35 results
Filters
Settings
Now showing1 - 10 of 35
- Some of the metrics are blocked by yourconsent settings
Item type:Publication, Access status: without files , AI copilot for FEL experimentsThis research investigates the development of an AI Copilot to support experimental scientists and staff during operations at the European X-Ray Free Electron Laser facility as part of ongoing efforts to leverage generative AI in scientific facility operations. The work focuses on problems commonly encountered during operations, identified through an initial survey of scientists and technical staff. The proposed Copilot combines anomaly detection methods with a retrieval-augmented generation (RAG) based knowledge assistant integrated into an open-source messaging platform, enabling scientists to interact with the system through a familiar interface while receiving notifications when anomalies are detected. Control system data collected during operational activities is used to build and evaluate the anomaly detection approach. In particular, a Markov chain-based anomaly detection method is evaluated using a synthetic dataset and later real operational control system data. This work lays the foundation for investigating how an AI copilot can best support European XFEL practitioners, how explainable AI methods based on case-based reasoning can explain anomaly detection outcomes, and how a RAG-based architecture can present real-time anomaly alerts and their explanations in an understandable, actionable, and factually grounded manner while minimizing hallucinations.Publicationtype: Conference Paper8 - Some of the metrics are blocked by yourconsent settings
Item type:Publication, Access status: with files , Rethinking trust in responsible AI(CEUR-WS, 2025); ; ; ; Trust is widely recognized as a core principle of Responsible AI, yet its interpretation varies significantly across disciplines. This paper examines how computer science, sociology, philosophy, and law conceptualize trust in AI systems, highlighting both tensions and complementarities. From a computer science perspective, trust is often approached as a set of system-level properties that should be formalized and evaluated with metrics. In contrast, the social sciences and humanities emphasize its relational, normative, and institutional dimensions. We argue that trust cannot be reduced to a single system property or technical measure, as it emerges from social-technical interactions involving users, developers, legal norms, and social expectations. To support interdisciplinary dialogue, we propose treating trust as a boundary concept that enables cooperation across epistemic communities acknowledging conceptual differences. Trust is widely recognized as a core principle of Responsible AI, yet its interpretation varies significantly across disciplines. This paper examines how computer science, sociology, philosophy, and law conceptualize trust in AI systems, highlighting both tensions and complementarities. From a computer science perspective, trust is often approached as a set of system-level properties that should be formalized and evaluated with metrics. In contrast, the social sciences and humanities emphasize its relational, normative, and institutional dimensions. We argue that trust cannot be reduced to a single system property or technical measure, as it emerges from social-technical interactions involving users, developers, legal norms, and social expectations. To support interdisciplinary dialogue, we propose treating trust as a boundary concept that enables cooperation across epistemic communities acknowledging conceptual differences.Publicationtype: Conference Paper21 4 - Some of the metrics are blocked by yourconsent settings
Item type:Publication, Access status: without files , Regression Trees for System Models and PredictionToday's systems are highly complex and often appear as black-box systems because of unknown internal functionalities. Thus, retrieving a model of a system is possible only based on observations of the system. We explore the usage of regression trees to learn a model of a complex system with continuous signals. Our approach for learning a regression tree uses observed inputs and outputs of a system from bounded history. We describe how to construct such a model and analyze the accuracy of predictions. Results show the applicability of regression tree models for continuous systems.Publicationtype: Conference Paper22 - Some of the metrics are blocked by yourconsent settings
Item type:Publication, Access status: without files , Measuring the Feasibility of Analogical Transfer using ComplexityAnalogies are 4-ary relations of the form “A is to B as C is to D". While focus has been mostly on how to solve an analogy, i.e. how to find correct values of D given A, B and C, less attention has been drawn on whether solving such an analogy was actually feasible. In this paper, we propose a quantification of the transferability of a source case (A and B) to solve a target problem C. This quantification is based on a complexity minimization principle which has been demonstrated to be efficient for solving analogies. We illustrate these notions on morphological analogies and show its connections with machine learning, and in particular with Unsupervised Domain Adaptation.Publicationtype: Conference Paper28 - Some of the metrics are blocked by yourconsent settings
Item type:Publication, Access status: with files , Using natural language processing for supply chain mapping: a systematic review of current approachesPurpose: The COVID-19 crisis has shown that the global supply chains are not as resilient as expected. First investigations indicate that the main contributing factor is a lack of visibility into the supply chain's lower tiers. Simultaneously, the willingness to share data in the supply chain is low as companies mainly consider their data as proprietary. However, large amounts of data are available on the internet. The amount of this data is steadily increasing; however, the problem remains, that this data is hardly structured. Therefore, this paper investigates current approaches to use this data for supply chain transparency and derives further research directions. Methodology: The paper uses a systematic review of the literature followed by content analysis. The research process further follows established frameworks in the literature and is subdivided into distinct stages. Findings: Descriptive and clustering results show a fragmented research field, where current approaches disconnect from prior research. We classify the methods using a simple taxonomy and show developments from rule-based to supervised techniques and horizontal to vertical mining approaches. The techniques with rule-based-matching procedures mainly suffer from low recall. The current approaches do not satisfy yet essential requirements on supply chain mapping based on natural language. Originality: To the best of the authors' knowledge, no prior research has been attempted to review textual data usage for supply chain mapping. Therefore, this paper's main contribution is to fill this gap and add further evidence to the use of data-driven supply chain management methods.Publicationtype: Conference PaperScopus© Citations 7 1314 1665 - Some of the metrics are blocked by yourconsent settings
Item type:Publication, Access status: without files , An approach for partially automated test generation based on signal recordingsThe increasing complexity of aircraft systems and the number of functions running on avionics components leads to a rapid growth of the number of required testing. In addition, the mission profile can change over the long life cycle of the aircraft, so that the originally developed tests may not cover all scenarios that occur during the operational use. Therefore, new test strategies are needed which allows tests to be generated without the effort growing along with it. At the same time, the aim is to identify and analyse previously unknown behavioural abnormalities. This paper describes an approach for the semi-automated generation of new test scripts based on recorded data from operations or test and simulation activities. For this purpose, methods were developed to convert these data into a generic format, so that they can be managed and processed with uniform functions. The recordings can be filtered via a graphical user interface (GUI) to derive test stimuli and verdicts. For the generation of the test script an automated process was developed, which is based on the specification for the test description language Generic State Chart extensible Markup Language.Publicationtype: Conference Paper56 - Some of the metrics are blocked by yourconsent settings
Item type:Publication, Access status: without files , Metamodeling wireless communication in cyber-physical systems(2019-06); ; With recent developments in embedded sensing technologies, cyber-physical systems, materializing Industry 4.0 concepts, are increasingly implemented in civil engineering to advance structural health monitoring (SHM) and control applications. Recent studies have shown the potential of metamodels enabling information integration and interoperability between different platforms and technologies, while metamodeling of cyber-physical systems has been scarce. In this study, a metamodel for describing cyber-physical systems, putting emphasis on communication issues, is proposed and implemented into a SHM and control system. The metamodel is mapped into the Industry Foundation Classes (IFC) data schema that is standardized for describing structures compliant to the principles of building information modeling (BIM). Finally, the metamodel proposed in this study is validated by IFC-compliant, BIM-based example modeling and implementation of a cyber-physical system designed to monitor and control a laboratory test structure.Publicationtype: Conference Paper39 - Some of the metrics are blocked by yourconsent settings
Item type:Publication, Access status: without files , A semantic model of intelligent transportation systems(2019-06); Intelligent transportation systems, representing core components of smart cities, combine sensing, computing, and wireless communication technologies to provide efficient and convenient mobility. Road intelligent transportation systems (ITS) have been studied in recent decades through simulation platforms that integrate computational models for various use cases, such as traffic lights control and management. However, semantic descriptions, illustrating road ITS as a whole and creating a basis for designing simulation platforms, have not been addressed. In this paper, a semantic model of road intelligent transportation systems is proposed, which describes road ITS components and architecture, serving as a formal basis for road ITS simulation platforms. Building upon the semantic model, an extension of the Industry Foundation Classes schema, facilitating ITS simulation platforms based on building information modeling, is discussed. The paper concludes with a summary, a discussion, and an outlook on potential formalization efforts.Publicationtype: Conference Paper46 - Some of the metrics are blocked by yourconsent settings
Item type:Publication, Access status: with files , Tool chain for avionics design, development, integration and testThe design, development, integration and test of avionics systems is a complex task. Several national and European projects aimed at improving the methods and tools for new IMA platforms. Since about 12 years, the Institute of Aircraft Systems Engineering of the Hamburg University of Technology continuously contributed to such projects. This paper gives an overview about the tool chain that has been developed so far and addresses a new extension in the field of avionics tests and its automation that will be developed in on-going and future projects. © 2019 CEUR-WS.Publicationtype: Conference PaperScopus© Citations 1 515 475 - Some of the metrics are blocked by yourconsent settings
Item type:Publication, Access status: without files , BPMT 2019 - Proceedings of the Dissertation Award, Doctoral Consortium, and Demonstration Track at BPM 2019, co-located with 17th International Conference on Business Process Management, BPM 2019 : Vienna, austria, September 1-6, 2019(RWTH Aachen, 2019)The proceedings contain 36 papers. The topics discussed include: cognitive BPM: business process automation and innovation with artificial intelligence; process mining on event graphs: a framework to extensively support projects; process mining as a strategy of inquiry: understanding design interventions and the development of business processes; visualization of environmental performance indicators (EPI) on business process models: a hospitality industry perspective; the role of culture in business process management adoption; ensemble predictive process mining – taking predictive process mining to the next level; business process sketch recognition; compliance to data protection and purpose control using process mining technique; the design and validation of a process data analytics methodology for improving meat and livestock value chains; the business process management game; and action logger: enabling process mining for robotic process automation.Publicationtype: Conference Proceedings33