Paper Info
Title
Enhancing unsupervised canonical correlation analysis-based frequency detection of SSVEPs by incorporating background EEG.
Abstract
Steady-state visual evoked potential (SSVEP)-based brain-computer interfaces (BCIs) have potential to provide a fast communication channel between human brain and external devices. In SSVEP-based BCIs, Canonical Correlation Analysis (CCA) has been widely used to detect frequency-coded SSVEPs due to its high efficiency and robustness. However, the detectability of SSVEPs differs among frequencies due to a power-law distribution of the power spectra of spontaneous electroencephalogram (EEG) signals. This study proposed a new method based on the fact that changes of canonical correlation coefficients for SSVEPs and background EEG signals follow the same trend along frequency. The proposed method defined a normalized canonical correlation coefficient, the ratio of the canonical correlation coefficient for SSVEPs to the mean of the canonical correlation coefficients for background EEG signals, to enhance the frequency detection of SSVEPs. An SSVEP dataset from 13 subjects was used for comparing classification performance between the proposed method and the standard CCA method. Classification accuracy and simulated information transfer rates (ITR) suggest that, in an unsupervised way, the proposed method could considerably improve the frequency detection accuracy of SSVEPs with little computational effort.
Year
DOI
Venue
2014
10.1109/EMBC.2014.6944267
EMBC
Keywords
Field
DocType
ssvep dataset,itr,external devices,ssvep-based bci,medical signal detection,electroencephalography,brain-computer interfaces,frequency detection accuracy,visual evoked potentials,simulated information transfer rates,communication channel,normalized canonical correlation coefficient,power-law distribution,signal classification,spontaneous electroencephalogram signals,background eeg signals,frequency-coded ssvep detection,standard cca method,classification accuracy,steady-state visual evoked potential-based brain-computer interfaces,classification performance,canonical correlation analysis,power spectra,correlation methods,unsupervised canonical correlation analysis-based frequency detection,human brain
Normalization (statistics),Pattern recognition,Computer science,Canonical correlation,Robustness (computer science),Speech recognition,Frequency detection,Artificial intelligence,Electroencephalography
Conference
Volume
ISSN
Citations 
2014
1557-170X
2
PageRank 
References 
Authors
0.48
0
5
Name
Order
Citations
PageRank
Masaki Nakanishi113121.62
Yijun Wang230846.68
Yu-Te Wang313517.37
Yasue Mitsukura416347.48
Tzyy-Ping Jung51410202.52