Analysis of Electrode Shift Effects on Wavelet Features Embedded in a Myoelectric Pattern Recognition System

dc.contributor.authorFontana, Juan M.
dc.contributor.authorChiu, Alan W. L.
dc.contributor.otherUniversity of Alabama Tuscaloosa
dc.contributor.otherLouisiana Technical University
dc.contributor.otherRose Hulman Institute Technology
dc.date.accessioned2023-09-28T21:10:23Z
dc.date.available2023-09-28T21:10:23Z
dc.date.issued2014
dc.description.abstractMyoelectric pattern recognition systems can translate muscle contractions into prosthesis commands; however, the lack of long-term robustness of such systems has resulted in low acceptability. Specifically, socket misalignment may cause disturbances related to electrodes shifting from their original recording location, which affects the myoelectric signals (MES) and produce degradation of the classification performance. In this work, the impact of such disturbances on wavelet features extracted from MES was evaluated in terms of classification accuracy. Additionally, two principal component analysis frameworks were studied to reduce the wavelet feature set. MES from seven able-body subjects and one subject with congenital transradial limb loss were studied. The electrode shifts were artificially introduced by recording signals during six sessions for each subject. A small drop in classification accuracy from 93.8% (no disturbances) to 88.3% (with disturbances) indicated that wavelet features were able to adapt to the variability introduced by electrode shift disturbances. The classification performance of the reduced feature set was significantly lower than the performance of the full wavelet feature set. The results observed in this study suggest that the effect of electrode shift disturbances on the MES can potentially be mitigated by using wavelet features embedded in a pattern recognition system.en_US
dc.format.mediumelectronic
dc.format.mimetypeapplication/pdf
dc.identifier.citationFontana, J. M., & Chiu, A. W. L. (2014). Analysis of Electrode Shift Effects on Wavelet Features Embedded in a Myoelectric Pattern Recognition System. In Assistive Technology (Vol. 26, Issue 2, pp. 71–80). Informa UK Limited. https://doi.org/10.1080/10400435.2013.827138
dc.identifier.doi10.1080/10400435.2013.827138
dc.identifier.orcidhttps://orcid.org/0000-0002-8934-1359
dc.identifier.urihttps://ir.ua.edu/handle/123456789/12043
dc.languageEnglish
dc.language.isoen_US
dc.publisherTaylor & Francis
dc.subjectelectrode shifts
dc.subjectfeature extraction
dc.subjectmyoelectric control
dc.subjectprincipal component analysis
dc.subjectsupport vector machines
dc.subjectwavelet decomposition
dc.subjectSURFACE EMG
dc.subjectCLASSIFICATION
dc.subjectSTRATEGY
dc.subjectSCHEME
dc.subjectRehabilitation
dc.titleAnalysis of Electrode Shift Effects on Wavelet Features Embedded in a Myoelectric Pattern Recognition Systemen_US
dc.typeArticle
dc.typetext
Files
Original bundle
Now showing 1 - 1 of 1
Loading...
Thumbnail Image
Name:
10.108010400435.2013.827138.pdf
Size:
1.89 MB
Format:
Adobe Portable Document Format