The offline feature extraction of four-class motor imagery EEG based on ICA and Wavelet-CSP

Xiaoping Bai, Xiangzhou Wang, Shuhua Zheng*, Mingxin Yu

*Corresponding author for this work

Research output: Chapter in Book/Report/Conference proceedingConference contributionpeer-review

28 Citations (Scopus)

Abstract

The signal processing of electroencephalogram (EEG) is the key technology in a brain-computer interface (BCI) system. A widely used method is to purify the raw EEG with an 8-30Hz band-pass filter and extract features by common spatial patterns (CSP). However its results for BCI Competition IV are not very satisfactory. To improve the classification success rate, this paper proposed a novel Wavelet-CSP with ICA-filter method. For the data sets from BCI Competition IV, the features of the four-class motor imagery were trained and tested using the Support Vector Machines (SVM). The experimental results showed that the proposed method had a higher average kappa coefficient of 0.68 than 0.52 of the general method.

Original languageEnglish
Title of host publicationProceedings of the 33rd Chinese Control Conference, CCC 2014
EditorsShengyuan Xu, Qianchuan Zhao
PublisherIEEE Computer Society
Pages7189-7194
Number of pages6
ISBN (Electronic)9789881563842
DOIs
Publication statusPublished - 11 Sept 2014
EventProceedings of the 33rd Chinese Control Conference, CCC 2014 - Nanjing, China
Duration: 28 Jul 201430 Jul 2014

Publication series

NameProceedings of the 33rd Chinese Control Conference, CCC 2014
ISSN (Print)1934-1768
ISSN (Electronic)2161-2927

Conference

ConferenceProceedings of the 33rd Chinese Control Conference, CCC 2014
Country/TerritoryChina
CityNanjing
Period28/07/1430/07/14

Keywords

  • Brain-computer-interface (BCI)
  • ICA
  • SVM
  • Wavelet-CSP
  • electroencephalogram (EEG)

Fingerprint

Dive into the research topics of 'The offline feature extraction of four-class motor imagery EEG based on ICA and Wavelet-CSP'. Together they form a unique fingerprint.

Cite this