Research on feature extraction algorithms in BCI

Author

Sun-Yuge ; Ye-Ning ; Zhao, Lihong ; Xu, Xinhe

Author_Institution

Coll. of Inf. Sci. & Eng., Northeastern Univ., Shenyang, China

fYear

2009

fDate

17-19 June 2009

Firstpage

5874

Lastpage

5878

Abstract

In this paper, wavelet packet algorithm, wavelet entropy algorithm and AR model algorithm were investigated for feature extraction. EEG data of six subjects were analyzed while they performed five different mental tasks. Based on the recognition rate under different mental EEG combination and different subject, it proved that wavelet entropy algorithm had better classification accuracy compared with the other two algorithms. The highest recognition rate is up to 98.48%. The research is valuable and significant in the realization of control and communication based on the mental tasks in BCI.

Keywords

brain-computer interfaces; electroencephalography; entropy; feature extraction; image recognition; medical image processing; wavelet transforms; AR model algorithm; BCI; EEG data; brain-computer interface; classification accuracy; feature extraction algorithm; recognition rate; wavelet entropy algorithm; wavelet packet algorithm; Brain computer interfaces; Brain modeling; Communication system control; Educational institutions; Electroencephalography; Entropy; Eyes; Feature extraction; Scalp; Wavelet packets; AR model; BCI; Mental EEG; Wavelet Entropy; Wavelet Packet;

fLanguage

English

Publisher

ieee

Conference_Titel

Control and Decision Conference, 2009. CCDC '09. Chinese

Conference_Location

Guilin

Print_ISBN

978-1-4244-2722-2

Electronic_ISBN

978-1-4244-2723-9

Type

conf

DOI

10.1109/CCDC.2009.5195251

Filename

5195251