{"id":{"repo_id":"calpoly","oai_identifier":"oai:digitalcommons.calpoly.edu:theses-4670"},"canonical_url":"https://search.ndltd.org/etd/calpoly/oai:digitalcommons.calpoly.edu:theses-4670","repository":{"repo_id":"calpoly","name":"Cal Poly","base_url":"https://digitalcommons.calpoly.edu/do/oai/"},"display":{"title":"Opening the Black Box with REGAL: A Novel Explainable AI Approach to Uncover Key Predictors in Search and Rescue Success","abstract":"The outcome of a search and rescue (SAR) operation is influenced by a complex, non-linear interplay among numerous factors, including geographic context, subject-specific characteristics, and environmental conditions. The high dimensionality and intricate dependencies among these variables pose significant challenges to traditional exploratory modeling approaches, limiting their ability to uncover meaningful patterns and relationships associated with mission success. This study introduces Rules Based Explanations for Generated neighborhoods Around Localized cases (REGAL), a novel adaptation of the Local Interpretable Model-agnostic Explanations (LIME) framework to explain deep multimodal neural networks and what key features it assesses to determine search and rescue success. REGAL addresses limitations of traditional LIME by incorporating decision tree-based explanation mechanisms. These include split-based feature importance and the analysis of feature interactions, offering more contextually relevant and actionable insights into model behavior. REGAL also utilizes a generative modeling approach to create perturbations, to allow for more controlled, yet extensive analysis around a localized case.","abstract_html":"The outcome of a search and rescue (SAR) operation is influenced by a complex, non-linear interplay among numerous factors, including geographic context, subject-specific characteristics, and environmental conditions. The high dimensionality and intricate dependencies among these variables pose significant challenges to traditional exploratory modeling approaches, limiting their ability to uncover meaningful patterns and relationships associated with mission success. This study introduces Rules Based Explanations for Generated neighborhoods Around Localized cases (REGAL), a novel adaptation of the Local Interpretable Model-agnostic Explanations (LIME) framework to explain deep multimodal neural networks and what key features it assesses to determine search and rescue success. REGAL addresses limitations of traditional LIME by incorporating decision tree-based explanation mechanisms. These include split-based feature importance and the analysis of feature interactions, offering more contextually relevant and actionable insights into model behavior. REGAL also utilizes a generative modeling approach to create perturbations, to allow for more controlled, yet extensive analysis around a localized case.","abstract_has_math":false,"creators":["Kim, Brandon Hyunjun"],"institution":null,"degree_name":"MS in Statistics","degree_level":null,"degree_discipline":"Statistics","degree_department":null,"school":null,"contributors":["Kelly Bodwin","Statistics","College of Science and Mathematics"],"advisors":[],"committee_chairs":[],"committee_members":[],"year":null,"date_issued":"","date_published":null,"updated_at":"2026-11-19T07:12:36Z","subjects":["Explainable AI","LIME","Generative AI","Computer Vision","Machine Learning","Artificial Intelligence and Robotics","Data Science","Statistical Methodology","Statistical Models"],"languages":[],"rights":[],"rights_urls":[],"identifier_entries":[],"person_identifier_entries":[]},"links":{"outbound_url":"https://digitalcommons.calpoly.edu/theses/3029","outbound_label":"Repository record","outbound_source":"dc:identifier","record_url":"https://digitalcommons.calpoly.edu/theses/3029","record_label":"Repository record","record_kind":"record","record_source":"dc:identifier","download_url":null,"download_label":null,"download_source":null,"access_status":null,"embargo_until":null,"access_note":null},"source_record":{"url":"https://digitalcommons.calpoly.edu/do/oai/?verb=GetRecord&metadataPrefix=oai_etdms&identifier=oai%3Adigitalcommons.calpoly.edu%3Atheses-4670","prefix":"oai_etdms"},"metadata_groups":[{"id":"people","label":"People","entries":[{"key":"dc:contributor","label":"Contributor","values":["Kelly Bodwin","Statistics","College of Science and Mathematics"]},{"key":"dc:creator","label":"Author","values":["Kim, Brandon Hyunjun"]}]},{"id":"academic_context","label":"Academic Context","entries":[{"key":"dc:date.available","label":"Dc Date Available","values":["2025-06-07T07:00:00Z"]},{"key":"dc:date.created","label":"Dc Date Created","values":["2025-06-01T07:00:00Z"]},{"key":"thesis:degree_discipline","label":"Discipline","values":["Statistics"]},{"key":"thesis:degree_name","label":"Degree Name","values":["MS in Statistics"]}]},{"id":"subjects_keywords","label":"Subjects and Keywords","entries":[{"key":"dc:subject","label":"Dc Subject","values":["Explainable AI","LIME","Generative AI","Computer Vision","Machine Learning","Artificial Intelligence and Robotics","Data Science","Statistical Methodology","Statistical Models"]}]},{"id":"identifiers","label":"Identifiers","entries":[{"key":"dc:identifier","label":"Identifier","values":["https://digitalcommons.calpoly.edu/theses/3029"]}]},{"id":"additional","label":"Additional Metadata","entries":[{"key":"dc:description.abstract","label":"Abstract","values":["The outcome of a search and rescue (SAR) operation is influenced by a complex, non-linear interplay among numerous factors, including geographic context, subject-specific characteristics, and environmental conditions. The high dimensionality and intricate dependencies among these variables pose significant challenges to traditional exploratory modeling approaches, limiting their ability to uncover meaningful patterns and relationships associated with mission success. This study introduces Rules Based Explanations for Generated neighborhoods Around Localized cases (REGAL), a novel adaptation of the Local Interpretable Model-agnostic Explanations (LIME) framework to explain deep multimodal neural networks and what key features it assesses to determine search and rescue success. REGAL addresses limitations of traditional LIME by incorporating decision tree-based explanation mechanisms. These include split-based feature importance and the analysis of feature interactions, offering more contextually relevant and actionable insights into model behavior. REGAL also utilizes a generative modeling approach to create perturbations, to allow for more controlled, yet extensive analysis around a localized case."]},{"key":"dc:title","label":"Title","values":["Opening the Black Box with REGAL: A Novel Explainable AI Approach to Uncover Key Predictors in Search and Rescue Success"]}]}],"canonical_facts":{"dc:contributor":["Kelly Bodwin","Statistics","College of Science and Mathematics"],"dc:creator":["Kim, Brandon Hyunjun"],"dc:date.available":["2025-06-07T07:00:00Z"],"dc:date.created":["2025-06-01T07:00:00Z"],"dc:description.abstract":["The outcome of a search and rescue (SAR) operation is influenced by a complex, non-linear interplay among numerous factors, including geographic context, subject-specific characteristics, and environmental conditions. The high dimensionality and intricate dependencies among these variables pose significant challenges to traditional exploratory modeling approaches, limiting their ability to uncover meaningful patterns and relationships associated with mission success. This study introduces Rules Based Explanations for Generated neighborhoods Around Localized cases (REGAL), a novel adaptation of the Local Interpretable Model-agnostic Explanations (LIME) framework to explain deep multimodal neural networks and what key features it assesses to determine search and rescue success. REGAL addresses limitations of traditional LIME by incorporating decision tree-based explanation mechanisms. These include split-based feature importance and the analysis of feature interactions, offering more contextually relevant and actionable insights into model behavior. REGAL also utilizes a generative modeling approach to create perturbations, to allow for more controlled, yet extensive analysis around a localized case."],"dc:identifier":["https://digitalcommons.calpoly.edu/theses/3029"],"dc:subject":["Explainable AI","LIME","Generative AI","Computer Vision","Machine Learning","Artificial Intelligence and Robotics","Data Science","Statistical Methodology","Statistical Models"],"dc:title":["Opening the Black Box with REGAL: A Novel Explainable AI Approach to Uncover Key Predictors in Search and Rescue Success"],"thesis:degree_discipline":["Statistics"],"thesis:degree_name":["MS in Statistics"]},"updated_at":"2026-11-19T07:12:36Z"}