Imaginary Motion EEG Analysis and Identification Based on AR Model

DOI

10.2991/icca-16.2016.26How to use a DOI?

Keywords

EEG, motor imagery, AR model, Feature extraction and classification

Abstract

BCI converted EEG to the corresponding user commands to achieve direct communication and control of the human brain and a computer or other electronic devices. Study on motor imagery EEG feature extraction and classification is an important branch of BCI research. Imaginary movement EEG is defined by the brain to imagine limb movements without actually being generated by the movement. Firstly, the collected C3, C4 EEG channel spectrum and power spectrum were analyzed to find the frequency range that contains significant motion Imaginary feature, whereby the design of suitable band-pass filter for filtering, and uses the independent component analysis (ICA) algorithm de-noising. Doing domain ERD analysis of the filtered EEG to determine the occurrence time of a single test to happen synchronize / sync event, then interception the segment of EEG data from the time domain, and then through auto-regression model, wavelet packet analysis and AR Model power Spectrum analysis of EEG preprocessed feature extraction, and the extracted feature value is input to the two classes for classification. Finally, compare the results of the classification analysis, the classification of the most suitable type and classification of eigenvalues best in the classifier.

Copyright

© 2016, the Authors. Published by Atlantis Press.

Open Access

This is an open access article distributed under the CC BY-NC license (http://creativecommons.org/licenses/by-nc/4.0/).

Download article (PDF)

TY  - CONF
AU  - Lijuan Shi
AU  - Guixue Cui
AU  - Zhenxin Li
AU  - Bingchao Dong
AU  - Yi Yu
PY  - 2016/01
DA  - 2016/01
TI  - Imaginary Motion EEG Analysis and Identification Based on AR Model
BT  - Proceedings of the 2016 International Conference on Intelligent Control and Computer Application
PB  - Atlantis Press
SP  - 118
EP  - 121
SN  - 2352-538X
UR  - https://doi.org/10.2991/icca-16.2016.26
DO  - 10.2991/icca-16.2016.26
ID  - Shi2016/01
ER  -