A5102908049- Semantic Web and Ontologies
- Scientific Computing and Data Management
- Biomedical Text Mining and Ontologies
- Clinical practice guidelines implementation
- Business Process Modeling and Analysis
- Distributed and Parallel Computing Systems
- AI-based Problem Solving and Planning
- Data Stream Mining Techniques
- Electronic Health Records Systems
- Topic Modeling
- Natural Language Processing Techniques
- Software System Performance and Reliability
- IoT and Edge/Fog Computing
- Data Quality and Management
- Machine Learning and Data Classification
- Service-Oriented Architecture and Web Services
- Machine Learning and Algorithms
- Recommender Systems and Techniques
- Meta-analysis and systematic reviews
- Software Engineering Research
- Cardiac, Anesthesia and Surgical Outcomes
- COVID-19 diagnosis using AI
- Human-Automation Interaction and Safety
- Face and Expression Recognition
- Blockchain Technology Applications and Security
Koblenz University of Applied Sciences
2024
Karlsruhe Institute of Technology
2014-2020
The analysis of ongoing processes is an important task in business process management. This not surprising, since (e.g.) being able to predict future events enables companies intervene at early stage if deviations from a desired workflow are likely occur. Subsequently, errors and associated financial losses can be prevented or avoided. A common basis for sequence previous that typically stored socalled event log. In this work we present neural network with attention mechanism, which trained...
In the surgical domain, individual clinical experience, which is derived in large part from past cases, plays an important role treatment decision process. Simultaneously surgeon has to keep track of a amount data, emerging number heterogeneous systems during all phases treatment. This complemented with constantly growing knowledge studies and literature. To recall this vast information at right moment poses challenge that should be supported by adequate technology. While many tools projects...
With the digital transformation of companies, ever larger amounts data are generated and available for analysis. Process mining techniques can be used to extract analyze process models from these data. Related have quickly developed into an important field with constantly increasing investments in recent years. Thus, automated analysis processes has gained role many companies. In this context, graphs been shown intuitive representation how gathered carried out using aforementioned...
For cardiac surgeons, mitral valve reconstruction (MVR) surgery is a highly demanding procedure, where an artificial annuloplasty ring implanted onto the annulus to re-enable valve's proper closing functionality. successful operation surgeon has keep track of variety relevant impact factors, such as patient-individual medical history records, geometries, or tissue properties surgical target, and thereon-based deduce type size best-suitable prosthesis according practical experience. With this...
In contemporary medicine, diagnostic processes provided by Clinical Practice Guidelines (CPGs) play a key role. A CPG provides recommendations that open up scope of actions for the medical practitioner. But there is gap between theoretical knowledge and practical solutions. Furthermore, barriers implementation can arise. Taking these challenges into account, we propose framework facilitating processes. For this reason, CPGs Chronic Myeloid Leukemia (CML) Myelodysplastic Syndromes (MDS) are...
In recent years, the amount of entities in large knowledge bases has been increasing rapidly. Such can help to bridge unstructured text with structured and thus be beneficial for many entity-centric applications. The key issue is link entity mentions bases, where main challenge lies mention ambiguity. Many methods have proposed tackle this problem. However, most assume certain characteristics input documents, e.g., only named are considered. paper, we propose a context-aware approach...
To provide assistance functions in context of surgical interventions, the use medical workflows plays an important role. Workflow models can be used to assess progress on-going surgery, enabling tailored (i.e., sensitive) support for practitioner. Subsequently, this provides opportunities prevent malpractices, enhance patient's outcome and preserve a high level satisfaction. In work, we propose framework which enables formalization workflows. It is driven by dialog as well technical experts...
The past few years have been marked by an increased use of sensor technologies, abundant availability mobile devices, and growing popularity wearables, which enable the direct integration their data as part rich client applications. Despite potential added value that such aggregate applications bring, implementations are usually custom solutions for particular cases do not support easy further devices. To this end, vision Web Things (WoT) is to leverage standards in order interconnect all...
Complex tasks for heterogeneous data sources, such as finding and linking named entities in text documents or detecting objects images, often require multiple steps to be solved a processing pipeline. In most of the cases, there exist numerous, exchangeable software components single step, each an expert with certain characteristics. Which apply which observed instance step becomes challenge that is even hard humans decide. this work, we treat problem Single-Agent System (SAS) where...
Information on the Web is heterogeneous and available in constantly increasing quantities. Consequently, there are numerous, partly redundant data analytics services, each optimized for with certain characteristics. Often, tasks require multiple services to be pipelined find a solution, where combinations of exchangeable single steps might outperform one-service-predictions. This work proposes Multi-Agent System (MAS) perception prior setting, decentralized agents considered manage having...
The use of assistance functions for diagnosis and surgical interventions has become an evolving area mastering challenges contemporary medicine. Inter alia, these can help to prevent malpractices preserve a high level satisfaction patients as well employees. To enable such in context computer-assisted orthopaedic surgery (CAOS), we elaborate the Markov Logic Networks (MLNs) modelling phases. In contrast commonly researched systems process modelling, MLNs combine rule-based probabilistic...
Abstract The key purpose of assistance robots is to help people coping with work-related or everyday tasks. To ensure an intuitive and effective support by robot, its expectation conform behavior essential. In particular, when using in geriatrics assist elderly patients, special attention the human-robot interaction should be paid. order patients maintain their independence abilities as much possible, robot only intervene needed. Therefore, continuous estimation patient’s need for particular...
In modern medicine, Clinical Practice Guidelines (CPGs) are well-established resources for the appropriate treatment of diseases. Evidence-based CPGs contain recommendations which based on state art and have been achieved by consensus several experts. Nevertheless, there is a potential problems in translating guideline documents into specific actions physicians. Therefore we propose to formalize process an understandable representation as UML activities together with domain expert. This...