{"id":{"repo_id":"usf","oai_identifier":"oai:digitalcommons.usf.edu:etd-12298"},"canonical_url":"https://search.ndltd.org/etd/usf/oai:digitalcommons.usf.edu:etd-12298","repository":{"repo_id":"usf","name":"University of South Florida","base_url":"https://digitalcommons.usf.edu/do/oai/"},"display":{"title":"“Smart Trap”: A Portable Device for Real-Time Mosquito Capturing and Classification Using Image-Based Analysis","abstract":"Capturing mosquitoes in real-time and taking high-quality images for classification with state-of-the-art methods is not only time-consuming but also expensive. Sometimes even carefully controlled environments and experimental setups fail to capture living mosquitoes. Catching live mosquitoes is necessary to be able to study aspects of their physiology and behavior that cannot be investigated by collections of resting mosquitoes and dead specimens, and to help estimate the local population numbers. My thesis introduces a “Smart Trap”, a small portable device that can attract mosquitoes in real-time, capture them, take high-quality images with dual cameras, and store those images in the cloud. The images can later be used for further classification based on the necessity of the circumstances. This trap sets an example that tools based on artificial intelligence show prospects for monitoring mosquitoes to prevent vector-borne illnesses. A manual for the “Smart-Trap” is also available which shows the step-by-step making process of the smart trap so that anyone can make it. It is not only inexpensive but also a great alternative to expensive scientific processes that take a long time to capture and classify mosquitoes. Currently, for the back-end prediction model, a lightweight Mobilenetv2 architecture is used along with transfer learning to predict the mosquitoes. The accuracy achieved is 90% on the data collected from the “Smart-Trap”. Though there are some false positive predictions, the false negative predictions are much less which is a good sign.","abstract_html":"Capturing mosquitoes in real-time and taking high-quality images for classification with state-of-the-art methods is not only time-consuming but also expensive. Sometimes even carefully controlled environments and experimental setups fail to capture living mosquitoes. Catching live mosquitoes is necessary to be able to study aspects of their physiology and behavior that cannot be investigated by collections of resting mosquitoes and dead specimens, and to help estimate the local population numbers. My thesis introduces a “Smart Trap”, a small portable device that can attract mosquitoes in real-time, capture them, take high-quality images with dual cameras, and store those images in the cloud. The images can later be used for further classification based on the necessity of the circumstances. This trap sets an example that tools based on artificial intelligence show prospects for monitoring mosquitoes to prevent vector-borne illnesses. A manual for the “Smart-Trap” is also available which shows the step-by-step making process of the smart trap so that anyone can make it. It is not only inexpensive but also a great alternative to expensive scientific processes that take a long time to capture and classify mosquitoes. Currently, for the back-end prediction model, a lightweight Mobilenetv2 architecture is used along with transfer learning to predict the mosquitoes. The accuracy achieved is 90% on the data collected from the “Smart-Trap”. Though there are some false positive predictions, the false negative predictions are much less which is a good sign.","abstract_has_math":false,"creators":["Rahman, Fahim"],"institution":"University of South Florida","degree_name":"MS in Computer Science (M.S.C.S.)","degree_level":"Thesis","degree_discipline":"Computer Science and Engineering","degree_department":null,"school":null,"contributors":["Sriram Chellappan, Ph.D.","Shaun Canavan, Ph.D.","Ankur Mali, Ph.D."],"advisors":[],"committee_chairs":[],"committee_members":[],"year":2025,"date_issued":"2025-03-14T07:00:00Z","date_published":"2025-03-14T07:00:00Z","updated_at":"2026-11-19T08:49:32Z","subjects":["Cloud","Masking","Neural Networks","Raspberry-PI","Computer Sciences"],"languages":[],"rights":[],"rights_urls":[],"identifier_entries":[],"person_identifier_entries":[]},"links":{"outbound_url":"https://digitalcommons.usf.edu/etd/10995","outbound_label":"Repository record","outbound_source":"dc:identifier","record_url":"https://digitalcommons.usf.edu/etd/10995","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.usf.edu/do/oai/?verb=GetRecord&metadataPrefix=oai_etdms&identifier=oai%3Adigitalcommons.usf.edu%3Aetd-12298","prefix":"oai_etdms"},"metadata_groups":[{"id":"people","label":"People","entries":[{"key":"dc:contributor","label":"Contributor","values":["Sriram Chellappan, Ph.D.","Shaun Canavan, Ph.D.","Ankur Mali, Ph.D."]},{"key":"dc:creator","label":"Author","values":["Rahman, Fahim"]}]},{"id":"academic_context","label":"Academic Context","entries":[{"key":"dc:date","label":"Dc Date","values":["2025-03-14T07:00:00Z"]},{"key":"thesis:degree_discipline","label":"Discipline","values":["Computer Science and Engineering"]},{"key":"thesis:degree_level","label":"Degree Level","values":["Thesis","M.S.C.S."]},{"key":"thesis:degree_name","label":"Degree Name","values":["MS in Computer Science (M.S.C.S.)"]},{"key":"thesis:institution_name","label":"Thesis Institution Name","values":["University of South Florida"]}]},{"id":"subjects_keywords","label":"Subjects and Keywords","entries":[{"key":"dc:subject","label":"Dc Subject","values":["Cloud","Masking","Neural Networks","Raspberry-PI","Computer Sciences"]}]},{"id":"identifiers","label":"Identifiers","entries":[{"key":"dc:identifier","label":"Identifier","values":["https://digitalcommons.usf.edu/etd/10995"]}]},{"id":"additional","label":"Additional Metadata","entries":[{"key":"dc:description","label":"Description","values":["Capturing mosquitoes in real-time and taking high-quality images for classification with state-of-the-art methods is not only time-consuming but also expensive. Sometimes even carefully controlled environments and experimental setups fail to capture living mosquitoes. Catching live mosquitoes is necessary to be able to study aspects of their physiology and behavior that cannot be investigated by collections of resting mosquitoes and dead specimens, and to help estimate the local population numbers. My thesis introduces a “Smart Trap”, a small portable device that can attract mosquitoes in real-time, capture them, take high-quality images with dual cameras, and store those images in the cloud. The images can later be used for further classification based on the necessity of the circumstances. This trap sets an example that tools based on artificial intelligence show prospects for monitoring mosquitoes to prevent vector-borne illnesses. A manual for the “Smart-Trap” is also available which shows the step-by-step making process of the smart trap so that anyone can make it. It is not only inexpensive but also a great alternative to expensive scientific processes that take a long time to capture and classify mosquitoes. Currently, for the back-end prediction model, a lightweight Mobilenetv2 architecture is used along with transfer learning to predict the mosquitoes. The accuracy achieved is 90% on the data collected from the “Smart-Trap”. Though there are some false positive predictions, the false negative predictions are much less which is a good sign."]},{"key":"dc:title","label":"Title","values":["“Smart Trap”: A Portable Device for Real-Time Mosquito Capturing and Classification Using Image-Based Analysis"]}]}],"canonical_facts":{"dc:contributor":["Sriram Chellappan, Ph.D.","Shaun Canavan, Ph.D.","Ankur Mali, Ph.D."],"dc:creator":["Rahman, Fahim"],"dc:date":["2025-03-14T07:00:00Z"],"dc:description":["Capturing mosquitoes in real-time and taking high-quality images for classification with state-of-the-art methods is not only time-consuming but also expensive. Sometimes even carefully controlled environments and experimental setups fail to capture living mosquitoes. Catching live mosquitoes is necessary to be able to study aspects of their physiology and behavior that cannot be investigated by collections of resting mosquitoes and dead specimens, and to help estimate the local population numbers. My thesis introduces a “Smart Trap”, a small portable device that can attract mosquitoes in real-time, capture them, take high-quality images with dual cameras, and store those images in the cloud. The images can later be used for further classification based on the necessity of the circumstances. This trap sets an example that tools based on artificial intelligence show prospects for monitoring mosquitoes to prevent vector-borne illnesses. A manual for the “Smart-Trap” is also available which shows the step-by-step making process of the smart trap so that anyone can make it. It is not only inexpensive but also a great alternative to expensive scientific processes that take a long time to capture and classify mosquitoes. Currently, for the back-end prediction model, a lightweight Mobilenetv2 architecture is used along with transfer learning to predict the mosquitoes. The accuracy achieved is 90% on the data collected from the “Smart-Trap”. Though there are some false positive predictions, the false negative predictions are much less which is a good sign."],"dc:identifier":["https://digitalcommons.usf.edu/etd/10995"],"dc:subject":["Cloud","Masking","Neural Networks","Raspberry-PI","Computer Sciences"],"dc:title":["“Smart Trap”: A Portable Device for Real-Time Mosquito Capturing and Classification Using Image-Based Analysis"],"thesis:degree_discipline":["Computer Science and Engineering"],"thesis:degree_level":["Thesis","M.S.C.S."],"thesis:degree_name":["MS in Computer Science (M.S.C.S.)"],"thesis:institution_name":["University of South Florida"]},"updated_at":"2026-11-19T08:49:32Z"}