A credit rationale forms an integral part of the credit granting and credit decision making process. Historically such credit rationales were written as a natural language document, the creation of which is a time consuming and manual process. The solution that we propose is to create a Linked Data based credit rationale that we call the Advanced Credit Rationale (AdCR). This enables the automated checking of the credit rationale for potential regulatory issues, as well as semantic based querying over a whole portfolio of such credit rationales. In this work we propose an approach that facilitates the creation of a credit rationale that is based on a Linked Data knowledge graph. We evaluate this approach with a prototype. We also demonstrate that with this approach the creation of a Linked Data based credit rationale should not take more time than a natural language based credit rationale. In addition we show that the structures that a Linked Data based credit rationale provides are generally seen as helpful.
Ensuring compliance with various laws and regulations is of utmost priority for financial institutions. In this work we propose an approach to tackle these issues by encoding them into software contracts using a Controlled Natural Language. In particular, we encode a portion of the Money Market Statistical Reporting (MMSR) regulations into contracts specified by the clojure.spec framework. We show how various features of a contract framework, in particular clojure.spec, can help to tackle issues that occur when dealing with compliance: validation with explanations and test data generation.
Understanding and analysing large scale clinical knowledge bases is a problem, due to explicit domain specific information is often missing and/or incomplete. Furthermore, such knowledge sources are often large enough that manual techinques to add such information is an complex and expensive process. In this work an approach was presented to turn such knowledge sources into full fledged, semantically enabled, analytics and decision support systems. This approach was demonstrated using a large laboratory dataset.
Semantic Web technologies can enable semantic aware solutions such as decision support systems, even in mobile environments. However the mobile platform has some very specific constraints that provides challenges to such tools, in particular reasoners. In this work a framework is presented to benchmark and evaluate such tools and is used to compare mobile reasoning performance.
Semantic Web technologies can enable semantic aware solutions such as decision support systems. In order to make use of such technologies in mobile environments, effective and efficient mobile reasoners are needed. As there was a lack of benchmark information on rule reasoners in mobile settings, a test suite based on Atrial Fibrillation decision support was created. Using this rule set 4 different mobile reasoners were evaluated and compared.
Assistive technologies in mobile and smart environments, have their unique challenges due to mobility, failure tolerance and privacy. In particular Clinical Decision Support Systems (CDSS), that can assist health professionals and patients in such context, pose difficulties for implementations. In this work, an approach is demonstrated with which these constraints can be overcome. This approach has been successfully validated for a Sleep Apnea CDSS.
The analysis of execution traces, logs of the running program, is a commonly used dynamic analysis. By using ontologies, a formal and machine understandable way of representing knowledge, we can improve upon existing techniques to understand and analyze such execution traces.
An ontology based approach for using Dynamic Analysis was presented. Dynamic Analysis is the analysis of a running program. By using ontologies, a formal and machine understandable way of representing knowledge, Dynamic Analysis can be improved. This proposed approach was demonstrated by an example based on Frequency Spectrum Analysis.