TraxVBF: A hybrid transformer-xLSTM framework for EMG signal processing and assistive technology development in rehabilitation
The fact that people with mobility impairments often have great difficulties in performing essential Activities of Daily Living (ADL) shows the importance of developing effective rehabilitation strategies. To address this need, we propose TraxVBF, a multimodal visual biofeedback submodel using surfa...
Saved in:
| Main Authors: | , , , , |
|---|---|
| Format: | Article |
| Language: | English |
| Published: |
Elsevier
2025-02-01
|
| Series: | Sensing and Bio-Sensing Research |
| Subjects: | |
| Online Access: | http://www.sciencedirect.com/science/article/pii/S2214180425000157 |
| Tags: |
Add Tag
No Tags, Be the first to tag this record!
|
| _version_ | 1832583099986214912 |
|---|---|
| author | Seyyed Ali Zendehbad Athena Sharifi Razavi Marzieh Allami Sanjani Zahra Sedaghat Saleh Lashkari |
| author_facet | Seyyed Ali Zendehbad Athena Sharifi Razavi Marzieh Allami Sanjani Zahra Sedaghat Saleh Lashkari |
| author_sort | Seyyed Ali Zendehbad |
| collection | DOAJ |
| description | The fact that people with mobility impairments often have great difficulties in performing essential Activities of Daily Living (ADL) shows the importance of developing effective rehabilitation strategies. To address this need, we propose TraxVBF, a multimodal visual biofeedback submodel using surface Electromyography (sEMG) signals and kinematic movement data to exploit muscle synergy patterns. TraxVBF offers innovative real time visual feedback that can be used to enhance neurorehabilitation systems. Pre-processing and extracting muscle synergy patterns is performed by the Hierarchical Fast Alternating Least Squares (Fast-HALS) algorithm, and key movement points are identified with the Modified MediaPipe algorithm to capture temporal and spatial dynamics with precision using TraxVBF, which is driven by Extended Long Short-Term Memory (xLSTM) and Transformer architectures. This allows the model to predict movement trajectories accurately, enabling motor learning and functional recovery of patients through real time feedback without the expensive hardware. The model is shown to significantly improve performance metrics such as Mean Square Error (MSE), Root Mean Square Error (RMSE), and Coefficient of Determination (R2). For healthy participants, TraxVBF-type Base outperforms state of the art models (LSTM and GRU) with an MSE of 0.06 and R2 of 0.89. Practical evaluations with an average R2 of 0.880 for healthy participants and 0.327 for patients demonstrate the model generalizability. These results indicate that TraxVBF may be a useful tool to improve motor learning and rehabilitation, and longer term clinical trials and multi-sensory biofeedback are needed. |
| format | Article |
| id | doaj-art-8a717729ad0243c0a1db582a9bf9a78a |
| institution | Kabale University |
| issn | 2214-1804 |
| language | English |
| publishDate | 2025-02-01 |
| publisher | Elsevier |
| record_format | Article |
| series | Sensing and Bio-Sensing Research |
| spelling | doaj-art-8a717729ad0243c0a1db582a9bf9a78a2025-01-29T05:01:16ZengElsevierSensing and Bio-Sensing Research2214-18042025-02-0147100749TraxVBF: A hybrid transformer-xLSTM framework for EMG signal processing and assistive technology development in rehabilitationSeyyed Ali Zendehbad0Athena Sharifi Razavi1Marzieh Allami Sanjani2Zahra Sedaghat3Saleh Lashkari4Department of Biomedical Engineering, Mashhad Branch, Islamic Azad University, Mashhad, Iran; Corresponding author.Clinical Research Development Unit of Bou Ali Sina Hospital, School of Medicine, Mazandaran University of Medical Sciences, Sari, IranDepartment of Biomedical Engineering, Mashhad Branch, Islamic Azad University, Mashhad, IranClinical Research Development Unit of Bou Ali Sina Hospital, School of Medicine, Mazandaran University of Medical Sciences, Sari, IranHealth Technology Research Center, Imam Reza International University, Mashhad, IranThe fact that people with mobility impairments often have great difficulties in performing essential Activities of Daily Living (ADL) shows the importance of developing effective rehabilitation strategies. To address this need, we propose TraxVBF, a multimodal visual biofeedback submodel using surface Electromyography (sEMG) signals and kinematic movement data to exploit muscle synergy patterns. TraxVBF offers innovative real time visual feedback that can be used to enhance neurorehabilitation systems. Pre-processing and extracting muscle synergy patterns is performed by the Hierarchical Fast Alternating Least Squares (Fast-HALS) algorithm, and key movement points are identified with the Modified MediaPipe algorithm to capture temporal and spatial dynamics with precision using TraxVBF, which is driven by Extended Long Short-Term Memory (xLSTM) and Transformer architectures. This allows the model to predict movement trajectories accurately, enabling motor learning and functional recovery of patients through real time feedback without the expensive hardware. The model is shown to significantly improve performance metrics such as Mean Square Error (MSE), Root Mean Square Error (RMSE), and Coefficient of Determination (R2). For healthy participants, TraxVBF-type Base outperforms state of the art models (LSTM and GRU) with an MSE of 0.06 and R2 of 0.89. Practical evaluations with an average R2 of 0.880 for healthy participants and 0.327 for patients demonstrate the model generalizability. These results indicate that TraxVBF may be a useful tool to improve motor learning and rehabilitation, and longer term clinical trials and multi-sensory biofeedback are needed.http://www.sciencedirect.com/science/article/pii/S2214180425000157BiofeedbackExtended long short-term memoryMotor controlMuscle synergy patternsTransformersSurface electromyography |
| spellingShingle | Seyyed Ali Zendehbad Athena Sharifi Razavi Marzieh Allami Sanjani Zahra Sedaghat Saleh Lashkari TraxVBF: A hybrid transformer-xLSTM framework for EMG signal processing and assistive technology development in rehabilitation Sensing and Bio-Sensing Research Biofeedback Extended long short-term memory Motor control Muscle synergy patterns Transformers Surface electromyography |
| title | TraxVBF: A hybrid transformer-xLSTM framework for EMG signal processing and assistive technology development in rehabilitation |
| title_full | TraxVBF: A hybrid transformer-xLSTM framework for EMG signal processing and assistive technology development in rehabilitation |
| title_fullStr | TraxVBF: A hybrid transformer-xLSTM framework for EMG signal processing and assistive technology development in rehabilitation |
| title_full_unstemmed | TraxVBF: A hybrid transformer-xLSTM framework for EMG signal processing and assistive technology development in rehabilitation |
| title_short | TraxVBF: A hybrid transformer-xLSTM framework for EMG signal processing and assistive technology development in rehabilitation |
| title_sort | traxvbf a hybrid transformer xlstm framework for emg signal processing and assistive technology development in rehabilitation |
| topic | Biofeedback Extended long short-term memory Motor control Muscle synergy patterns Transformers Surface electromyography |
| url | http://www.sciencedirect.com/science/article/pii/S2214180425000157 |
| work_keys_str_mv | AT seyyedalizendehbad traxvbfahybridtransformerxlstmframeworkforemgsignalprocessingandassistivetechnologydevelopmentinrehabilitation AT athenasharifirazavi traxvbfahybridtransformerxlstmframeworkforemgsignalprocessingandassistivetechnologydevelopmentinrehabilitation AT marziehallamisanjani traxvbfahybridtransformerxlstmframeworkforemgsignalprocessingandassistivetechnologydevelopmentinrehabilitation AT zahrasedaghat traxvbfahybridtransformerxlstmframeworkforemgsignalprocessingandassistivetechnologydevelopmentinrehabilitation AT salehlashkari traxvbfahybridtransformerxlstmframeworkforemgsignalprocessingandassistivetechnologydevelopmentinrehabilitation |