Feature Set to sEMG Classification Obtained With Fisher Score
The best way to represent EMG signals for classification is a topic that has been widely studied due to the need to improve precision when identifying the type of movement being performed. However, by increasing the number of features when forming a matrix that represents the signals, the processing...
| Main Authors: | , , , |
|---|---|
| Format: | Article |
| Language: | English |
| Published: |
IEEE
2024-01-01
|
| Series: | IEEE Access |
| Subjects: | |
| Online Access: | https://ieeexplore.ieee.org/document/10388339/ |
| _version_ | 1797338465040334848 |
|---|---|
| author | Diana C. Toledo-Perez Marcos Aviles Roberto A. Gomez-Loenzo Juvenal Rodriguez-Resendiz |
| author_facet | Diana C. Toledo-Perez Marcos Aviles Roberto A. Gomez-Loenzo Juvenal Rodriguez-Resendiz |
| author_sort | Diana C. Toledo-Perez |
| collection | DOAJ |
| description | The best way to represent EMG signals for classification is a topic that has been widely studied due to the need to improve precision when identifying the type of movement being performed. However, by increasing the number of features when forming a matrix that represents the signals, the processing time increases since it not only involves calculating the features that are extracted from the signal but also the time that the classifier takes to answer. The central purpose of this research is to develop and validate a methodology that uses the Fisher Score to select a set of features in the classification of sEMG signals. This selected set is descriptive enough to achieve high levels of accuracy in detecting EMG signal patterns across multiple subjects. The analysis shows that using a variant of MAV, SSC, WAMP, RMS, and the maximum value together with the Shannon entropy and zero crossings of the Wavelet transform has an accuracy greater than 99%. Finally, a group of features is proposed to classify EMG signals that yield an accuracy greater than 98% and do not require more than 15 ms of processing time. |
| first_indexed | 2024-03-08T09:31:38Z |
| format | Article |
| id | doaj.art-1da3dcce976d454db21766ee11fe1a48 |
| institution | Directory Open Access Journal |
| issn | 2169-3536 |
| language | English |
| last_indexed | 2024-03-08T09:31:38Z |
| publishDate | 2024-01-01 |
| publisher | IEEE |
| record_format | Article |
| series | IEEE Access |
| spelling | doaj.art-1da3dcce976d454db21766ee11fe1a482024-01-31T00:01:29ZengIEEEIEEE Access2169-35362024-01-0112139621397010.1109/ACCESS.2024.335304410388339Feature Set to sEMG Classification Obtained With Fisher ScoreDiana C. Toledo-Perez0https://orcid.org/0000-0002-2230-6751Marcos Aviles1https://orcid.org/0000-0003-2838-4854Roberto A. Gomez-Loenzo2https://orcid.org/0000-0001-7501-5272Juvenal Rodriguez-Resendiz3https://orcid.org/0000-0001-8598-5600Facultad de Ingeniería, Universidad Autónoma de Querétaro, Querétaro, MexicoFacultad de Ingeniería, Universidad Autónoma de Querétaro, Querétaro, MexicoFacultad de Ingeniería, Universidad Autónoma de Querétaro, Querétaro, MexicoFacultad de Ingeniería, Universidad Autónoma de Querétaro, Querétaro, MexicoThe best way to represent EMG signals for classification is a topic that has been widely studied due to the need to improve precision when identifying the type of movement being performed. However, by increasing the number of features when forming a matrix that represents the signals, the processing time increases since it not only involves calculating the features that are extracted from the signal but also the time that the classifier takes to answer. The central purpose of this research is to develop and validate a methodology that uses the Fisher Score to select a set of features in the classification of sEMG signals. This selected set is descriptive enough to achieve high levels of accuracy in detecting EMG signal patterns across multiple subjects. The analysis shows that using a variant of MAV, SSC, WAMP, RMS, and the maximum value together with the Shannon entropy and zero crossings of the Wavelet transform has an accuracy greater than 99%. Finally, a group of features is proposed to classify EMG signals that yield an accuracy greater than 98% and do not require more than 15 ms of processing time.https://ieeexplore.ieee.org/document/10388339/SVMFisher scorefeature selectionsEMGpattern recognition |
| spellingShingle | Diana C. Toledo-Perez Marcos Aviles Roberto A. Gomez-Loenzo Juvenal Rodriguez-Resendiz Feature Set to sEMG Classification Obtained With Fisher Score IEEE Access SVM Fisher score feature selection sEMG pattern recognition |
| title | Feature Set to sEMG Classification Obtained With Fisher Score |
| title_full | Feature Set to sEMG Classification Obtained With Fisher Score |
| title_fullStr | Feature Set to sEMG Classification Obtained With Fisher Score |
| title_full_unstemmed | Feature Set to sEMG Classification Obtained With Fisher Score |
| title_short | Feature Set to sEMG Classification Obtained With Fisher Score |
| title_sort | feature set to semg classification obtained with fisher score |
| topic | SVM Fisher score feature selection sEMG pattern recognition |
| url | https://ieeexplore.ieee.org/document/10388339/ |
| work_keys_str_mv | AT dianactoledoperez featuresettosemgclassificationobtainedwithfisherscore AT marcosaviles featuresettosemgclassificationobtainedwithfisherscore AT robertoagomezloenzo featuresettosemgclassificationobtainedwithfisherscore AT juvenalrodriguezresendiz featuresettosemgclassificationobtainedwithfisherscore |