A Comparison Study of Canonical Correlation Analysis Based Methods for Detecting Steady-State Visual Evoked Potentials

• Published in: PloS one Vol. 10; no. 10; p. e0140703
• Main Authors: Nakanishi, Masaki, Wang, Yijun, Wang, Yu-Te, Jung, Tzyy-Ping
• Format: Journal Article
• Language: English
• Published: United States Public Library of Science 19.10.2015; Public Library of Science (PLoS)
• Subjects: Adult; Algorithms; Analysis; Brain; Brain-Computer Interfaces; Calibration; Canonical correlation (Statistics); Communication; Computer simulation; Correlation; Correlation analysis; Data processing; EEG; Electroencephalography; Engineering; Evoked potentials; Evoked Potentials, Visual; Female; Fourier transforms; Human-computer interface; Humans; Identification; Information transfer; Interfaces; Life assessment; Male; Medicine; Methods; Neurosciences; Performance evaluation; Reference signals; Signal processing; Statistics as Topic - methods; Steady state; Steady state theory; Studies; User training; Visual evoked potentials; La Jolla California; United States > US; California
• ISSN: 1932-6203; 1932-6203
• DOI: 10.1371/journal.pone.0140703

Canonical correlation analysis (CCA) has been widely used in the detection of the steady-state visual evoked potentials (SSVEPs) in brain-computer interfaces (BCIs). The standard CCA method, which uses sinusoidal signals as reference signals, was first proposed for SSVEP detection without calibration. However, the detection performance can be deteriorated by the interference from the spontaneous EEG activities. Recently, various extended methods have been developed to incorporate individual EEG calibration data in CCA to improve the detection performance. Although advantages of the extended CCA methods have been demonstrated in separate studies, a comprehensive comparison between these methods is still missing. This study performed a comparison of the existing CCA-based SSVEP detection methods using a 12-class SSVEP dataset recorded from 10 subjects in a simulated online BCI experiment. Classification accuracy and information transfer rate (ITR) were used for performance evaluation. The results suggest that individual calibration data can significantly improve the detection performance. Furthermore, the results showed that the combination method based on the standard CCA and the individual template based CCA (IT-CCA) achieved the highest performance.