{"id":{"repo_id":"utc","oai_identifier":"oai:scholar.utc.edu:theses-2201"},"canonical_url":"https://search.dev.ndltd.org/etd/utc/oai:scholar.utc.edu:theses-2201","repository":{"repo_id":"utc","name":"University of Tennessee - Chattanooga","base_url":"https://scholar.utc.edu/do/oai/"},"display":{"title":"Predicting continuous hand pose from wearable EMG sensor data using transformer-based deep-learning models","abstract":"This thesis investigated Transformer-based deep-learning models for predicting continuous hand pose from electromyography (EMG) signals collected with a low-cost, eight-channel wearable armband. A modular software laboratory was developed to support data acquisition, synchronization, visualization, model training, and inference. A single-subject, three-hour dataset of synchronized EMG and hand-tracking data was collected, with hand pose represented both as 15-dimensional joint flexion angles and 84-dimensional finger-bone orientation quaternions in a hand-centered frame. Compared with a Long Short-Term Memory (LSTM)-based model, the Transformer-based model reduced whole-hand median prediction error from 3.6° to 3.3° for a joint angle model and from 17.4° to 15.1° for a bone orientation model. Experimental results demonstrated that Transformer models outperformed LSTM models in both median and 90th-percentile prediction error, particularly for angle-based outputs. These findings support the use of Transformer architectures for accurate, continuous hand-pose estimation with wearable EMG, relevant to applications in prosthetics and human-machine interfaces.","abstract_html":"This thesis investigated Transformer-based deep-learning models for predicting continuous hand pose from electromyography (EMG) signals collected with a low-cost, eight-channel wearable armband. A modular software laboratory was developed to support data acquisition, synchronization, visualization, model training, and inference. A single-subject, three-hour dataset of synchronized EMG and hand-tracking data was collected, with hand pose represented both as 15-dimensional joint flexion angles and 84-dimensional finger-bone orientation quaternions in a hand-centered frame. Compared with a Long Short-Term Memory (LSTM)-based model, the Transformer-based model reduced whole-hand median prediction error from 3.6° to 3.3° for a joint angle model and from 17.4° to 15.1° for a bone orientation model. Experimental results demonstrated that Transformer models outperformed LSTM models in both median and 90th-percentile prediction error, particularly for angle-based outputs. These findings support the use of Transformer architectures for accurate, continuous hand-pose estimation with wearable EMG, relevant to applications in prosthetics and human-machine interfaces.","abstract_has_math":false,"creators":["McDowell, Jason"],"institution":"University of Tennessee at Chattanooga","degree_name":null,"degree_level":null,"degree_discipline":null,"degree_department":null,"school":null,"contributors":["Kaplanoglu, Erkan","Varol, Serkan; Abrha, Wolday D.","College of Engineering and Computer Science"],"advisors":[],"committee_chairs":[],"committee_members":[],"year":null,"date_issued":"","date_published":null,"updated_at":"2026-07-24T05:47:28Z","subjects":["Electromyography","Hand--Movements--Measurement","Human activity recognition","Human-machine systems"],"languages":["English","eng"],"rights":[],"rights_urls":["http://rightsstatements.org/vocab/InC/1.0/"],"identifier_entries":[]},"links":{"outbound_url":"https://scholar.utc.edu/theses/1019","outbound_label":"Repository record","outbound_source":"dc:identifier"},"metadata_groups":[{"id":"people","label":"People","entries":[{"key":"dc:contributor","label":"Contributor","values":["Kaplanoglu, Erkan","Varol, Serkan; Abrha, Wolday D.","College of Engineering and Computer Science"]},{"key":"dc:creator","label":"Author","values":["McDowell, Jason"]}]},{"id":"academic_context","label":"Academic Context","entries":[{"key":"dc:date","label":"Dc Date","values":["2025-08-01T07:00:00Z"]},{"key":"dc:publisher","label":"Institution","values":["University of Tennessee at Chattanooga","Chattanooga (Tenn.)"]},{"key":"dc:relation","label":"Dc Relation","values":["Masters Theses and Doctoral Dissertations"]},{"key":"dc:type","label":"Dc Type","values":["Masters theses","Text"]}]},{"id":"subjects_keywords","label":"Subjects and Keywords","entries":[{"key":"dc:subject","label":"Dc Subject","values":["Electromyography","Hand--Movements--Measurement","Human activity recognition","Human-machine systems"]}]},{"id":"language_rights","label":"Language and Rights","entries":[{"key":"dc:language","label":"Dc Language","values":["English","eng"]},{"key":"dc:rights","label":"Dc Rights","values":["http://rightsstatements.org/vocab/InC/1.0/"]}]},{"id":"identifiers","label":"Identifiers","entries":[{"key":"dc:identifier","label":"Identifier","values":["https://scholar.utc.edu/theses/1019"]}]},{"id":"additional","label":"Additional Metadata","entries":[{"key":"dc:description","label":"Description","values":["Dept. of Engineering Management","M. S.; A thesis submitted to the faculty of the University of Tennessee at Chattanooga in partial fulfillment of the requirements of the degree of Master of Science."]},{"key":"dc:description.abstract","label":"Abstract","values":["This thesis investigated Transformer-based deep-learning models for predicting continuous hand pose from electromyography (EMG) signals collected with a low-cost, eight-channel wearable armband. A modular software laboratory was developed to support data acquisition, synchronization, visualization, model training, and inference. A single-subject, three-hour dataset of synchronized EMG and hand-tracking data was collected, with hand pose represented both as 15-dimensional joint flexion angles and 84-dimensional finger-bone orientation quaternions in a hand-centered frame. Compared with a Long Short-Term Memory (LSTM)-based model, the Transformer-based model reduced whole-hand median prediction error from 3.6° to 3.3° for a joint angle model and from 17.4° to 15.1° for a bone orientation model. Experimental results demonstrated that Transformer models outperformed LSTM models in both median and 90th-percentile prediction error, particularly for angle-based outputs. These findings support the use of Transformer architectures for accurate, continuous hand-pose estimation with wearable EMG, relevant to applications in prosthetics and human-machine interfaces."]},{"key":"dc:title","label":"Title","values":["Predicting continuous hand pose from wearable EMG sensor data using transformer-based deep-learning models"]}]}],"canonical_facts":{"dc:contributor":["Kaplanoglu, Erkan","Varol, Serkan; Abrha, Wolday D.","College of Engineering and Computer Science"],"dc:creator":["McDowell, Jason"],"dc:date":["2025-08-01T07:00:00Z"],"dc:description":["Dept. of Engineering Management","M. S.; A thesis submitted to the faculty of the University of Tennessee at Chattanooga in partial fulfillment of the requirements of the degree of Master of Science."],"dc:description.abstract":["This thesis investigated Transformer-based deep-learning models for predicting continuous hand pose from electromyography (EMG) signals collected with a low-cost, eight-channel wearable armband. A modular software laboratory was developed to support data acquisition, synchronization, visualization, model training, and inference. A single-subject, three-hour dataset of synchronized EMG and hand-tracking data was collected, with hand pose represented both as 15-dimensional joint flexion angles and 84-dimensional finger-bone orientation quaternions in a hand-centered frame. Compared with a Long Short-Term Memory (LSTM)-based model, the Transformer-based model reduced whole-hand median prediction error from 3.6° to 3.3° for a joint angle model and from 17.4° to 15.1° for a bone orientation model. Experimental results demonstrated that Transformer models outperformed LSTM models in both median and 90th-percentile prediction error, particularly for angle-based outputs. These findings support the use of Transformer architectures for accurate, continuous hand-pose estimation with wearable EMG, relevant to applications in prosthetics and human-machine interfaces."],"dc:identifier":["https://scholar.utc.edu/theses/1019"],"dc:language":["English","eng"],"dc:publisher":["University of Tennessee at Chattanooga","Chattanooga (Tenn.)"],"dc:relation":["Masters Theses and Doctoral Dissertations"],"dc:rights":["http://rightsstatements.org/vocab/InC/1.0/"],"dc:subject":["Electromyography","Hand--Movements--Measurement","Human activity recognition","Human-machine systems"],"dc:title":["Predicting continuous hand pose from wearable EMG sensor data using transformer-based deep-learning models"],"dc:type":["Masters theses","Text"]},"updated_at":"2026-07-24T05:47:28Z"}