Bayesian Method for Continuous Cursor Control in EEG-Based Brain-Computer Interface

To develop effective learning algorithms for continuous prediction of cursor movement using EEG signals is a challenging research issue in brain-computer interface (BCI). To train a classifier for continuous prediction, trials in training dataset are first divided into segments. The difficulty is that the actual intention (label) at each time interval (segment) is unknown. In this paper, we propose a novel statistical approach under Bayesian learning framework to learn the parameters of a classifier. To make use of all the training dataset, we iteratively estimate probability of the unknown label, and use this probability to assist the training process. Experimental results have shown that the performance of the proposed method is equal to or better than the best results so far