Identification and Classification of Electroencephalogram Signals Based on Independent Component Analysis
Lists
Only you see this
Abstract
This paper aims to develop a desirable EEG-based classification algorithm. For this purpose, the discrete wavelet transform was applied to denoise the EEG signals. Then, the brain’s left and right hand movement features were extracted from the denoised signals by the independent component analysis (ICA). Finally, the support vector machine (SVM) classifier was adopted to recognize and classify the movement of the left and right hand actions. The experimental results show that our method achieves the recognition accuracy of 89.5% and 90.6% respectively. The research findings provide a valuable reference for the future research into the BCI system.
BibTeX
@inproceedings{zhang2018identification,
author = {Chao Zhang and Jing Xu and Pan Su and Yudan Yang},
title = {{Identification and Classification of Electroencephalogram Signals Based on Independent Component Analysis}},
booktitle = {NeuroQuantology},
year = {2018},
doi = {10.14704/nq.2018.16.5.1392},
}Loading related content...