Frequency Recognition Based on Canonical Correlation Analysis for SSVEP-Based BCIs

Author

Zhonglin Lin ; Changshui Zhang ; Wei Wu ; Xiaorong Gao

Author_Institution

Dept. of Autom., Tsinghua Univ., Beijing

Volume

53

Issue

12

fYear

2006

Firstpage

2610

Lastpage

2614

Abstract

Canonical correlation analysis (CCA) is applied to analyze the frequency components of steady-state visual evoked potentials (SSVEP) in electroencephalogram (EEG). The essence of this method is to extract a narrowband frequency component of SSVEP in EEG. A recognition approach is proposed based on the extracted frequency features for an SSVEP-based brain computer interface (BCI). Recognition Results of the approach were higher than those using a widely used fast Fourier transform (FFT)-based spectrum estimation method

Keywords

correlation methods; electroencephalography; feature extraction; handicapped aids; medical signal processing; visual evoked potentials; EEG; SSVEP-based BCI; brain computer interface; canonical correlation analysis; electroencephalogram; frequency feature extraction; frequency recognition; narrowband frequency component extraction; steady-state visual evoked potentials; Automation; Brain computer interfaces; Discrete Fourier transforms; Electroencephalography; Fast Fourier transforms; Frequency; Information analysis; Signal analysis; Spectral analysis; Steady-state; Brain computer interface; canonical correlation analysis; electroencephalogram; steady-state visual evoked potentials; Algorithms; Electroencephalography; Evoked Potentials, Visual; Fourier Analysis; Imagination; Pattern Recognition, Automated; Photic Stimulation; Reproducibility of Results; Sensitivity and Specificity; Statistics as Topic; User-Computer Interface; Visual Cortex; Visual Perception;

fLanguage

English

Journal_Title

Biomedical Engineering, IEEE Transactions on

Publisher

ieee

ISSN

0018-9294

Type

jour

DOI

10.1109/TBME.2006.886577

Filename

4015614