{"id":{"repo_id":"csusb","oai_identifier":"oai:scholarworks.lib.csusb.edu:etd-2597"},"canonical_url":"https://search.ndltd.org/etd/csusb/oai:scholarworks.lib.csusb.edu:etd-2597","repository":{"repo_id":"csusb","name":"CSUniversity San Bernardino","base_url":"https://scholarworks.lib.csusb.edu/do/oai/"},"display":{"title":"Improved Sensor-Based Human Activity Recognition Via Hybrid Convolutional and Recurrent Neural Networks","abstract":"Non-intrusive sensor-based human activity recognition is utilized in a spectrum of applications including fitness tracking devices, gaming, health care monitoring, and smartphone applications. Deep learning models such as convolutional neural networks (CNNs) and long short-term memory (LSTMs) recurrent neural networks provide a way to achieve human activity recognition accurately and effectively. This project designed and explored a variety of multi-layer hybrid deep learning architectures which aimed to improve human activity recognition performance by integrating local features and was scale invariant with dependencies of activities. We achieved a 94.7% activity recognition rate on the University of California, Irvine public domain dataset for human activity recognition containing 6 activities with a 2-layer CNN-1-layer LSTM hybrid model. Additionally, we achieved an 88.0% activity recognition rate on the University of Texas at Dallas Multimodal Human Activity dataset containing 27 activities with a 4-layer CNN-1-layer LSTM hybrid model. For both datasets, our hybrid models outperformed other deep learning models and traditional machine learning methods.","abstract_html":"Non-intrusive sensor-based human activity recognition is utilized in a spectrum of applications including fitness tracking devices, gaming, health care monitoring, and smartphone applications. Deep learning models such as convolutional neural networks (CNNs) and long short-term memory (LSTMs) recurrent neural networks provide a way to achieve human activity recognition accurately and effectively. This project designed and explored a variety of multi-layer hybrid deep learning architectures which aimed to improve human activity recognition performance by integrating local features and was scale invariant with dependencies of activities. We achieved a 94.7% activity recognition rate on the University of California, Irvine public domain dataset for human activity recognition containing 6 activities with a 2-layer CNN-1-layer LSTM hybrid model. Additionally, we achieved an 88.0% activity recognition rate on the University of Texas at Dallas Multimodal Human Activity dataset containing 27 activities with a 4-layer CNN-1-layer LSTM hybrid model. For both datasets, our hybrid models outperformed other deep learning models and traditional machine learning methods.","abstract_has_math":false,"creators":["Perez-Gamboa, Sonia"],"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":["Qingquan Sun"],"advisors":[],"committee_chairs":[],"committee_members":[],"year":null,"date_issued":"","date_published":null,"updated_at":"2026-11-19T08:08:20Z","subjects":["Computer Science","Deep Learning","Human Activity Recognition","Artificial Intelligence and Robotics"],"languages":[],"rights":[],"rights_urls":[],"identifier_entries":[],"person_identifier_entries":[]},"links":{"outbound_url":"https://scholarworks.lib.csusb.edu/etd/1428","outbound_label":"Repository record","outbound_source":"dc:identifier","record_url":"https://scholarworks.lib.csusb.edu/etd/1428","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-2597","prefix":"oai_etdms"},"metadata_groups":[{"id":"people","label":"People","entries":[{"key":"dc:contributor","label":"Contributor","values":["Qingquan Sun"]},{"key":"dc:creator","label":"Author","values":["Perez-Gamboa, Sonia"]}]},{"id":"academic_context","label":"Academic Context","entries":[{"key":"dc:date.available","label":"Dc Date Available","values":["2022-04-15T07:00:00Z"]},{"key":"dc:date.created","label":"Dc Date Created","values":["2022-05-01T07:00:00Z"]},{"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":["Computer Science","Deep Learning","Human Activity Recognition","Artificial Intelligence and Robotics"]}]},{"id":"identifiers","label":"Identifiers","entries":[{"key":"dc:identifier","label":"Identifier","values":["https://scholarworks.lib.csusb.edu/etd/1428"]}]},{"id":"additional","label":"Additional Metadata","entries":[{"key":"dc:description.abstract","label":"Abstract","values":["Non-intrusive sensor-based human activity recognition is utilized in a spectrum of applications including fitness tracking devices, gaming, health care monitoring, and smartphone applications. Deep learning models such as convolutional neural networks (CNNs) and long short-term memory (LSTMs) recurrent neural networks provide a way to achieve human activity recognition accurately and effectively. This project designed and explored a variety of multi-layer hybrid deep learning architectures which aimed to improve human activity recognition performance by integrating local features and was scale invariant with dependencies of activities. We achieved a 94.7% activity recognition rate on the University of California, Irvine public domain dataset for human activity recognition containing 6 activities with a 2-layer CNN-1-layer LSTM hybrid model. Additionally, we achieved an 88.0% activity recognition rate on the University of Texas at Dallas Multimodal Human Activity dataset containing 27 activities with a 4-layer CNN-1-layer LSTM hybrid model. For both datasets, our hybrid models outperformed other deep learning models and traditional machine learning methods."]},{"key":"dc:title","label":"Title","values":["Improved Sensor-Based Human Activity Recognition Via Hybrid Convolutional and Recurrent Neural Networks"]}]}],"canonical_facts":{"dc:contributor":["Qingquan Sun"],"dc:creator":["Perez-Gamboa, Sonia"],"dc:date.available":["2022-04-15T07:00:00Z"],"dc:date.created":["2022-05-01T07:00:00Z"],"dc:description.abstract":["Non-intrusive sensor-based human activity recognition is utilized in a spectrum of applications including fitness tracking devices, gaming, health care monitoring, and smartphone applications. Deep learning models such as convolutional neural networks (CNNs) and long short-term memory (LSTMs) recurrent neural networks provide a way to achieve human activity recognition accurately and effectively. This project designed and explored a variety of multi-layer hybrid deep learning architectures which aimed to improve human activity recognition performance by integrating local features and was scale invariant with dependencies of activities. We achieved a 94.7% activity recognition rate on the University of California, Irvine public domain dataset for human activity recognition containing 6 activities with a 2-layer CNN-1-layer LSTM hybrid model. Additionally, we achieved an 88.0% activity recognition rate on the University of Texas at Dallas Multimodal Human Activity dataset containing 27 activities with a 4-layer CNN-1-layer LSTM hybrid model. For both datasets, our hybrid models outperformed other deep learning models and traditional machine learning methods."],"dc:identifier":["https://scholarworks.lib.csusb.edu/etd/1428"],"dc:subject":["Computer Science","Deep Learning","Human Activity Recognition","Artificial Intelligence and Robotics"],"dc:title":["Improved Sensor-Based Human Activity Recognition Via Hybrid Convolutional and Recurrent Neural Networks"],"thesis:degree_discipline":["School of Computer Science and Engineering"],"thesis:degree_level":["Project"],"thesis:degree_name":["Master of Science in Computer Science"]},"updated_at":"2026-11-19T08:08:20Z"}