Evaluation of Hand Action Classification Performance Using Machine Learning Based on Signals from Two sEMG Electrodes.

Publisher: MDPI Country of Publication: Switzerland NLM ID: 101204366 Publication Model: Electronic Cited Medium: Internet ISSN: 1424-8220 (Electronic) Linking ISSN: 14248220 NLM ISO Abbreviation: Sensors (Basel) Subsets: MEDLINE

Original Publication: Basel, Switzerland : MDPI, c2000-

Electromyography*/methods ; Hand*/physiology ; Machine Learning* ; Electrodes* ; Signal Processing, Computer-Assisted* ; Support Vector Machine* ; Algorithms*; Humans ; Male ; Adult ; Female ; Discriminant Analysis ; Young Adult

Classification-based myoelectric control has attracted significant interest in recent years, leading to prosthetic hands with advanced functionality, such as multi-grip hands. Thus far, high classification accuracies have been achieved by increasing the number of surface electromyography (sEMG) electrodes or adding other sensing mechanisms. While many prescribed myoelectric hands still adopt two-electrode sEMG systems, detailed studies on signal processing and classification performance are still lacking. In this study, nine able-bodied participants were recruited to perform six typical hand actions, from which sEMG signals from two electrodes were acquired using a Delsys Trigno Research+ acquisition system. Signal processing and machine learning algorithms, specifically, linear discriminant analysis (LDA), k-nearest neighbors (KNN), and support vector machines (SVM), were used to study classification accuracies. Overall classification accuracy of 93 ± 2%, action-specific accuracy of 97 ± 2%, and F1-score of 87 ± 7% were achieved, which are comparable with those reported from multi-electrode systems. The highest accuracies were achieved using SVM algorithm compared to LDA and KNN algorithms. A logarithmic relationship between classification accuracy and number of features was revealed, which plateaued at five features. These comprehensive findings may potentially contribute to signal processing and machine learning strategies for commonly prescribed myoelectric hand systems with two sEMG electrodes to further improve functionality.

J Orthop Sports Phys Ther. 1996 Dec;24(6):342-53. (PMID: 8938600)
IEEE Trans Neural Syst Rehabil Eng. 2018 Jan;26(1):244-251. (PMID: 29324410)
Disabil Rehabil. 2022 Jul;44(14):3708-3713. (PMID: 33377803)
Arch Phys Med Rehabil. 2020 Aug;101(8):1396-1406. (PMID: 32437692)
Front Neurorobot. 2016 Aug 22;10:7. (PMID: 27597823)
PLoS One. 2019 Aug 29;14(8):e0220899. (PMID: 31465469)
Disabil Rehabil Assist Technol. 2021 Nov;16(8):821-830. (PMID: 32189537)
IEEE Trans Neural Syst Rehabil Eng. 2010 Apr;18(2):185-92. (PMID: 20071269)
Sensors (Basel). 2016 Aug 17;16(8):. (PMID: 27548165)
Phys Med Rehabil Clin N Am. 2014 Feb;25(1):133-51. (PMID: 24287244)
Sci Rep. 2021 May 28;11(1):11275. (PMID: 34050220)
Malawi Med J. 2012 Sep;24(3):69-71. (PMID: 23638278)
J Electromyogr Kinesiol. 2000 Oct;10(5):361-74. (PMID: 11018445)
IEEE Trans Neural Syst Rehabil Eng. 2020 Feb;28(2):508-518. (PMID: 31841413)
Front Neurosci. 2021 Apr 26;15:621885. (PMID: 33981195)
IEEE Trans Neural Syst Rehabil Eng. 2022;30:893-904. (PMID: 35349446)
IEEE Trans Neural Syst Rehabil Eng. 2020 Jun;28(6):1428-1435. (PMID: 32286995)
Sensors (Basel). 2022 Jan 15;22(2):. (PMID: 35062627)
J Rehabil Res Dev. 2011;48(6):629-41. (PMID: 21938651)
J Xray Sci Technol. 2017;25(2):287-300. (PMID: 28269818)
Sci Rep. 2021 Feb 8;11(1):3300. (PMID: 33558547)
Sci Rep. 2022 Apr 8;12(1):5979. (PMID: 35395867)
Front Neurosci. 2021 Oct 12;15:733359. (PMID: 34712114)
J Rehabil Res Dev. 2011;48(6):xxi-xxxviii. (PMID: 21938647)
Annu Int Conf IEEE Eng Med Biol Soc. 2010;2010:6357-60. (PMID: 21096692)

(EPSRC) Grant EP/S02249X/1 ESPRC

Keywords: classification; hand actions; machine learning; myoelectric prosthetics; sEMG; upper limb

Date Created: 20240427 Date Completed: 20240427 Latest Revision: 20240429

20240429

PMC11054923

10.3390/s24082383

38676000