{"id":{"repo_id":"vt","oai_identifier":"oai:vtechworks.lib.vt.edu:10919/138272"},"canonical_url":"https://search.dev.ndltd.org/etd/vt/oai:vtechworks.lib.vt.edu:10919/138272","repository":{"repo_id":"vt","name":"Virginia Tech","base_url":"https://vtechworks.lib.vt.edu/oai/request"},"display":{"title":"Accurate On-Body Distance Estimation using BLE RSSI and IMU Sensor Fusion","abstract":"Signal strength-based localization has gained significant traction, with technologies like Wi-Fi, BLE, and UWB being widely studied for indoor applications. However, the specific use of BLE Received Signal Strength Indicator (RSSI) for robust, short-range distance estimation on the human body remains a challenging area, primarily due to signal instability caused by multipath fading and body shadowing. This thesis presents a novel framework that fuses BLE RSSI with Inertial Measurement Unit (IMU) orientation data to overcome these limitations. We developed a custom wearable system using ESP32 microcontrollers and BNO085 IMUs and conducted a study with 6 human participants performing a series of defined arm movements. A high-precision XSens motion capture suit provided ground-truth data. This data was used to train a Long Short-Term Memory (LSTM) based model, termed QuaternionRNN, which leverages temporal sequences of normalized quaternions and RSSI to predict inter-sensor distances. The proposed model achieved a median absolute distance prediction error of approximately 3 cm on a generalized dataset. Furthermore, in a rigorous subject-wise cross-validation analysis, the model demonstrated strong generalization to unseen users, maintaining a median absolute error between 4-7 cm. This work establishes that fusing BLE RSSI with IMU data provides a cost-effective, accurate, and generalizable solution for on-body localization, offering a viable tool for applications in remote rehabilitation monitoring and human motion analysis.","abstract_html":"Signal strength-based localization has gained significant traction, with technologies like Wi-Fi, BLE, and UWB being widely studied for indoor applications. However, the specific use of BLE Received Signal Strength Indicator (RSSI) for robust, short-range distance estimation on the human body remains a challenging area, primarily due to signal instability caused by multipath fading and body shadowing. This thesis presents a novel framework that fuses BLE RSSI with Inertial Measurement Unit (IMU) orientation data to overcome these limitations. We developed a custom wearable system using ESP32 microcontrollers and BNO085 IMUs and conducted a study with 6 human participants performing a series of defined arm movements. A high-precision XSens motion capture suit provided ground-truth data. This data was used to train a Long Short-Term Memory (LSTM) based model, termed QuaternionRNN, which leverages temporal sequences of normalized quaternions and RSSI to predict inter-sensor distances. The proposed model achieved a median absolute distance prediction error of approximately 3 cm on a generalized dataset. Furthermore, in a rigorous subject-wise cross-validation analysis, the model demonstrated strong generalization to unseen users, maintaining a median absolute error between 4-7 cm. This work establishes that fusing BLE RSSI with IMU data provides a cost-effective, accurate, and generalizable solution for on-body localization, offering a viable tool for applications in remote rehabilitation monitoring and human motion analysis.","abstract_has_math":false,"creators":["Rajput, Aksh"],"institution":"Virginia Tech","degree_name":"Master of Science","degree_level":"masters","degree_discipline":"Mechanical Engineering","degree_department":"Mechanical Engineering","school":null,"contributors":[],"advisors":[],"committee_chairs":["Asbeck, Alan Thomas"],"committee_members":["Komendera, Erik","L'Afflitto, Andrea"],"year":2025,"date_issued":"2025-10-20","date_published":"2025-10-20","updated_at":"2026-07-22T22:20:11Z","subjects":["BLE","RSSI","IMU","ESP32","LSTM","QuarternionRNN","distance estimation"],"languages":["en"],"rights":["In Copyright"],"rights_urls":["http://rightsstatements.org/vocab/InC/1.0/"],"identifier_entries":[{"key":"dc:identifier.other","label":"Dc Identifier Other","values":["vt_gsexam:44795"],"render_values":[{"text":"vt_gsexam:44795","href":null,"code":true}]}]},"links":{"outbound_url":"https://hdl.handle.net/10919/138272","outbound_label":"Handle","outbound_source":"dc:identifier.uri"},"metadata_groups":[{"id":"people","label":"People","entries":[{"key":"dc:contributor.committeechair","label":"Committee Chair","values":["Asbeck, Alan Thomas"]},{"key":"dc:contributor.committeemember","label":"Committee Member","values":["Komendera, Erik","L'Afflitto, Andrea"]},{"key":"dc:contributor.department","label":"Department","values":["Mechanical Engineering"]},{"key":"dc:creator","label":"Author","values":["Rajput, Aksh"]}]},{"id":"academic_context","label":"Academic Context","entries":[{"key":"dc:date.accessioned","label":"Dc Date Accessioned","values":["2025-10-21T08:00:48Z"]},{"key":"dc:date.available","label":"Dc Date Available","values":["2025-10-21T08:00:48Z"]},{"key":"dc:date.issued","label":"Date","values":["2025-10-20"]},{"key":"dc:publisher","label":"Institution","values":["Virginia Tech"]},{"key":"dc:type","label":"Dc Type","values":["Thesis"]},{"key":"thesis:degree_discipline","label":"Discipline","values":["Mechanical Engineering"]},{"key":"thesis:degree_level","label":"Degree Level","values":["masters"]},{"key":"thesis:degree_name","label":"Degree Name","values":["Master of Science"]},{"key":"thesis:institution_name","label":"Thesis Institution Name","values":["Virginia Polytechnic Institute and State University"]}]},{"id":"subjects_keywords","label":"Subjects and Keywords","entries":[{"key":"dc:subject","label":"Dc Subject","values":["BLE","RSSI","IMU","ESP32","LSTM","QuarternionRNN","distance estimation"]}]},{"id":"language_rights","label":"Language and Rights","entries":[{"key":"dc:language.iso","label":"Language (ISO)","values":["en"]},{"key":"dc:rights","label":"Dc Rights","values":["In Copyright"]},{"key":"dc:rights.uri","label":"Rights URI","values":["http://rightsstatements.org/vocab/InC/1.0/"]}]},{"id":"identifiers","label":"Identifiers","entries":[{"key":"dc:identifier.other","label":"Dc Identifier Other","values":["vt_gsexam:44795"]},{"key":"dc:identifier.uri","label":"Identifier URI","values":["https://hdl.handle.net/10919/138272"]}]},{"id":"additional","label":"Additional Metadata","entries":[{"key":"dc:description.abstract","label":"Abstract","values":["Signal strength-based localization has gained significant traction, with technologies like Wi-Fi, BLE, and UWB being widely studied for indoor applications. However, the specific use of BLE Received Signal Strength Indicator (RSSI) for robust, short-range distance estimation on the human body remains a challenging area, primarily due to signal instability caused by multipath fading and body shadowing. This thesis presents a novel framework that fuses BLE RSSI with Inertial Measurement Unit (IMU) orientation data to overcome these limitations. We developed a custom wearable system using ESP32 microcontrollers and BNO085 IMUs and conducted a study with 6 human participants performing a series of defined arm movements. A high-precision XSens motion capture suit provided ground-truth data. This data was used to train a Long Short-Term Memory (LSTM) based model, termed QuaternionRNN, which leverages temporal sequences of normalized quaternions and RSSI to predict inter-sensor distances. The proposed model achieved a median absolute distance prediction error of approximately 3 cm on a generalized dataset. Furthermore, in a rigorous subject-wise cross-validation analysis, the model demonstrated strong generalization to unseen users, maintaining a median absolute error between 4-7 cm. This work establishes that fusing BLE RSSI with IMU data provides a cost-effective, accurate, and generalizable solution for on-body localization, offering a viable tool for applications in remote rehabilitation monitoring and human motion analysis."]},{"key":"dc:description.abstractgeneral","label":"General Abstract","values":["For patients recovering from a stroke, therapy often involves specific arm and hand exercises. Tracking their movement and progress outside of a clinical setting, however, is difficult. Professional motion capture systems are expensive, complex, and confined to specialized labs. This research focuses on developing a simple, low-cost wearable sensor that can accurately track a patient's limb movements at home. We built a small device, about the size of a wristwatch, that combines two types of sensors: one that measures wireless signal strength (like the bars on your phone) and another that tracks orientation (like how your phone knows when you turn it sideways). By cleverly combining the data from these two sensors using artificial intelligence, our system can precisely measure the distance between a patient's hand and their body as they move. In our study, we found this wearable system can predict this distance with an accuracy of about 3-7 centimeters (1-3 inches). This technology could one day allow therapists to monitor their patients' recovery remotely, providing valuable feedback and making rehabilitation more accessible and effective."]},{"key":"dc:description.degree","label":"Dc Description Degree","values":["Master of Science"]},{"key":"dc:format.medium","label":"Dc Format Medium","values":["ETD"]},{"key":"dc:title","label":"Title","values":["Accurate On-Body Distance Estimation using BLE RSSI and IMU Sensor Fusion"]}]}],"canonical_facts":{"dc:contributor.committeechair":["Asbeck, Alan Thomas"],"dc:contributor.committeemember":["Komendera, Erik","L'Afflitto, Andrea"],"dc:contributor.department":["Mechanical Engineering"],"dc:creator":["Rajput, Aksh"],"dc:date.accessioned":["2025-10-21T08:00:48Z"],"dc:date.available":["2025-10-21T08:00:48Z"],"dc:date.issued":["2025-10-20"],"dc:description.abstract":["Signal strength-based localization has gained significant traction, with technologies like Wi-Fi, BLE, and UWB being widely studied for indoor applications. However, the specific use of BLE Received Signal Strength Indicator (RSSI) for robust, short-range distance estimation on the human body remains a challenging area, primarily due to signal instability caused by multipath fading and body shadowing. This thesis presents a novel framework that fuses BLE RSSI with Inertial Measurement Unit (IMU) orientation data to overcome these limitations. We developed a custom wearable system using ESP32 microcontrollers and BNO085 IMUs and conducted a study with 6 human participants performing a series of defined arm movements. A high-precision XSens motion capture suit provided ground-truth data. This data was used to train a Long Short-Term Memory (LSTM) based model, termed QuaternionRNN, which leverages temporal sequences of normalized quaternions and RSSI to predict inter-sensor distances. The proposed model achieved a median absolute distance prediction error of approximately 3 cm on a generalized dataset. Furthermore, in a rigorous subject-wise cross-validation analysis, the model demonstrated strong generalization to unseen users, maintaining a median absolute error between 4-7 cm. This work establishes that fusing BLE RSSI with IMU data provides a cost-effective, accurate, and generalizable solution for on-body localization, offering a viable tool for applications in remote rehabilitation monitoring and human motion analysis."],"dc:description.abstractgeneral":["For patients recovering from a stroke, therapy often involves specific arm and hand exercises. Tracking their movement and progress outside of a clinical setting, however, is difficult. Professional motion capture systems are expensive, complex, and confined to specialized labs. This research focuses on developing a simple, low-cost wearable sensor that can accurately track a patient's limb movements at home. We built a small device, about the size of a wristwatch, that combines two types of sensors: one that measures wireless signal strength (like the bars on your phone) and another that tracks orientation (like how your phone knows when you turn it sideways). By cleverly combining the data from these two sensors using artificial intelligence, our system can precisely measure the distance between a patient's hand and their body as they move. In our study, we found this wearable system can predict this distance with an accuracy of about 3-7 centimeters (1-3 inches). This technology could one day allow therapists to monitor their patients' recovery remotely, providing valuable feedback and making rehabilitation more accessible and effective."],"dc:description.degree":["Master of Science"],"dc:format.medium":["ETD"],"dc:identifier.other":["vt_gsexam:44795"],"dc:identifier.uri":["https://hdl.handle.net/10919/138272"],"dc:language.iso":["en"],"dc:publisher":["Virginia Tech"],"dc:rights":["In Copyright"],"dc:rights.uri":["http://rightsstatements.org/vocab/InC/1.0/"],"dc:subject":["BLE","RSSI","IMU","ESP32","LSTM","QuarternionRNN","distance estimation"],"dc:title":["Accurate On-Body Distance Estimation using BLE RSSI and IMU Sensor Fusion"],"dc:type":["Thesis"],"thesis:degree_discipline":["Mechanical Engineering"],"thesis:degree_level":["masters"],"thesis:degree_name":["Master of Science"],"thesis:institution_name":["Virginia Polytechnic Institute and State University"]},"updated_at":"2026-07-22T22:20:11Z"}