Search

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. [ABSTRACT FROM AUTHOR]

This paper discusses blind identification and deconvolution of two-input two-output channels corrupted by noises based on second-order statistics. First, the identifiability of channel is analyzed. By constructing an new criterion, the channel parameters can be identified precisely in the present of noises. Second, the cost function of identification is established and the corresponding algorithm is presented. Next, a feedback model is used for deconvolution, and several important problems, such as the effect of noises in the blind deconvolution of mixed sources and the stability of deconvolution model, are discussed. At last, simulation results are given to illustrate the theoretical results of this paper. [ABSTRACT FROM AUTHOR]