Forearm Orientation and Muscle Force Invariant Feature Selection Method for Myoelectric Pattern Recognition
Electromyogram (EMG) signal-based prosthetic hand can restore an amputee’s missing functionalities, which requires a faithful electromyogram pattern recognition (EMG-PR) system. However, forearm orientation and muscle force variation make the EMG-PR system more complex, and the problem be...
| Main Authors: | , , , , , |
|---|---|
| Format: | Article |
| Language: | English |
| Published: |
IEEE
2022-01-01
|
| Series: | IEEE Access |
| Subjects: | |
| Online Access: | https://ieeexplore.ieee.org/document/9762929/ |
| _version_ | 1828287190521610240 |
|---|---|
| author | Md. Johirul Islam Shamim Ahmad Fahmida Haque Mamun Bin Ibne Reaz Mohammad A. S. Bhuiyan Md. Rezaul Islam |
| author_facet | Md. Johirul Islam Shamim Ahmad Fahmida Haque Mamun Bin Ibne Reaz Mohammad A. S. Bhuiyan Md. Rezaul Islam |
| author_sort | Md. Johirul Islam |
| collection | DOAJ |
| description | Electromyogram (EMG) signal-based prosthetic hand can restore an amputee’s missing functionalities, which requires a faithful electromyogram pattern recognition (EMG-PR) system. However, forearm orientation and muscle force variation make the EMG-PR system more complex, and the problem becomes more complicated when muscle force levels and forearm orientations arise simultaneously. The problems can be minimized using a more significant number of features or high-density surface EMG, but it increases design complexity and needs higher computational power. In this regard, we have proposed a feature selection method that selects both feature and channel simultaneously. The proposed feature selection method selects only 7 to 20 features among 162 features with comparable or better performance. In this study, these selected features achieve a significant improvement in the accuracy, sensitivity, specificity, precision, F1 score, and Matthew correlation coefficient (MCC) by 3.18% to 4.28%, 9.14% to 12.85%, 1.83% to 2.57%, 8.30% to 10.99%, 9.22% to 13.92%, and 0.11 to 0.15, respectively comparing with four existing feature selection methods. In this research, the proposed feature selection method achieves a forearm orientation and muscle force invariant F1 score of 91.46% for training the k-nearest neighbor (KNN) classifier with two orientations, wrist fully supinated (O1) and wrist fully pronated (O3), with a medium force level. We have also achieved an F1 score of 93.27% for training the KNN classifier with all orientations with a medium force level. So, the proposed feature selection method would be very much helpful for finding the least dimensional features and achieving improved EMG-PR performance with multiple limiting factors. |
| first_indexed | 2024-04-13T09:44:14Z |
| format | Article |
| id | doaj.art-e031a3ddd53b48e6b76b1a9593b37daa |
| institution | Directory Open Access Journal |
| issn | 2169-3536 |
| language | English |
| last_indexed | 2024-04-13T09:44:14Z |
| publishDate | 2022-01-01 |
| publisher | IEEE |
| record_format | Article |
| series | IEEE Access |
| spelling | doaj.art-e031a3ddd53b48e6b76b1a9593b37daa2022-12-22T02:51:49ZengIEEEIEEE Access2169-35362022-01-0110464424647110.1109/ACCESS.2022.31704839762929Forearm Orientation and Muscle Force Invariant Feature Selection Method for Myoelectric Pattern RecognitionMd. Johirul Islam0https://orcid.org/0000-0002-5226-0547Shamim Ahmad1Fahmida Haque2Mamun Bin Ibne Reaz3https://orcid.org/0000-0002-0459-0365Mohammad A. S. Bhuiyan4https://orcid.org/0000-0003-0772-0556Md. Rezaul Islam5Department of Electrical and Electronic Engineering, University of Rajshahi, Rajshahi, BangladeshDepartment of Computer Science and Engineering, University of Rajshahi, Rajshahi, BangladeshDepartment of Electrical, Electronic and Systems Engineering, Universiti Kebangsaan Malaysia, Bangi, MalaysiaDepartment of Electrical, Electronic and Systems Engineering, Universiti Kebangsaan Malaysia, Bangi, MalaysiaDepartment of Electrical and Electronic Engineering, Xiamen University Malaysia, Bandar Sunsuria, MalaysiaDepartment of Electrical and Electronic Engineering, University of Rajshahi, Rajshahi, BangladeshElectromyogram (EMG) signal-based prosthetic hand can restore an amputee’s missing functionalities, which requires a faithful electromyogram pattern recognition (EMG-PR) system. However, forearm orientation and muscle force variation make the EMG-PR system more complex, and the problem becomes more complicated when muscle force levels and forearm orientations arise simultaneously. The problems can be minimized using a more significant number of features or high-density surface EMG, but it increases design complexity and needs higher computational power. In this regard, we have proposed a feature selection method that selects both feature and channel simultaneously. The proposed feature selection method selects only 7 to 20 features among 162 features with comparable or better performance. In this study, these selected features achieve a significant improvement in the accuracy, sensitivity, specificity, precision, F1 score, and Matthew correlation coefficient (MCC) by 3.18% to 4.28%, 9.14% to 12.85%, 1.83% to 2.57%, 8.30% to 10.99%, 9.22% to 13.92%, and 0.11 to 0.15, respectively comparing with four existing feature selection methods. In this research, the proposed feature selection method achieves a forearm orientation and muscle force invariant F1 score of 91.46% for training the k-nearest neighbor (KNN) classifier with two orientations, wrist fully supinated (O1) and wrist fully pronated (O3), with a medium force level. We have also achieved an F1 score of 93.27% for training the KNN classifier with all orientations with a medium force level. So, the proposed feature selection method would be very much helpful for finding the least dimensional features and achieving improved EMG-PR performance with multiple limiting factors.https://ieeexplore.ieee.org/document/9762929/EMG pattern recognitionfeature selectionforearm orientationmuscle force variation |
| spellingShingle | Md. Johirul Islam Shamim Ahmad Fahmida Haque Mamun Bin Ibne Reaz Mohammad A. S. Bhuiyan Md. Rezaul Islam Forearm Orientation and Muscle Force Invariant Feature Selection Method for Myoelectric Pattern Recognition IEEE Access EMG pattern recognition feature selection forearm orientation muscle force variation |
| title | Forearm Orientation and Muscle Force Invariant Feature Selection Method for Myoelectric Pattern Recognition |
| title_full | Forearm Orientation and Muscle Force Invariant Feature Selection Method for Myoelectric Pattern Recognition |
| title_fullStr | Forearm Orientation and Muscle Force Invariant Feature Selection Method for Myoelectric Pattern Recognition |
| title_full_unstemmed | Forearm Orientation and Muscle Force Invariant Feature Selection Method for Myoelectric Pattern Recognition |
| title_short | Forearm Orientation and Muscle Force Invariant Feature Selection Method for Myoelectric Pattern Recognition |
| title_sort | forearm orientation and muscle force invariant feature selection method for myoelectric pattern recognition |
| topic | EMG pattern recognition feature selection forearm orientation muscle force variation |
| url | https://ieeexplore.ieee.org/document/9762929/ |
| work_keys_str_mv | AT mdjohirulislam forearmorientationandmuscleforceinvariantfeatureselectionmethodformyoelectricpatternrecognition AT shamimahmad forearmorientationandmuscleforceinvariantfeatureselectionmethodformyoelectricpatternrecognition AT fahmidahaque forearmorientationandmuscleforceinvariantfeatureselectionmethodformyoelectricpatternrecognition AT mamunbinibnereaz forearmorientationandmuscleforceinvariantfeatureselectionmethodformyoelectricpatternrecognition AT mohammadasbhuiyan forearmorientationandmuscleforceinvariantfeatureselectionmethodformyoelectricpatternrecognition AT mdrezaulislam forearmorientationandmuscleforceinvariantfeatureselectionmethodformyoelectricpatternrecognition |