Classification of Anticipatory Signals for Grasp and Release from Surface Electromyography
Surface electromyography (sEMG) is a technique for recording natural muscle activation signals, which can serve as control inputs for exoskeletons and prosthetic devices. Previous experiments have incorporated these signals using both classical and pattern-recognition control methods in order to act...
| Main Authors: | , , |
|---|---|
| Format: | Article |
| Language: | English |
| Published: |
MDPI AG
2016-10-01
|
| Series: | Sensors |
| Subjects: | |
| Online Access: | http://www.mdpi.com/1424-8220/16/11/1782 |
| _version_ | 1811298093712277504 |
|---|---|
| author | Ho Chit Siu Julie A. Shah Leia A. Stirling |
| author_facet | Ho Chit Siu Julie A. Shah Leia A. Stirling |
| author_sort | Ho Chit Siu |
| collection | DOAJ |
| description | Surface electromyography (sEMG) is a technique for recording natural muscle activation signals, which can serve as control inputs for exoskeletons and prosthetic devices. Previous experiments have incorporated these signals using both classical and pattern-recognition control methods in order to actuate such devices. We used the results of an experiment incorporating grasp and release actions with object contact to develop an intent-recognition system based on Gaussian mixture models (GMM) and continuous-emission hidden Markov models (HMM) of sEMG data. We tested this system with data collected from 16 individuals using a forearm band with distributed sEMG sensors. The data contain trials with shifted band alignments to assess robustness to sensor placement. This study evaluated and found that pattern-recognition-based methods could classify transient anticipatory sEMG signals in the presence of shifted sensor placement and object contact. With the best-performing classifier, the effect of label lengths in the training data was also examined. A mean classification accuracy of 75.96% was achieved through a unigram HMM method with five mixture components. Classification accuracy on different sub-movements was found to be limited by the length of the shortest sub-movement, which means that shorter sub-movements within dynamic sequences require larger training sets to be classified correctly. This classification of user intent is a potential control mechanism for a dynamic grasping task involving user contact with external objects and noise. Further work is required to test its performance as part of an exoskeleton controller, which involves contact with actuated external surfaces. |
| first_indexed | 2024-04-13T06:14:35Z |
| format | Article |
| id | doaj.art-8ab8e7cf9cc54d199876117cc5c920bc |
| institution | Directory Open Access Journal |
| issn | 1424-8220 |
| language | English |
| last_indexed | 2024-04-13T06:14:35Z |
| publishDate | 2016-10-01 |
| publisher | MDPI AG |
| record_format | Article |
| series | Sensors |
| spelling | doaj.art-8ab8e7cf9cc54d199876117cc5c920bc2022-12-22T02:58:53ZengMDPI AGSensors1424-82202016-10-011611178210.3390/s16111782s16111782Classification of Anticipatory Signals for Grasp and Release from Surface ElectromyographyHo Chit Siu0Julie A. Shah1Leia A. Stirling2Department of Aeronautics and Astronautics, Massachusetts Institute of Technology, 77 Massachusetts Ave, Cambridge, MA 02139, USADepartment of Aeronautics and Astronautics, Massachusetts Institute of Technology, 77 Massachusetts Ave, Cambridge, MA 02139, USADepartment of Aeronautics and Astronautics, Massachusetts Institute of Technology, 77 Massachusetts Ave, Cambridge, MA 02139, USASurface electromyography (sEMG) is a technique for recording natural muscle activation signals, which can serve as control inputs for exoskeletons and prosthetic devices. Previous experiments have incorporated these signals using both classical and pattern-recognition control methods in order to actuate such devices. We used the results of an experiment incorporating grasp and release actions with object contact to develop an intent-recognition system based on Gaussian mixture models (GMM) and continuous-emission hidden Markov models (HMM) of sEMG data. We tested this system with data collected from 16 individuals using a forearm band with distributed sEMG sensors. The data contain trials with shifted band alignments to assess robustness to sensor placement. This study evaluated and found that pattern-recognition-based methods could classify transient anticipatory sEMG signals in the presence of shifted sensor placement and object contact. With the best-performing classifier, the effect of label lengths in the training data was also examined. A mean classification accuracy of 75.96% was achieved through a unigram HMM method with five mixture components. Classification accuracy on different sub-movements was found to be limited by the length of the shortest sub-movement, which means that shorter sub-movements within dynamic sequences require larger training sets to be classified correctly. This classification of user intent is a potential control mechanism for a dynamic grasping task involving user contact with external objects and noise. Further work is required to test its performance as part of an exoskeleton controller, which involves contact with actuated external surfaces.http://www.mdpi.com/1424-8220/16/11/1782surface electromyographyGaussian mixture modelshidden Markov modelsmachine learningpattern recognition |
| spellingShingle | Ho Chit Siu Julie A. Shah Leia A. Stirling Classification of Anticipatory Signals for Grasp and Release from Surface Electromyography Sensors surface electromyography Gaussian mixture models hidden Markov models machine learning pattern recognition |
| title | Classification of Anticipatory Signals for Grasp and Release from Surface Electromyography |
| title_full | Classification of Anticipatory Signals for Grasp and Release from Surface Electromyography |
| title_fullStr | Classification of Anticipatory Signals for Grasp and Release from Surface Electromyography |
| title_full_unstemmed | Classification of Anticipatory Signals for Grasp and Release from Surface Electromyography |
| title_short | Classification of Anticipatory Signals for Grasp and Release from Surface Electromyography |
| title_sort | classification of anticipatory signals for grasp and release from surface electromyography |
| topic | surface electromyography Gaussian mixture models hidden Markov models machine learning pattern recognition |
| url | http://www.mdpi.com/1424-8220/16/11/1782 |
| work_keys_str_mv | AT hochitsiu classificationofanticipatorysignalsforgraspandreleasefromsurfaceelectromyography AT julieashah classificationofanticipatorysignalsforgraspandreleasefromsurfaceelectromyography AT leiaastirling classificationofanticipatorysignalsforgraspandreleasefromsurfaceelectromyography |