Predicting continuous hand pose from wearable EMG sensor data using transformer-based deep-learning models
Saved in:
| Title: | Predicting continuous hand pose from wearable EMG sensor data using transformer-based deep-learning models |
|---|---|
| Authors: | McDowell, Jason |
| Committee Members: | Kaplanoglu, Erkan; Varol, Serkan; Abrha, Wolday D.; College of Engineering and Computer Science |
| Summary: | 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. |
| URL: | https://scholar.utc.edu/theses/1019 |
| Database: | OpenDissertations |
| FullText | Text: Availability: 0 |
|---|---|
| Header | DbId: ddu DbLabel: OpenDissertations An: ddu.oai.scholar.utc.edu.theses.2201 AccessLevel: 6 PubType: Dissertation/ Thesis PubTypeId: dissertation PreciseRelevancyScore: 0 |
| IllustrationInfo | |
| Items | – Name: Title Label: Title Group: Ti Data: Predicting continuous hand pose from wearable EMG sensor data using transformer-based deep-learning models – Name: Author Label: Authors Group: Au Data: <searchLink fieldCode="AR" term="%22McDowell%2C+Jason%22">McDowell, Jason</searchLink> – Name: Author Label: Committee Members Group: Au Data: <searchLink fieldCode="CO" term="%22Kaplanoglu%2C+Erkan%22">Kaplanoglu, Erkan</searchLink>; <searchLink fieldCode="CO" term="%22Varol%2C+Serkan%22">Varol, Serkan</searchLink>; <searchLink fieldCode="CO" term="%22Abrha%2C+Wolday+D%2E%22">Abrha, Wolday D.</searchLink>; <searchLink fieldCode="CO" term="%22College+of+Engineering+and+Computer+Science%22">College of Engineering and Computer Science</searchLink> – Name: Abstract Label: Summary Group: Ab Data: 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. – Name: URL Label: URL Group: URL Data: <link linkTarget="URL" linkTerm="https://scholar.utc.edu/theses/1019" linkWindow="_blank">https://scholar.utc.edu/theses/1019</link> |
| PLink | https://search.ebscohost.com/login.aspx?direct=true&site=eds-live&db=ddu&AN=ddu.oai.scholar.utc.edu.theses.2201 |
| RecordInfo | BibRecord: BibEntity: Languages: – Code: eng Text: English Subjects: – SubjectFull: Electromyography Type: general – SubjectFull: Hand--Movements--Measurement Type: general – SubjectFull: Human activity recognition Type: general – SubjectFull: Human-machine systems Type: general Titles: – TitleFull: Predicting continuous hand pose from wearable EMG sensor data using transformer-based deep-learning models Type: main BibRelationships: HasContributorRelationships: – PersonEntity: Name: NameFull: McDowell, Jason IsPartOfRelationships: – BibEntity: Dates: – D: 01 M: 08 Type: published Y: 2025 |
| ResultId | 1 |
