This study investigates automated deep-learning methodologies for two primary tasks, firstly fish and its habitat classification and deep-sea fish detection using the DeepFish dataset. A pretrained ResNet-50 model attained a validation accuracy of 82.8% for multi-class habitat classification, demonstrating robust performance in most habitats based on 6,517 images, although exhibiting lower recall for visually similar or underrepresented classes. A binary ResNet-50 classifier achieved 99.8% accuracy in distinguishing fish from. no-fish images using approximately 40,000 images. The YOLOv5s model, trained on 4,505 images containing 15,463 bounding-box annotations, achieved a mean average precision (mAP@0.5) of 98.2% All models were trained on the SeaHawk computing cluster with four GPUs. These findings highlight promising directions for future research in video-based modeling, semi-supervised learning and efficient marine edge computing.
","abstract_html":"<p>This study investigates automated deep-learning methodologies for two primary tasks, firstly fish and its habitat classification and deep-sea fish detection using the DeepFish dataset. A pretrained ResNet-50 model attained a validation accuracy of 82.8% for multi-class habitat classification, demonstrating robust performance in most habitats based on 6,517 images, although exhibiting lower recall for visually similar or underrepresented classes. A binary ResNet-50 classifier achieved 99.8% accuracy in distinguishing fish from. no-fish images using approximately 40,000 images. The YOLOv5s model, trained on 4,505 images containing 15,463 bounding-box annotations, achieved a mean average precision (mAP@0.5) of 98.2% All models were trained on the SeaHawk computing cluster with four GPUs. These findings highlight promising directions for future research in video-based modeling, semi-supervised learning and efficient marine edge computing.</p>","abstract_has_math":false,"creators":["Madari, Poojitha Priyadarshini"],"institution":null,"degree_name":"Master of Science (MS)","degree_level":"Masters Thesis","degree_discipline":null,"degree_department":null,"school":null,"contributors":["Dr. Chaoyang Zhang","Dr. Sarah Lee","Dr. Zhaoxian Zhou"],"advisors":[],"committee_chairs":[],"committee_members":[],"year":2025,"date_issued":"2025-12-01T08:00:00Z","date_published":"2025-12-01T08:00:00Z","updated_at":"2026-07-24T05:45:55Z","subjects":["Machine Learning","Deep learning","YOLOv5","ResNet-50","Marine","DeepFish Dataset"],"languages":[],"rights":[],"rights_urls":[],"identifier_entries":[]},"links":{"outbound_url":"https://aquila.usm.edu/masters_theses/1150","outbound_label":"Repository record","outbound_source":"dc:identifier"},"metadata_groups":[{"id":"people","label":"People","entries":[{"key":"dc:contributor","label":"Contributor","values":["Dr. Chaoyang Zhang","Dr. Sarah Lee","Dr. Zhaoxian Zhou"]},{"key":"dc:creator","label":"Author","values":["Madari, Poojitha Priyadarshini"]}]},{"id":"academic_context","label":"Academic Context","entries":[{"key":"dc:date.available","label":"Dc Date Available","values":["2026-01-19T08:00:00Z"]},{"key":"thesis:degree_level","label":"Degree Level","values":["Masters Thesis"]},{"key":"thesis:degree_name","label":"Degree Name","values":["Master of Science (MS)"]}]},{"id":"subjects_keywords","label":"Subjects and Keywords","entries":[{"key":"dc:subject","label":"Dc Subject","values":["Machine Learning","Deep learning","YOLOv5","ResNet-50","Marine","DeepFish Dataset"]}]},{"id":"identifiers","label":"Identifiers","entries":[{"key":"dc:identifier","label":"Identifier","values":["https://aquila.usm.edu/masters_theses/1150"]}]},{"id":"additional","label":"Additional Metadata","entries":[{"key":"dc:description.abstract","label":"Abstract","values":["This study investigates automated deep-learning methodologies for two primary tasks, firstly fish and its habitat classification and deep-sea fish detection using the DeepFish dataset. A pretrained ResNet-50 model attained a validation accuracy of 82.8% for multi-class habitat classification, demonstrating robust performance in most habitats based on 6,517 images, although exhibiting lower recall for visually similar or underrepresented classes. A binary ResNet-50 classifier achieved 99.8% accuracy in distinguishing fish from. no-fish images using approximately 40,000 images. The YOLOv5s model, trained on 4,505 images containing 15,463 bounding-box annotations, achieved a mean average precision (mAP@0.5) of 98.2% All models were trained on the SeaHawk computing cluster with four GPUs. These findings highlight promising directions for future research in video-based modeling, semi-supervised learning and efficient marine edge computing.
"]},{"key":"dc:title","label":"Title","values":["A Study on Deepsea Fish Detection Using Convolutional Neural Networks"]}]}],"canonical_facts":{"dc:contributor":["Dr. Chaoyang Zhang","Dr. Sarah Lee","Dr. Zhaoxian Zhou"],"dc:creator":["Madari, Poojitha Priyadarshini"],"dc:date.available":["2026-01-19T08:00:00Z"],"dc:description.abstract":["This study investigates automated deep-learning methodologies for two primary tasks, firstly fish and its habitat classification and deep-sea fish detection using the DeepFish dataset. A pretrained ResNet-50 model attained a validation accuracy of 82.8% for multi-class habitat classification, demonstrating robust performance in most habitats based on 6,517 images, although exhibiting lower recall for visually similar or underrepresented classes. A binary ResNet-50 classifier achieved 99.8% accuracy in distinguishing fish from. no-fish images using approximately 40,000 images. The YOLOv5s model, trained on 4,505 images containing 15,463 bounding-box annotations, achieved a mean average precision (mAP@0.5) of 98.2% All models were trained on the SeaHawk computing cluster with four GPUs. These findings highlight promising directions for future research in video-based modeling, semi-supervised learning and efficient marine edge computing.
"],"dc:identifier":["https://aquila.usm.edu/masters_theses/1150"],"dc:subject":["Machine Learning","Deep learning","YOLOv5","ResNet-50","Marine","DeepFish Dataset"],"dc:title":["A Study on Deepsea Fish Detection Using Convolutional Neural Networks"],"thesis:degree_level":["Masters Thesis"],"thesis:degree_name":["Master of Science (MS)"]},"updated_at":"2026-07-24T05:45:55Z"}