{"id":{"repo_id":"wvu","oai_identifier":"oai:researchrepository.wvu.edu:etd-2503"},"canonical_url":"https://search.dev.ndltd.org/etd/wvu/oai:researchrepository.wvu.edu:etd-2503","repository":{"repo_id":"wvu","name":"West Virginia University","base_url":"https://researchrepository.wvu.edu/do/oai/"},"display":{"title":"Information fusion schemes for real time risk assessment in adaptive control systems","abstract":"Intelligent Flight Control System (IFCS) deploys a neural network for in-flight aircraft failure accommodation. Verification and validation (V&V) of adaptive systems is a challenging research problem. Our approach to V&V relies on real-time monitoring of neural network learning. Monitors detect learning anomalies and react to different failure conditions. We investigated data fusion techniques suitable for the analysis of neural network monitors. Monitor outputs are fused into a measure of confidence, indicating the belief in the correctness of failure accommodation mechanism provided by the neural network. We investigated two data fusion techniques, one based on Dempster-Shafer theory and the other based on fuzzy logic. Our techniques were applied to nine flight simulation datasets including those with failures. The monitor fusion algorithms provide unique, meaningful and novel technique for V&V of adaptive flight control systems. Being theoretically sound, the algorithms can be applied to a broad range of other data fusion applications.","abstract_html":"Intelligent Flight Control System (IFCS) deploys a neural network for in-flight aircraft failure accommodation. Verification and validation (V&V) of adaptive systems is a challenging research problem. Our approach to V&V relies on real-time monitoring of neural network learning. Monitors detect learning anomalies and react to different failure conditions. We investigated data fusion techniques suitable for the analysis of neural network monitors. Monitor outputs are fused into a measure of confidence, indicating the belief in the correctness of failure accommodation mechanism provided by the neural network. We investigated two data fusion techniques, one based on Dempster-Shafer theory and the other based on fuzzy logic. Our techniques were applied to nine flight simulation datasets including those with failures. The monitor fusion algorithms provide unique, meaningful and novel technique for V&V of adaptive flight control systems. Being theoretically sound, the algorithms can be applied to a broad range of other data fusion applications.","abstract_has_math":false,"creators":["Mladenovski, Martin"],"institution":null,"degree_name":"MS","degree_level":"Thesis","degree_discipline":"Lane Department of Computer Science and Electrical Engineering","degree_department":null,"school":null,"contributors":["Bojan Cukic."],"advisors":[],"committee_chairs":[],"committee_members":[],"year":2004,"date_issued":"2004-08-01T07:00:00Z","date_published":"2004-08-01T07:00:00Z","updated_at":"2026-07-24T06:15:47Z","subjects":["Computer science"],"languages":[],"rights":[],"rights_urls":[],"identifier_entries":[{"key":"dc:identifier","label":"Identifier","values":["https://researchrepository.wvu.edu/etd/1500"],"render_values":[{"text":"https://researchrepository.wvu.edu/etd/1500","href":"https://researchrepository.wvu.edu/etd/1500","code":true}]}]},"links":{"outbound_url":"https://doi.org/10.33915/etd.1500","outbound_label":"DOI","outbound_source":"dc:identifier"},"metadata_groups":[{"id":"people","label":"People","entries":[{"key":"dc:contributor","label":"Contributor","values":["Bojan Cukic."]},{"key":"dc:creator","label":"Author","values":["Mladenovski, Martin"]}]},{"id":"academic_context","label":"Academic Context","entries":[{"key":"dc:date.available","label":"Dc Date Available","values":["2019-01-17T08:00:00Z"]},{"key":"thesis:degree_discipline","label":"Discipline","values":["Lane Department of Computer Science and Electrical Engineering"]},{"key":"thesis:degree_level","label":"Degree Level","values":["Thesis"]},{"key":"thesis:degree_name","label":"Degree Name","values":["MS"]}]},{"id":"subjects_keywords","label":"Subjects and Keywords","entries":[{"key":"dc:subject","label":"Dc Subject","values":["Computer science"]}]},{"id":"identifiers","label":"Identifiers","entries":[{"key":"dc:identifier","label":"Identifier","values":["https://doi.org/10.33915/etd.1500","https://researchrepository.wvu.edu/etd/1500"]}]},{"id":"additional","label":"Additional Metadata","entries":[{"key":"dc:description.abstract","label":"Abstract","values":["Intelligent Flight Control System (IFCS) deploys a neural network for in-flight aircraft failure accommodation. Verification and validation (V&V) of adaptive systems is a challenging research problem. Our approach to V&V relies on real-time monitoring of neural network learning. Monitors detect learning anomalies and react to different failure conditions. We investigated data fusion techniques suitable for the analysis of neural network monitors. Monitor outputs are fused into a measure of confidence, indicating the belief in the correctness of failure accommodation mechanism provided by the neural network. We investigated two data fusion techniques, one based on Dempster-Shafer theory and the other based on fuzzy logic. Our techniques were applied to nine flight simulation datasets including those with failures. The monitor fusion algorithms provide unique, meaningful and novel technique for V&V of adaptive flight control systems. Being theoretically sound, the algorithms can be applied to a broad range of other data fusion applications."]},{"key":"dc:title","label":"Title","values":["Information fusion schemes for real time risk assessment in adaptive control systems"]}]}],"canonical_facts":{"dc:contributor":["Bojan Cukic."],"dc:creator":["Mladenovski, Martin"],"dc:date.available":["2019-01-17T08:00:00Z"],"dc:description.abstract":["Intelligent Flight Control System (IFCS) deploys a neural network for in-flight aircraft failure accommodation. Verification and validation (V&V) of adaptive systems is a challenging research problem. Our approach to V&V relies on real-time monitoring of neural network learning. Monitors detect learning anomalies and react to different failure conditions. We investigated data fusion techniques suitable for the analysis of neural network monitors. Monitor outputs are fused into a measure of confidence, indicating the belief in the correctness of failure accommodation mechanism provided by the neural network. We investigated two data fusion techniques, one based on Dempster-Shafer theory and the other based on fuzzy logic. Our techniques were applied to nine flight simulation datasets including those with failures. The monitor fusion algorithms provide unique, meaningful and novel technique for V&V of adaptive flight control systems. Being theoretically sound, the algorithms can be applied to a broad range of other data fusion applications."],"dc:identifier":["https://doi.org/10.33915/etd.1500","https://researchrepository.wvu.edu/etd/1500"],"dc:subject":["Computer science"],"dc:title":["Information fusion schemes for real time risk assessment in adaptive control systems"],"thesis:degree_discipline":["Lane Department of Computer Science and Electrical Engineering"],"thesis:degree_level":["Thesis"],"thesis:degree_name":["MS"]},"updated_at":"2026-07-24T06:15:47Z"}