ICA based semi-supervised learning algorithm for BCI systems

Authors:
Jianzhao Qin;Yuanqing Li;Qijin Liu
Affiliations:
Institute of Automation Science and Engineering, South China University of Technology, Guangzhou, China;Institute of Automation Science and Engineering, South China University of Technology, Guangzhou, China;Institute of Automation Science and Engineering, South China University of Technology, Guangzhou, China
Venue:
ICA'06 Proceedings of the 6th international conference on Independent Component Analysis and Blind Signal Separation
Year:
2006

Citing 6
Cited 0

Independent component analysis, a new concept?

Signal Processing - Special issue on higher order statistics
Natural gradient learning for over- and under-complete bases in ICA

Neural Computation
Independent component analysis: algorithms and applications

Neural Networks
Adaptive Blind Signal and Image Processing: Learning Algorithms and Applications

Adaptive Blind Signal and Image Processing: Learning Algorithms and Applications
Sequential blind extraction of instantaneously mixed sources

IEEE Transactions on Signal Processing
Blind extraction of singularly mixed source signals

IEEE Transactions on Neural Networks

Quantified Score

Hi-index	0.00

Visualization

Abstract

As an emerging technique, brain-computer interfaces (BCIs) bring us a new communication interface which can translate brain activities into control signals of devices like computers, robots etc. In this study, we introduce an independent component analysis (ICA) based semi-supervised learning algorithm for BCI systems. In this algorithm, we separate the raw electroencephalographic (EEG) signals into several independent components using ICA; then choose a best independent component for feature extraction and classification. To demonstrate the validity of our algorithm, we apply it to an data set from an EEG-based cursor control experiment implemented in Wadsworth Center. The data analysis results show that both ICA preprocessing and semi-supervised learning can improve prediction accuracy significantly.