Subject-based feature extraction by using fisher WPD-CSP in brain-computer interfaces
详细信息 查看全文
- 作者：Banghua Yang ; yangbanghua@126.com" class="auth_mail" title="E-mail the corresponding author ; Huarong Li ; Qian Wang ; Yunyuan Zhang
- 关键词：Wavelet packet decomposition (WPD) ; Common spatial patterns (CSP) ; Fisher distance ; Brain&ndash ; computer interface (BCI) ; Electroencephalogram (EEG) ; Feature extraction
- 刊名：Computer Methods and Programs in Biomedicine
- 出版年：2016
- 出版时间：June 2016
- 年：2016
- 卷：129
- 期：Complete
- 页码：21-28
- 全文大小：1935 K
文摘
- •
A subject-based feature extraction method is discussed.
- •
The feature extraction method combines wavelet packet decomposition, common spatial patterns and fisher distance.
- •
The selection of sub-bands based on fisher distance tells apart those useless sub-bands and remain best sub-bands for each subject.
- •
The proposed method can extract suitable features for specific subject and achieve a higher classification accuracy than non-subject-based method.