{"id":{"repo_id":"utahstate","oai_identifier":"oai:digitalcommons.usu.edu:etd-9147"},"canonical_url":"https://search.ndltd.org/etd/utahstate/oai:digitalcommons.usu.edu:etd-9147","repository":{"repo_id":"utahstate","name":"Utah State University","base_url":"https://digitalcommons.usu.edu/do/oai/"},"display":{"title":"Automation of Feature Selection and Generation of Optimal Feature Subsets for Beehive Audio Sample Classification","abstract":"The last couple of decades have witnessed an abnormal phenomenon of reduction in the bee population, this is a serious matter of concern as three out of four crops available globally have honey bee as their sole pollinator causing significant economic losses and an unbalance in the ecosystem. There have been many theories about the cause of bee colony collapses such as parasites, pesticides and poor nutrition however conclusive evidence of this phenomenon is yet to be identified. Human inspection of beehives requires precision. It takes an experienced beekeeper to determine the health of a hive by the sounds generated by the bees. If the sound indicates poor health, the beekeeper must then disrupt the hive to inspect and ascertain possible causes of poor health. This interferes with beehive activity, which can then threaten even further hive health. This work uses Feature Engineering and Machine Learning to develop techniques to monitor hive health. The thesis aims at building an automation technique for finding the best feature subsets using datasets containing different classes of audio sounds. Selecting good features forms the basis for machine learning models to further classify these audio samples. The purpose of finding the best features is to get a better audio classification which helps beekeepers know about the health of beehives and address problems such as bee immunity, effects of pesticides and environmental and nutritional stressors from remote locations.","abstract_html":"The last couple of decades have witnessed an abnormal phenomenon of reduction in the bee population, this is a serious matter of concern as three out of four crops available globally have honey bee as their sole pollinator causing significant economic losses and an unbalance in the ecosystem. There have been many theories about the cause of bee colony collapses such as parasites, pesticides and poor nutrition however conclusive evidence of this phenomenon is yet to be identified. Human inspection of beehives requires precision. It takes an experienced beekeeper to determine the health of a hive by the sounds generated by the bees. If the sound indicates poor health, the beekeeper must then disrupt the hive to inspect and ascertain possible causes of poor health. This interferes with beehive activity, which can then threaten even further hive health. This work uses Feature Engineering and Machine Learning to develop techniques to monitor hive health. The thesis aims at building an automation technique for finding the best feature subsets using datasets containing different classes of audio sounds. Selecting good features forms the basis for machine learning models to further classify these audio samples. The purpose of finding the best features is to get a better audio classification which helps beekeepers know about the health of beehives and address problems such as bee immunity, effects of pesticides and environmental and nutritional stressors from remote locations.","abstract_has_math":false,"creators":["Bhouraskar, Aditya"],"institution":"Hosted by Utah State University Libraries","degree_name":"Master of Science (MS)","degree_level":"Thesis","degree_discipline":"Computer Science","degree_department":null,"school":null,"contributors":["Vladimir Kulyukin","Nicholas Flann","Curtis Dyreson"],"advisors":[],"committee_chairs":[],"committee_members":[],"year":null,"date_issued":"","date_published":null,"updated_at":"2026-11-19T08:52:04Z","subjects":["feature selection","feature automation","beehive audio samples","Computer Sciences"],"languages":[],"rights":[],"rights_urls":[],"identifier_entries":[{"key":"dc:identifier.doi","label":"DOI","values":["https://doi.org/10.26076/ba69-74be"],"render_values":[{"text":"https://doi.org/10.26076/ba69-74be","href":"https://doi.org/10.26076/ba69-74be","code":true}]}],"person_identifier_entries":[]},"links":{"outbound_url":"https://digitalcommons.usu.edu/etd/8006","outbound_label":"Repository record","outbound_source":"dc:identifier","record_url":"https://digitalcommons.usu.edu/etd/8006","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.usu.edu/do/oai/?verb=GetRecord&metadataPrefix=oai_etdms&identifier=oai%3Adigitalcommons.usu.edu%3Aetd-9147","prefix":"oai_etdms"},"metadata_groups":[{"id":"people","label":"People","entries":[{"key":"dc:contributor","label":"Contributor","values":["Vladimir Kulyukin","Nicholas Flann","Curtis Dyreson"]},{"key":"dc:creator","label":"Author","values":["Bhouraskar, Aditya"]}]},{"id":"academic_context","label":"Academic Context","entries":[{"key":"dc:date.available","label":"Dc Date Available","values":["2010-01-01T08:00:00Z"]},{"key":"dc:date.created","label":"Dc Date Created","values":["2020-12-01T08:00:00Z"]},{"key":"dc:publisher","label":"Institution","values":["Hosted by Utah State University Libraries"]},{"key":"thesis:degree_discipline","label":"Discipline","values":["Computer Science"]},{"key":"thesis:degree_level","label":"Degree Level","values":["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":["feature selection","feature automation","beehive audio samples","Computer Sciences"]}]},{"id":"identifiers","label":"Identifiers","entries":[{"key":"dc:identifier","label":"Identifier","values":["https://digitalcommons.usu.edu/etd/8006"]},{"key":"dc:identifier.doi","label":"DOI","values":["https://doi.org/10.26076/ba69-74be"]}]},{"id":"additional","label":"Additional Metadata","entries":[{"key":"dc:description.abstract","label":"Abstract","values":["The last couple of decades have witnessed an abnormal phenomenon of reduction in the bee population, this is a serious matter of concern as three out of four crops available globally have honey bee as their sole pollinator causing significant economic losses and an unbalance in the ecosystem. There have been many theories about the cause of bee colony collapses such as parasites, pesticides and poor nutrition however conclusive evidence of this phenomenon is yet to be identified. Human inspection of beehives requires precision. It takes an experienced beekeeper to determine the health of a hive by the sounds generated by the bees. If the sound indicates poor health, the beekeeper must then disrupt the hive to inspect and ascertain possible causes of poor health. This interferes with beehive activity, which can then threaten even further hive health. This work uses Feature Engineering and Machine Learning to develop techniques to monitor hive health. The thesis aims at building an automation technique for finding the best feature subsets using datasets containing different classes of audio sounds. Selecting good features forms the basis for machine learning models to further classify these audio samples. The purpose of finding the best features is to get a better audio classification which helps beekeepers know about the health of beehives and address problems such as bee immunity, effects of pesticides and environmental and nutritional stressors from remote locations."]},{"key":"dc:title","label":"Title","values":["Automation of Feature Selection and Generation of Optimal Feature Subsets for Beehive Audio Sample Classification"]}]}],"canonical_facts":{"dc:contributor":["Vladimir Kulyukin","Nicholas Flann","Curtis Dyreson"],"dc:creator":["Bhouraskar, Aditya"],"dc:date.available":["2010-01-01T08:00:00Z"],"dc:date.created":["2020-12-01T08:00:00Z"],"dc:description.abstract":["The last couple of decades have witnessed an abnormal phenomenon of reduction in the bee population, this is a serious matter of concern as three out of four crops available globally have honey bee as their sole pollinator causing significant economic losses and an unbalance in the ecosystem. There have been many theories about the cause of bee colony collapses such as parasites, pesticides and poor nutrition however conclusive evidence of this phenomenon is yet to be identified. Human inspection of beehives requires precision. It takes an experienced beekeeper to determine the health of a hive by the sounds generated by the bees. If the sound indicates poor health, the beekeeper must then disrupt the hive to inspect and ascertain possible causes of poor health. This interferes with beehive activity, which can then threaten even further hive health. This work uses Feature Engineering and Machine Learning to develop techniques to monitor hive health. The thesis aims at building an automation technique for finding the best feature subsets using datasets containing different classes of audio sounds. Selecting good features forms the basis for machine learning models to further classify these audio samples. The purpose of finding the best features is to get a better audio classification which helps beekeepers know about the health of beehives and address problems such as bee immunity, effects of pesticides and environmental and nutritional stressors from remote locations."],"dc:identifier":["https://digitalcommons.usu.edu/etd/8006"],"dc:identifier.doi":["https://doi.org/10.26076/ba69-74be"],"dc:publisher":["Hosted by Utah State University Libraries"],"dc:subject":["feature selection","feature automation","beehive audio samples","Computer Sciences"],"dc:title":["Automation of Feature Selection and Generation of Optimal Feature Subsets for Beehive Audio Sample Classification"],"thesis:degree_discipline":["Computer Science"],"thesis:degree_level":["Thesis"],"thesis:degree_name":["Master of Science (MS)"]},"updated_at":"2026-11-19T08:52:04Z"}