{"id":{"repo_id":"csusb","oai_identifier":"oai:scholarworks.lib.csusb.edu:etd-1864"},"canonical_url":"https://search.ndltd.org/etd/csusb/oai:scholarworks.lib.csusb.edu:etd-1864","repository":{"repo_id":"csusb","name":"CSUniversity San Bernardino","base_url":"https://scholarworks.lib.csusb.edu/do/oai/"},"display":{"title":"SENSOR-BASED HUMAN ACTIVITY RECOGNITION USING BIDIRECTIONAL LSTM FOR CLOSELY RELATED ACTIVITIES","abstract":"Recognizing human activities using deep learning methods has significance in many fields such as sports, motion tracking, surveillance, healthcare and robotics. Inertial sensors comprising of accelerometers and gyroscopes are commonly used for sensor based HAR. In this study, a Bidirectional Long Short-Term Memory (BLSTM) approach is explored for human activity recognition and classification for closely related activities on a body worn inertial sensor data that is provided by the UTD-MHAD dataset. The BLSTM model of this study could achieve an overall accuracy of 98.05% for 15 different activities and 90.87% for 27 different activities performed by 8 persons with 4 trials per activity per person. A comparison of this BLSTM model is made with the Unidirectional LSTM model. It is observed that there is a significant improvement in the accuracy for recognition of all 27 activities in the case of BLSTM than LSTM.","abstract_html":"Recognizing human activities using deep learning methods has significance in many fields such as sports, motion tracking, surveillance, healthcare and robotics. Inertial sensors comprising of accelerometers and gyroscopes are commonly used for sensor based HAR. In this study, a Bidirectional Long Short-Term Memory (BLSTM) approach is explored for human activity recognition and classification for closely related activities on a body worn inertial sensor data that is provided by the UTD-MHAD dataset. The BLSTM model of this study could achieve an overall accuracy of 98.05% for 15 different activities and 90.87% for 27 different activities performed by 8 persons with 4 trials per activity per person. A comparison of this BLSTM model is made with the Unidirectional LSTM model. It is observed that there is a significant improvement in the accuracy for recognition of all 27 activities in the case of BLSTM than LSTM.","abstract_has_math":false,"creators":["Pavai, Arumugam Thendramil"],"institution":null,"degree_name":"Master of Science in Computer Science","degree_level":"Project","degree_discipline":"School of Computer Science and Engineering","degree_department":null,"school":null,"contributors":["Sun, Qingquan"],"advisors":[],"committee_chairs":[],"committee_members":[],"year":null,"date_issued":"","date_published":null,"updated_at":"2026-11-19T08:06:34Z","subjects":["deep learning","inertial sensors","human activity recognition","bidirectional long short-term memory","Artificial Intelligence and Robotics","Computer Engineering","Computer Sciences"],"languages":[],"rights":[],"rights_urls":[],"identifier_entries":[],"person_identifier_entries":[]},"links":{"outbound_url":"https://scholarworks.lib.csusb.edu/etd/776","outbound_label":"Repository record","outbound_source":"dc:identifier","record_url":"https://scholarworks.lib.csusb.edu/etd/776","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://scholarworks.lib.csusb.edu/do/oai/?verb=GetRecord&metadataPrefix=oai_etdms&identifier=oai%3Ascholarworks.lib.csusb.edu%3Aetd-1864","prefix":"oai_etdms"},"metadata_groups":[{"id":"people","label":"People","entries":[{"key":"dc:contributor","label":"Contributor","values":["Sun, Qingquan"]},{"key":"dc:creator","label":"Author","values":["Pavai, Arumugam Thendramil"]}]},{"id":"academic_context","label":"Academic Context","entries":[{"key":"dc:date.available","label":"Dc Date Available","values":["2018-11-09T08:00:00Z"]},{"key":"dc:date.created","label":"Dc Date Created","values":["2018-12-01T08:00:00Z"]},{"key":"thesis:degree_discipline","label":"Discipline","values":["School of Computer Science and Engineering"]},{"key":"thesis:degree_level","label":"Degree Level","values":["Project"]},{"key":"thesis:degree_name","label":"Degree Name","values":["Master of Science in Computer Science"]}]},{"id":"subjects_keywords","label":"Subjects and Keywords","entries":[{"key":"dc:subject","label":"Dc Subject","values":["deep learning","inertial sensors","human activity recognition","bidirectional long short-term memory","Artificial Intelligence and Robotics","Computer Engineering","Computer Sciences"]}]},{"id":"identifiers","label":"Identifiers","entries":[{"key":"dc:identifier","label":"Identifier","values":["https://scholarworks.lib.csusb.edu/etd/776"]}]},{"id":"additional","label":"Additional Metadata","entries":[{"key":"dc:description.abstract","label":"Abstract","values":["Recognizing human activities using deep learning methods has significance in many fields such as sports, motion tracking, surveillance, healthcare and robotics. Inertial sensors comprising of accelerometers and gyroscopes are commonly used for sensor based HAR. In this study, a Bidirectional Long Short-Term Memory (BLSTM) approach is explored for human activity recognition and classification for closely related activities on a body worn inertial sensor data that is provided by the UTD-MHAD dataset. The BLSTM model of this study could achieve an overall accuracy of 98.05% for 15 different activities and 90.87% for 27 different activities performed by 8 persons with 4 trials per activity per person. A comparison of this BLSTM model is made with the Unidirectional LSTM model. It is observed that there is a significant improvement in the accuracy for recognition of all 27 activities in the case of BLSTM than LSTM."]},{"key":"dc:title","label":"Title","values":["SENSOR-BASED HUMAN ACTIVITY RECOGNITION USING BIDIRECTIONAL LSTM FOR CLOSELY RELATED ACTIVITIES"]}]}],"canonical_facts":{"dc:contributor":["Sun, Qingquan"],"dc:creator":["Pavai, Arumugam Thendramil"],"dc:date.available":["2018-11-09T08:00:00Z"],"dc:date.created":["2018-12-01T08:00:00Z"],"dc:description.abstract":["Recognizing human activities using deep learning methods has significance in many fields such as sports, motion tracking, surveillance, healthcare and robotics. Inertial sensors comprising of accelerometers and gyroscopes are commonly used for sensor based HAR. In this study, a Bidirectional Long Short-Term Memory (BLSTM) approach is explored for human activity recognition and classification for closely related activities on a body worn inertial sensor data that is provided by the UTD-MHAD dataset. The BLSTM model of this study could achieve an overall accuracy of 98.05% for 15 different activities and 90.87% for 27 different activities performed by 8 persons with 4 trials per activity per person. A comparison of this BLSTM model is made with the Unidirectional LSTM model. It is observed that there is a significant improvement in the accuracy for recognition of all 27 activities in the case of BLSTM than LSTM."],"dc:identifier":["https://scholarworks.lib.csusb.edu/etd/776"],"dc:subject":["deep learning","inertial sensors","human activity recognition","bidirectional long short-term memory","Artificial Intelligence and Robotics","Computer Engineering","Computer Sciences"],"dc:title":["SENSOR-BASED HUMAN ACTIVITY RECOGNITION USING BIDIRECTIONAL LSTM FOR CLOSELY RELATED ACTIVITIES"],"thesis:degree_discipline":["School of Computer Science and Engineering"],"thesis:degree_level":["Project"],"thesis:degree_name":["Master of Science in Computer Science"]},"updated_at":"2026-11-19T08:06:34Z"}