows for discovering a more precise process model. -
PublicationA Generic Trace Ordering Framework for Incremental Process Discovery( 2022)
;Domnitsch, E.Aalst, Wil van derExecuting operational processes generates valuable event data in organizations’ information systems. Process discovery describes the learning of process models from such event data. Incremental process discovery algorithms allow learning a process model from event data gradually. In this context, process behavior recorded in event data is incrementally fed into the discovery algorithm that integrates the added behavior to a process model under construction. In this paper, we investigate the open research question of the impact of the ordering of incrementally selected process behavior on the quality, i.e., recall and precision, of the learned process models. We propose a framework for defining ordering strategies for traces, i.e., observed process behavior, for incremental process discovery. Further, we provide concrete instantiations of this framework. We evaluate different trace-ordering strategies on real-life event data. The results show that trace-ordering strategies can significantly improve the quality of the learned process models. -
PublicationA Literature Review on the Impact of Modern Technologies on Management Reporting( 2022)
;Ulrich, Patrick ;Frank, Vanessa ;Büttner, RicardoBecker, WolfgangIn this paper, two systematic literature searches are used to pursue questions about digitization in management reporting on the one hand and role-specific questions on the other. We assume that greater digitization in terms of efficiency and effectiveness will change the role of management accountants in general and in reporting in particular, as this should lead to more automation and possibly more time for consulting activities from management accountants/controllers. After a strictly documented filtering process, a total of 51 papers remained for the analysis of the research questions posed. As a result, in addition to research gaps in management reporting, the most important information technology (IT) tools in management accounting and management reporting can be identified. Concerning corporate performance and management accounting performance, the research also reveals a connection with digitization/IT trends in controlling, controller roles, and role conflicts. The systematic literature evaluations serve as a basis for further research to verify the possible causal relationships found. -
PublicationA Maturity Model for Assessing the Digitalization of Public Health Agencies: Development and Evaluation( 2023)
;Doctor, Eileen ;Fürstenau, Daniel ;Gersch, Martin ;Hall, Kristina ;Kauffmann, Anna Lina ;Schulte-Althoff, Matthias ;Schlieter, Hannes ;Stark, JeannetteWyrtki, KatrinRequests for a coordinated response during the COVID-19 pandemic revealed the limitations of locally-operating public health agencies (PHAs) and have resulted in a growing interest in their digitalization. However, digitalizing PHAs - i.e., transforming them technically and organizationally - toward the needs of both employees and citizens is challenging, especially in federally-managed local government settings. This paper reports on a project that develops and evaluates a continuous (vs. a staged) maturity model, the PHAMM, for digitalizing PHAs as a cornerstone of a digitally resilient public health system in the future. The model supports a coordinated approach to formulating a vision and structuring the steps toward it, engaging employees along the transformation journey necessary for a federally-managed field. Further, it is now being used to allocate substantial national funds to foster digitalization. By developing the model in a coordinated approach and using it for distributing federal resources, this work expands the potential usage cases for maturity models. The authors conclude with lessons learned and discuss how the model can incentivize local digitalization in federal fields. -
PublicationA multi-agent model of urban microgrids: Assessing the effects of energy-market shocks using real-world data( 2023)
;Madler, Jochen ;Harding, SebastianThe shift towards renewable energy sources (RES) in energy systems is becoming increasingly important. Residential energy generation and storage assets, smart home energy management systems, and peer-to-peer (P2P) electricity trading in microgrids can help integrate and balance decentralized renewable electricity supply with an increasingly electrified power, heat, and transport demand, reducing costs and CO2 emissions. However, these microgrids are difficult to model because they consist of autonomous and interacting entities, leading to emergent phenomena and a high degree of complexity. Agent-based modeling is an established technique to simulate the complexity of microgrids. However, the existing literature still lacks real-world implementation studies and, as a first step, models capable of validating the existing results with real-world data. To this end, we present an agent-based model and analyze the corresponding microgrid performance with real-world data. The model quantifies economic, technical, and environmental metrics to simulate microgrid performance holistically and, in line with state-of-the-art research, consists of self-interested, autonomous agents with specific load profiles, RES generation, and demand-response potential. The model can simulate a P2P marketplace where electricity is traded between agents. In the second part of the paper, we validate the model with data from a medium-sized German city. In this case study, we also compare microgrid performance in 2022, during the energy market crisis in Europe, with historical data from 2019 to assess the effects of energy market shocks. Our results show how microgrids with P2P trading can reduce electricity costs and CO2 emissions. However, our trading mechanism illustrates that the benefits of energy-community trading are almost exclusively shared among prosumers, highlighting the need to consider distributional issues when implementing P2P trading. -
PublicationA multivocal literature review of decentralized finance: Current knowledge and future research avenues( 2023)
;Gramlich, Vincent ;Principato, Marc ;Schellinger, BenjaminWhile decentralized finance (DeFi) has the potential to emulate and, indeed, outperform existing financial systems, it remains a complex phenomenon yet to be extensively researched. To make the most of this potential, its practitioners must gain a rigorous understanding of its intricacies, as must information systems (IS) researchers. Against this background, this study uses a multivocal literature review to capture the state of research in DeFi. Thereby, we (1) present a consolidating definition of DeFi as we (2) analyze, synthesize, and discuss the current state of knowledge in the field of DeFi. We do so while adapting the blockchain research framework proposed by (Risius and Spohrer, Business & Information Systems Engineering 59:385–409, 2017). Furthermore, we (3) identify gaps in the literature and indicate future research directions in DeFi. Even though our findings highlight several shortcomings in DeFi that have prevented its widespread adoption, our literature review shows a large consensus on DeFi’s many promising features and potential to complement the traditional financial system. To that end, this paper is presented to encourage further research to mitigate the current risks of DeFi, the payoff of which will be an enriched financial ecosystem. -
PublicationA natural language querying interface for process mining( 2023)
;Barbieri, Luciana ;Madeira, Edmundo Roberto Mauro ;Stroeh, KleberAalst, Wil van derIn spite of recent advances in process mining, making this new technology accessible to non-technical users remains a challenge. Process maps and dashboards still seem to frighten many line of business professionals. In order to democratize this technology, we propose a natural language querying interface that allows non-technical users to retrieve relevant information and insights about their processes by simply asking questions in plain English. In this work we propose a reference architecture to support questions in natural language and provide the right answers by integrating to existing process mining tools. We combine classic natural language processing techniques (such as entity recognition and semantic parsing) with an abstract logical representation for process mining queries. We also provide a compilation of real natural language questions and an implementation of the architecture that interfaces to an existing commercial tool: Everflow. We also introduce a taxonomy for process mining related questions, and use that as a background grid to analyze the performance of this experiment. Finally, we point to potential future work opportunities in this field. -
PublicationA Privacy-Preserving Distributed Analytics Platform for Health Care Data( 2022)
;Welten, S. ;Mou, Y. ;Neumann, L. ;Jaberansary, M. ;Ucer Yediel, Yeliz ;Kirsten, T. ;Decker, S.Beyan, Oya DenizBackground: In recent years, data-driven medicine has gained increasing importance in terms of diagnosis, treatment, and research due to the exponential growth of health care data. However, data protection regulations prohibit data centralisation for analysis purposes because of potential privacy risks like the accidental disclosure of data to third parties. Therefore, alternative data usage policies, which comply with present privacy guidelines, are of particular interest. Objective: We aim to enable analyses on sensitive patient data by simultaneously complying with local data protection regulations using an approach called the Personal Health Train (PHT), which is a paradigm that utilises distributed analytics (DA) methods. The main principle of the PHT is that the analytical task is brought to the data provider and the data instances remain in their original location. Methods: In this work, we present our implementation of the PHT paradigm, which preserves the sovereignty and autonomy of the data providers and operates with a limited number of communication channels. We further conduct a DA use case on data stored in three different and distributed data providers. Results: We show that our infrastructure enables the training of data models based on distributed data sources. Conclusion Our work presents the capabilities of DA infrastructures in the health care sector, which lower the regulatory obstacles of sharing patient data. We further demonstrate its ability to fuel medical science by making distributed data sets available for scientists or health care practitioners. -
PublicationA Service Oriented Architecture for the Digitalization and Automation of Distribution Grids( 2022)
;Pau, Marco ;Mirz, Markus ;Dinkelbach, Jan ;McKeever, Padraic ;Ponci, FerdinandaModern distribution grids are complex systems that need advanced management for their secure and reliable operation. The Information and Communication Technology domain today offers unprecedented opportunities for the smart design of tools in support of grid operators. This paper presents a new philosophy for the digitalization and automation of distribution grids, based on a modular architecture of microservices implemented via container technology. This architecture enables a service-oriented deployment of the intelligence needed in the Distribution Management Systems, moving beyond the traditional view of monolithic software installations in the control rooms. The proposed architecture unlocks a broad set of possibilities, including cloud-based implementations, extension of legacy systems and fast integration of machine learning-based analytic tools. Moreover, it potentially opens a completely new market of turnkey services for distribution grid management, thus avoiding large upfront investments for grid operators. This paper presents the main concepts and benefits of the proposed philosophy, together with an example of field implementation based on open source components carried out in the context of the European project SOGNO. -
PublicationA Systematic Literature Review of Current IoT-Based Approaches for Improving Sustainable Public Transportation in Smart Cities( 2022)
;Breitenbach, Johannes ;Gross, Jan ;Dittrich, Daniel ;Neumann, Pauline ;Schilling, Alexander ;Zaman, EsraBüttner, RicardoFollowing the awareness of the need to optimize the sustainability of public transportation resources, we conduct a systematic literature review of the current Internet of Things-based approaches and technologies improving sustainable public transportation in smart cities. Using internationally peer-reviewed literature, we analyze the current state of research and identify research gaps. Major findings include the flexibility of various sensors for different use cases, data collection hot spots in public transportation, and the quality of service enhancements for passengers. Our study aims to provide practitioners and researchers with guidance on applying Internet of Things-based approaches to develop smart and sustainable transportation solutions in smart cities. -
PublicationA Systematic Literature Review of Deep Learning Approaches in Smart Meter Data Analytics( 2022)
;Breitenbach, Johannes ;Gross, Jan ;Wengert, Manuel ;Anurathan, James ;Bitsch, Rico ;Kosar, Zafer ;Tuelue, EmreBüttner, RicardoAs the identification of the energy consumption represents a crucial part of the smart grid, smart meters are considered one of the most important devices in the evolution of the electrical grid. Following the recent developments which have given rise to deep learning, this paper systematically reviews the literature on deep learning approaches in smart meter data analytics. To systematically structure and analyze the current state of research, we propose a framework for deep learning-based smart meter data analytics, which investigates relevant internationally peer-reviewed literature in the field against the background of the main future challenges of smart meter data analytics. Our research aims to foster the understanding and adaption of modern deep learning methods to solve existing challenges regarding the energy supply and identify future research needs. -
PublicationA Systematic Literature Review of Machine Learning Applications for Process Monitoring and Control in Semiconductor Manufacturing( 2022)
;Gentner, Tobias ;Breitenbach, Johannes ;Neitzel, Timon ;Schulze, JacobBüttner, RicardoDue to diversity and many possibilities for data collection in semiconductor manufacturing, various complex machine learning approaches exist for different process steps. However, a systematic overview of these approaches is missing. This study, therefore, systematically reviews machine learning applications for process monitoring and control in semiconductor manufacturing based on peer-reviewed literature. To structure the review, we use the wafer fabrication plant-wide framework for process monitoring and control and the framework of continuous process improvement based on machine learning technique. We identify respective application areas and future research needs of machine learning for process monitoring and control in semiconductor manufactnring. -
PublicationA Systematic Literature Review of Machine Learning Approaches for Detecting Events and Disturbances in Smart Grid Systems( 2022)
;Büttner, Ricardo ;Breitenbach, Johannes ;Gross, Jan ;Krueger, Isabell ;Gouromichos, Hari ;Listl, Marvin ;Leicht, LouisKlier, ThorstenThis study systematically reviews international peer-reviewed literature to show existing scientific approaches on how machine learning and deep learning methods can improve the detection of events and disturbances in smart grid systems. Smart grids can adapt and react flexibly to different situations. Different approaches can be exploited to protect the whole system more efficiently. Using an extended smart control center framework, we systematically structure our literature analysis, allowing us to identify unaddressed research gaps, guiding future research on contributing to ensuring and improving security in smart grids. -
PublicationA Systematic Literature Review of Machine Learning Approaches for Optimization in Additive Manufacturing( 2022)
;Breitenbach, Johannes ;Seidenspinner, Friedrich ;Vural, Furkan ;Beisswanger, PhilippBüttner, RicardoThe rapid expansion of additive manufacturing into more and more industries increases the need to improve productivity by optimizing the technological process chains. This paper reviews literature about machine learning approaches using big data on High-Performance Computing resources for optimizing additive manufacturing processes, starting from the parts' geometrical design. Based on the literature included in international peer-reviewed journals and conferences, we build a comprehensive overview of optimization methods in the three main stages geometrical design, process parameter configuration, and in-situ anomaly detection. Furthermore, we aim to foster the understanding and adaption of the identified machine learning approaches for optimizing additive manufacturing and identify future research needs. -
PublicationA Systematic Literature Review of Virtual and Augmented Reality Applications for Maintenance in Manufacturing( 2022)
;Büttner, Ricardo ;Breitenbach, Johannes ;Wannenwetsch, Kai ;Ostermann, IsabelPriel, ReneVirtual and augmented reality approaches, which support maintenance workers with up-to-date physical images and easy-to-understand data representations, are gaining importance. These approaches can increase the efficiency and quality of plant maintenance. In this review, based on the literature included in international peer-reviewed journals and conferences, we identify different areas and applications for virtual and augmented reality approaches that support maintenance in an in-dustrial environment. Furthermore, we motivate future research for technologies that are more manageable and better suited to the manufacturing environment. -
PublicationA Systematic Review of Identity and Access Management Requirements in Enterprises and Potential Contributions of Self-Sovereign Identity( 2023)
;Glöckler, Jana ;Sedlmeir, Johannes ;Frank, FrankFridgen, GilbertDigital identity and access management (IAM) poses significant challenges for companies. Cyberattacks and resulting data breaches frequently have their root cause in enterprises’ IAM systems. During the COVID-19 pandemic, issues with the remote authentication of employees working from home highlighted the need for better IAM solutions. Using a design science research approach, the paper reviews the requirements for IAM systems from an enterprise perspective and identifies the potential benefits of self-sovereign identity (SSI) – an emerging, passwordless paradigm in identity management that provides end users with cryptographic attestations stored in digital wallet apps. To do so, this paper first conducts a systematic literature review followed by an interview study and categorizes IAM system requirements according to security and compliance, operability, technology, and user aspects. In a second step, it presents an SSI-based prototype for IAM, whose suitability for addressing IAM challenges was assessed by twelve domain experts. The results suggest that the SSI-based authentication of employees can address requirements in each of the four IAM requirement categories. SSI can specifically improve manageability and usability aspects and help implement acknowledged best practices such as the principle of least privilege. Nonetheless, the findings also reveal that SSI is not a silver bullet for all of the challenges that today’s complex IAM systems face. -
PublicationAccept Me as I Am or See Me Go: A Qualitative Analysis of User Acceptance of Self-Sovereign Identity Applications( 2023)
;Neubauer, Lena ;Stramm, Jan ;Völter, FabianeZwede, TillSelf-sovereign identity represents a novel phenomenon aiming to innovate how entities interact with, manage, and prove identity-related information. As with any emerging phenomenon, user acceptance represents a major challenge for the adoption of Self-sovereign identity. Since previous initiatives for digital identity management solutions have not been successfully adopted while at the same time their benefits are largely driven by network effects, user acceptance research is of particular importance for Self-sovereign identity. Therefore, we investigate the user acceptance of Self-sovereign identity by conducting a qualitative interview study. We contribute novel variables to existing theory and offer guidelines for building Self-sovereign identity systems. -
PublicationAdaptive Cross-Platform Learning for Teachers in Adult and Continuing Education( 2022)
;Krause, Thorsten ;Gösling, Henning ;Digel, Sabine ;Biel, CarmenThomas, OliverAvailable online trainings and learning contents for teachers in adult and continuing education (ACE) are scattered across many learning platforms. We presume great synergies by enabling teachers to combine learning content of multiple ACE platforms in their individual learning paths and receive verifiable credentials as proof of competency afterwards. In our three-year consortium research project KUPPEL, we investigate how to enable personalized and adaptive cross-platform learning for teachers in ACE. KUPPEL will connect existing ACE platforms using a multi-agent system in a cloud. Each learner will be represented by a learner agent that will continuously give personalized recommendations for content and learning peers. In this paper, we describe the main components of the KUPPEL cloud, i.e., the multi-agent system, the recommender system and self-sovereign identity and verifiable credentials with blockchain technology. With our work, we seek to ease access to online learning resources, improve learning outcomes and make online learning more attractive to learners.