Analysis of surface electromyography for hand gesure classification
Abstract
Electromyography (EMG) is the measure of electrical activity produced by skeletal muscle. It is useful in prosthetic and rehabilitation technology as well as ability to handle electronic devices and robotics. If the EMG signal from the body especially hand movement can be apprehended, better value for people all around the world can be provided. Furthermore, it can be used to control smart-phone and be integrated with wearable technology. Another interesting application of this technology is in sign language recognition which is able to assist many disabled people in their daily lives. In this paper, hand gesture signals are acquired, extracted, analysed and classified. The EMG data from hand gesture which are rock, paper and scissors managed to be extracted. We use time domain feature to classified using Principal Component Analysis and regression tree. The result was highly accurate with 72.59% and 80.85% for PCA and regression tree respectively.
Keywords
Hand Gesture, Sign language recognition, Wearable technology, Principal Component Analysis, Regression Tree
Full Text:
PDFDOI: http://doi.org/10.11591/ijeecs.v15.i3.pp1366-1373
Refbacks
- There are currently no refbacks.
This work is licensed under a Creative Commons Attribution-ShareAlike 4.0 International License.
Indonesian Journal of Electrical Engineering and Computer Science (IJEECS)
p-ISSN: 2502-4752, e-ISSN: 2502-4760
This journal is published by the Institute of Advanced Engineering and Science (IAES) in collaboration with Intelektual Pustaka Media Utama (IPMU).