A5040189126- Semantic Web and Ontologies
- Biomedical Text Mining and Ontologies
- Natural Language Processing Techniques
- Scientific Computing and Data Management
- Multisensory perception and integration
- Advanced Text Analysis Techniques
- Phonocardiography and Auscultation Techniques
- Topic Modeling
- Service-Oriented Architecture and Web Services
- Distributed and Parallel Computing Systems
- Music and Audio Processing
- Rough Sets and Fuzzy Logic
Otto-von-Guericke University Magdeburg
2020-2024
Heterogeneous data, different definitions and incompatible models are a huge problem in many domains, with no exception for the field of energy systems analysis. Hence, it is hard to re-use results, compare model results or couple at all. Ontologies provide precisely defined vocabulary build common shared conceptualisation domain. Here, we present Open Energy Ontology (OEO) developed domain Using OEO provides several benefits community. First, enables consistent annotation large amounts data...
In ontology development, there is a gap between domain ontologies which mostly use the Web Ontology Language, OWL, and foundational written in first-order logic, FOL. To bridge this gap, we present Gavel, tool that supports development of heterogeneous ‘FOWL’ extend OWL with FOL annotations, able to reason over combined set axioms. Since annotations are stored FOWL remain compatible existing infrastructure. We show for OBI, stronger integration its top-level BFO via our approach enables us...
Connecting chemical structural representations with meaningful categories and semantic annotations representing existing knowledge enables data-driven digital discovery from chemistry data. Ontologies are annotation resources that provide definitions a classification hierarchy for domain. They widely used throughout the life sciences. ChEBI is large-scale ontology domain of biologically interesting connects structures biological categories. Classifying novel molecular into ontologies such as...
In ontology development, there is a gap between domain ontologies which mostly use the web language, OWL, and foundational written in first-order logic, FOL. To bridge this gap, we present Gavel, tool that supports development of heterogeneous 'FOWL' extend OWL with FOL annotations, able to reason over combined set axioms. Since annotations are stored FOWL remain compatible existing infrastructure. We show for OBI, stronger integration its top-level BFO via our approach enables us detect...
Deep learning models are often unaware of the inherent constraints task they applied to. However, many downstream tasks require logical consistency. For ontology classification tasks, such include subsumption and disjointness relations between classes. In order to increase consistency deep models, we propose a semantic loss that combines label-based with terms penalising subsumption- or disjointness-violations. Our evaluation on ChEBI shows is able decrease number violations by several...
Smartphones and other mobile devices offer a valu-able opportunity to gather patient-specific health data during everyday life. However, the increasing popularity of apps demands specialized analysis methods that can handle unique, patient-based, time-dependent, often multivariate collected by these apps. This work explores patient-based mHealth develop personalized prediction models. The models incor-porate not only from individual patient, but also similar patients using neighborhoods. Our...