{"id":{"repo_id":"carleton","oai_identifier":"oai:carleton.scholaris.ca:20.500.14718/45274"},"canonical_url":"https://search.dev.ndltd.org/etd/carleton/oai:carleton.scholaris.ca:20.500.14718/45274","repository":{"repo_id":"carleton","name":"Carleton University","base_url":"https://carleton.scholaris.ca/server/oai/request"},"display":{"title":"Human Activity Recognition using Hearing Aids","abstract":"As people age, monitoring physical activity becomes increasingly important for assessing and maintaining health. Wearable devices are a promising means of accomplishing this measurement since they are unobtrusive, portable, and accessible. This thesis investigates the feasibility of using hearing aid accelerometers for step counting, functional mobility assessment, and human activity recognition (HAR) under free living conditions. The use of ear-worn sensors for pedometry was validated using commercial hearing aids with integrated accelerometers. Algorithms for the automatic assessment of timed up and go and sit to stand timing were proposed and validated on hearing aid accelerometer data. To improve HAR accuracy using a deep learning model for ear-based accelerometers, two methods were proposed. First, transfer learning was used to supplement the limited number of head worn accelerometer datasets by using data recorded across the body. Second, sensor fusion from both ears was demonstrated to improve the deep learning model’s accuracy.","abstract_html":"As people age, monitoring physical activity becomes increasingly important for assessing and maintaining health. Wearable devices are a promising means of accomplishing this measurement since they are unobtrusive, portable, and accessible. This thesis investigates the feasibility of using hearing aid accelerometers for step counting, functional mobility assessment, and human activity recognition (HAR) under free living conditions. The use of ear-worn sensors for pedometry was validated using commercial hearing aids with integrated accelerometers. Algorithms for the automatic assessment of timed up and go and sit to stand timing were proposed and validated on hearing aid accelerometer data. To improve HAR accuracy using a deep learning model for ear-based accelerometers, two methods were proposed. First, transfer learning was used to supplement the limited number of head worn accelerometer datasets by using data recorded across the body. Second, sensor fusion from both ears was demonstrated to improve the deep learning model’s accuracy.","abstract_has_math":false,"creators":["Sloan, William Robert"],"institution":"Carleton University","degree_name":"Master of Applied Science (M.App.Sc.)","degree_level":"Master's","degree_discipline":"Engineering, Electrical and Computer","degree_department":null,"school":null,"contributors":[],"advisors":[],"committee_chairs":[],"committee_members":[],"year":2026,"date_issued":"2026","date_published":"2026","updated_at":"2026-07-24T01:34:34Z","subjects":[],"languages":["en"],"rights":["Copyright © 2026 the author(s). Theses may be used for non-commercial research, educational, or related academic purposes only. Such uses include personal study, distribution to students, research and scholarship. Theses may only be shared by linking to the Carleton University Institutional Repository and no part may be copied without proper attribution to the author; no part may be used for commercial purposes directly or indirectly via a for-profit platform; no adaptation or derivative works are permitted without consent from the copyright owner."],"rights_urls":[],"identifier_entries":[{"key":"dc:identifier.doi","label":"DOI","values":["10.22215/etd/2026-17117"],"render_values":[{"text":"10.22215/etd/2026-17117","href":"https://doi.org/10.22215/etd/2026-17117","code":true}]}]},"links":{"outbound_url":"https://hdl.handle.net/20.500.14718/45274","outbound_label":"Handle","outbound_source":"dc:identifier.uri"},"metadata_groups":[{"id":"people","label":"People","entries":[{"key":"dc:creator","label":"Author","values":["Sloan, William Robert"]}]},{"id":"academic_context","label":"Academic Context","entries":[{"key":"dc:date.accessioned","label":"Dc Date Accessioned","values":["2026-07-22T18:52:35Z"]},{"key":"dc:date.issued","label":"Date","values":["2026"]},{"key":"dc:publisher","label":"Institution","values":["Carleton University"]},{"key":"dc:type","label":"Dc Type","values":["thesis"]},{"key":"thesis:degree_discipline","label":"Discipline","values":["Engineering, Electrical and Computer"]},{"key":"thesis:degree_level","label":"Degree Level","values":["Master's"]},{"key":"thesis:degree_name","label":"Degree Name","values":["Master of Applied Science (M.App.Sc.)"]}]},{"id":"language_rights","label":"Language and Rights","entries":[{"key":"dc:language.iso","label":"Language (ISO)","values":["en"]},{"key":"dc:rights","label":"Dc Rights","values":["Copyright © 2026 the author(s). Theses may be used for non-commercial research, educational, or related academic purposes only. Such uses include personal study, distribution to students, research and scholarship. Theses may only be shared by linking to the Carleton University Institutional Repository and no part may be copied without proper attribution to the author; no part may be used for commercial purposes directly or indirectly via a for-profit platform; no adaptation or derivative works are permitted without consent from the copyright owner."]}]},{"id":"identifiers","label":"Identifiers","entries":[{"key":"dc:identifier.doi","label":"DOI","values":["10.22215/etd/2026-17117"]},{"key":"dc:identifier.uri","label":"Identifier URI","values":["https://hdl.handle.net/20.500.14718/45274"]}]},{"id":"additional","label":"Additional Metadata","entries":[{"key":"dc:description.abstract","label":"Abstract","values":["As people age, monitoring physical activity becomes increasingly important for assessing and maintaining health. Wearable devices are a promising means of accomplishing this measurement since they are unobtrusive, portable, and accessible. This thesis investigates the feasibility of using hearing aid accelerometers for step counting, functional mobility assessment, and human activity recognition (HAR) under free living conditions. The use of ear-worn sensors for pedometry was validated using commercial hearing aids with integrated accelerometers. Algorithms for the automatic assessment of timed up and go and sit to stand timing were proposed and validated on hearing aid accelerometer data. To improve HAR accuracy using a deep learning model for ear-based accelerometers, two methods were proposed. First, transfer learning was used to supplement the limited number of head worn accelerometer datasets by using data recorded across the body. Second, sensor fusion from both ears was demonstrated to improve the deep learning model’s accuracy."]},{"key":"dc:title","label":"Title","values":["Human Activity Recognition using Hearing Aids"]}]}],"canonical_facts":{"dc:creator":["Sloan, William Robert"],"dc:date.accessioned":["2026-07-22T18:52:35Z"],"dc:date.issued":["2026"],"dc:description.abstract":["As people age, monitoring physical activity becomes increasingly important for assessing and maintaining health. Wearable devices are a promising means of accomplishing this measurement since they are unobtrusive, portable, and accessible. This thesis investigates the feasibility of using hearing aid accelerometers for step counting, functional mobility assessment, and human activity recognition (HAR) under free living conditions. The use of ear-worn sensors for pedometry was validated using commercial hearing aids with integrated accelerometers. Algorithms for the automatic assessment of timed up and go and sit to stand timing were proposed and validated on hearing aid accelerometer data. To improve HAR accuracy using a deep learning model for ear-based accelerometers, two methods were proposed. First, transfer learning was used to supplement the limited number of head worn accelerometer datasets by using data recorded across the body. Second, sensor fusion from both ears was demonstrated to improve the deep learning model’s accuracy."],"dc:identifier.doi":["10.22215/etd/2026-17117"],"dc:identifier.uri":["https://hdl.handle.net/20.500.14718/45274"],"dc:language.iso":["en"],"dc:publisher":["Carleton University"],"dc:rights":["Copyright © 2026 the author(s). Theses may be used for non-commercial research, educational, or related academic purposes only. Such uses include personal study, distribution to students, research and scholarship. Theses may only be shared by linking to the Carleton University Institutional Repository and no part may be copied without proper attribution to the author; no part may be used for commercial purposes directly or indirectly via a for-profit platform; no adaptation or derivative works are permitted without consent from the copyright owner."],"dc:title":["Human Activity Recognition using Hearing Aids"],"dc:type":["thesis"],"thesis:degree_discipline":["Engineering, Electrical and Computer"],"thesis:degree_level":["Master's"],"thesis:degree_name":["Master of Applied Science (M.App.Sc.)"]},"updated_at":"2026-07-24T01:34:34Z"}