A Comparative Study of Canonical Correlation Analysis and Power Spectral Density Analysis for SSVEP Detection

Author

Wei, Qingguo ; Xiao, Meixia ; Lu, Zongwu

Author_Institution

Dept. of Electron. Eng., Nanchang Univ., Nanchang, China

Volume

2

fYear

2011

Firstpage

7

Lastpage

10

Abstract

Steady-state visual evoked potentials (SSVEPs) are widely employed for target detection in brain-computer interfaces (BCIs). Canonical correlation analysis (CCA), which extends ordinary correlation to two sets of variables, is a new method for SSVEP detection. In this paper, the performance of CCA is compared with that of traditional power spectral density analysis (PSDA) in terms of power spectral amplitude, recognition accuracy, information transfer rate and operating speed. The results show that the CCA method outperforms the PSDA in all these technical indexes.

Keywords

brain-computer interfaces; object detection; visual evoked potentials; SSVEP detection; brain-computer interfaces; canonical correlation analysis; information transfer rate; power spectral amplitude; power spectral density analysis; recognition accuracy; steady-state visual evoked potentials; target detection; Accuracy; Correlation; Electroencephalography; Harmonic analysis; Signal to noise ratio; Target recognition; Visualization; brain-computer interface; canonical correlation analysis; power spectral density analysis; steady-state visual evoked potentials;

fLanguage

English

Publisher

ieee

Conference_Titel

Intelligent Human-Machine Systems and Cybernetics (IHMSC), 2011 International Conference on

Conference_Location

Zhejiang

Print_ISBN

978-1-4577-0676-9

Type

conf

DOI

10.1109/IHMSC.2011.72

Filename

6038202