{"id":{"repo_id":"rowan","oai_identifier":"oai:rdw.rowan.edu:etd-4484"},"canonical_url":"https://search.ndltd.org/etd/rowan/oai:rdw.rowan.edu:etd-4484","repository":{"repo_id":"rowan","name":"Rowan University","base_url":"https://rdw.rowan.edu/do/oai/"},"display":{"title":"INTELLIGENT SKIES: DEEP LEARNING ARCHITECTURES FOR SCALABLE AVIATION SAFETY SYSTEMS","abstract":"The growing complexity of aviation operations, particularly in rotorcraft and vertical flight necessitates the development of intelligent, automated systems to enhance safety and situational awareness. This thesis investigates the application of artificial intelligence (AI), with a focus on deep learning (DL), to address critical safety challenges in aviation. Four core use cases are examined: helicopter cockpit flight data monitoring, runway detection, helipad segmentation, and obstacle localization around rotorcraft landing zones. Each application targets a specific gap in current aviation infrastructure, with an emphasis on operational needs identified by the Federal Aviation Administration (FAA). Leveraging a range of DL architectures, including convolutional neural networks and zero-shot vision-language models, this work demonstrates how modern DL computer vision techniques can be effectively applied to complex, safety-critical tasks using video footage and high-resolution satellite imagery. The proposed models are designed for scalability and seamless integration into existing aviation workflows, ensuring both practicality and impact. The results underscore DL’s potential to modernize aviation safety systems, enhance situational awareness, and enable more proactive and data-driven safety management practices.","abstract_html":"The growing complexity of aviation operations, particularly in rotorcraft and vertical flight necessitates the development of intelligent, automated systems to enhance safety and situational awareness. This thesis investigates the application of artificial intelligence (AI), with a focus on deep learning (DL), to address critical safety challenges in aviation. Four core use cases are examined: helicopter cockpit flight data monitoring, runway detection, helipad segmentation, and obstacle localization around rotorcraft landing zones. Each application targets a specific gap in current aviation infrastructure, with an emphasis on operational needs identified by the Federal Aviation Administration (FAA). Leveraging a range of DL architectures, including convolutional neural networks and zero-shot vision-language models, this work demonstrates how modern DL computer vision techniques can be effectively applied to complex, safety-critical tasks using video footage and high-resolution satellite imagery. The proposed models are designed for scalability and seamless integration into existing aviation workflows, ensuring both practicality and impact. The results underscore DL’s potential to modernize aviation safety systems, enhance situational awareness, and enable more proactive and data-driven safety management practices.","abstract_has_math":false,"creators":["Khelifi, Amine"],"institution":null,"degree_name":"M.S. Electrical and Computer Engineering","degree_level":"Thesis","degree_discipline":"Electrical and Computer Engineering","degree_department":null,"school":null,"contributors":["Nidhal C. Bouaynaya, Ph.D.","Ying Tang, Ph.D.","Charles C. Johnson"],"advisors":[],"committee_chairs":[],"committee_members":[],"year":null,"date_issued":"","date_published":null,"updated_at":"2026-11-19T09:00:05Z","subjects":["AI;Aviation safety;Deep Learning;Machine Learning"],"languages":[],"rights":[],"rights_urls":[],"identifier_entries":[],"person_identifier_entries":[]},"links":{"outbound_url":"https://rdw.rowan.edu/etd/3478","outbound_label":"Repository record","outbound_source":"dc:identifier","record_url":"https://rdw.rowan.edu/etd/3478","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://rdw.rowan.edu/do/oai/?verb=GetRecord&metadataPrefix=oai_etdms&identifier=oai%3Ardw.rowan.edu%3Aetd-4484","prefix":"oai_etdms"},"metadata_groups":[{"id":"people","label":"People","entries":[{"key":"dc:contributor","label":"Contributor","values":["Nidhal C. Bouaynaya, Ph.D.","Ying Tang, Ph.D.","Charles C. Johnson"]},{"key":"dc:creator","label":"Author","values":["Khelifi, Amine"]}]},{"id":"academic_context","label":"Academic Context","entries":[{"key":"dc:date.available","label":"Dc Date Available","values":["2026-01-27T08:00:00Z"]},{"key":"dc:date.created","label":"Dc Date Created","values":["2026-01-27T08:00:00Z"]},{"key":"thesis:degree_discipline","label":"Discipline","values":["Electrical and Computer Engineering"]},{"key":"thesis:degree_level","label":"Degree Level","values":["Thesis"]},{"key":"thesis:degree_name","label":"Degree Name","values":["M.S. Electrical and Computer Engineering"]}]},{"id":"subjects_keywords","label":"Subjects and Keywords","entries":[{"key":"dc:subject","label":"Dc Subject","values":["AI;Aviation safety;Deep Learning;Machine Learning"]}]},{"id":"identifiers","label":"Identifiers","entries":[{"key":"dc:identifier","label":"Identifier","values":["https://rdw.rowan.edu/etd/3478"]}]},{"id":"additional","label":"Additional Metadata","entries":[{"key":"dc:description.abstract","label":"Abstract","values":["The growing complexity of aviation operations, particularly in rotorcraft and vertical flight necessitates the development of intelligent, automated systems to enhance safety and situational awareness. This thesis investigates the application of artificial intelligence (AI), with a focus on deep learning (DL), to address critical safety challenges in aviation. Four core use cases are examined: helicopter cockpit flight data monitoring, runway detection, helipad segmentation, and obstacle localization around rotorcraft landing zones. Each application targets a specific gap in current aviation infrastructure, with an emphasis on operational needs identified by the Federal Aviation Administration (FAA). Leveraging a range of DL architectures, including convolutional neural networks and zero-shot vision-language models, this work demonstrates how modern DL computer vision techniques can be effectively applied to complex, safety-critical tasks using video footage and high-resolution satellite imagery. The proposed models are designed for scalability and seamless integration into existing aviation workflows, ensuring both practicality and impact. The results underscore DL’s potential to modernize aviation safety systems, enhance situational awareness, and enable more proactive and data-driven safety management practices."]},{"key":"dc:title","label":"Title","values":["INTELLIGENT SKIES: DEEP LEARNING ARCHITECTURES FOR SCALABLE AVIATION SAFETY SYSTEMS"]}]}],"canonical_facts":{"dc:contributor":["Nidhal C. Bouaynaya, Ph.D.","Ying Tang, Ph.D.","Charles C. Johnson"],"dc:creator":["Khelifi, Amine"],"dc:date.available":["2026-01-27T08:00:00Z"],"dc:date.created":["2026-01-27T08:00:00Z"],"dc:description.abstract":["The growing complexity of aviation operations, particularly in rotorcraft and vertical flight necessitates the development of intelligent, automated systems to enhance safety and situational awareness. This thesis investigates the application of artificial intelligence (AI), with a focus on deep learning (DL), to address critical safety challenges in aviation. Four core use cases are examined: helicopter cockpit flight data monitoring, runway detection, helipad segmentation, and obstacle localization around rotorcraft landing zones. Each application targets a specific gap in current aviation infrastructure, with an emphasis on operational needs identified by the Federal Aviation Administration (FAA). Leveraging a range of DL architectures, including convolutional neural networks and zero-shot vision-language models, this work demonstrates how modern DL computer vision techniques can be effectively applied to complex, safety-critical tasks using video footage and high-resolution satellite imagery. The proposed models are designed for scalability and seamless integration into existing aviation workflows, ensuring both practicality and impact. The results underscore DL’s potential to modernize aviation safety systems, enhance situational awareness, and enable more proactive and data-driven safety management practices."],"dc:identifier":["https://rdw.rowan.edu/etd/3478"],"dc:subject":["AI;Aviation safety;Deep Learning;Machine Learning"],"dc:title":["INTELLIGENT SKIES: DEEP LEARNING ARCHITECTURES FOR SCALABLE AVIATION SAFETY SYSTEMS"],"thesis:degree_discipline":["Electrical and Computer Engineering"],"thesis:degree_level":["Thesis"],"thesis:degree_name":["M.S. Electrical and Computer Engineering"]},"updated_at":"2026-11-19T09:00:05Z"}