Classification of EMG signals with CNN features and voting ensemble classifier

M. Emimal, W. Jino Hans, T. M. Inbamalar and N. Mahiban Lindsay

Computer Methods in Biomechanics and Biomedical Engineering, 2025, vol. 28, issue 7, 1042-1056

Abstract: Electromyography (EMG) signals are primarily used to control prosthetic hands. Classifying hand gestures efficiently with EMG signals presents numerous challenges. In addition to overcoming these challenges, a successful combination of feature extraction and classification approaches will improve classification accuracy. In the current work, convolutional neural network (CNN) features are used to reduce the redundancy problems associated with time and frequency domain features to improve classification accuracy. The features from the EMG signal are extracted using a CNN and are fed to the ‘k’ nearest neighbor (KNN) classifier with a different number of neighbors (1NN,3NN,5NN,and 7NN). It results in an ensemble of classifiers that are combined using a hard voting-based classifier. Based on the benchmark Ninapro DB4 database and CapgMyo database, the proposed framework obtained 91.3% classification accuracy on CapgMyo and 89.5% on Ninapro DB4.

Date: 2025
References: Add references at CitEc
Citations:

Downloads: (external link)
http://hdl.handle.net/10.1080/10255842.2024.2310726 (text/html)
Access to full text is restricted to subscribers.

Related works:
This item may be available elsewhere in EconPapers: Search for items with the same title.

Export reference: BibTeX RIS (EndNote, ProCite, RefMan) HTML/Text

Persistent link: https://EconPapers.repec.org/RePEc:taf:gcmbxx:v:28:y:2025:i:7:p:1042-1056

Ordering information: This journal article can be ordered from
http://www.tandfonline.com/pricing/journal/gcmb20

DOI: 10.1080/10255842.2024.2310726

Access Statistics for this article

Computer Methods in Biomechanics and Biomedical Engineering is currently edited by Director of Biomaterials John Middleton

More articles in Computer Methods in Biomechanics and Biomedical Engineering from Taylor & Francis Journals
Bibliographic data for series maintained by Chris Longhurst ().