An Offline Auditory P300 Brain-Computer Interface Using Principal and Independent Component Analysis Techniques for Functional Electrical Stimulation Application

作者：Bentley Alexander S J^*; Andrew Colin M; John Lester R

来源：30th Annual International Conference of the IEEE-Engineering-in-Medicine-and-Biology-Society, 2008-08-20 to 2008-08-24.

DOI：10.1109/IEMBS.2008.4650252

A brain-computer interface (BCI) provides technology that allows communication and control for people who are unable to interact with their environment. A P300 BCI exploits the fact that external or internal stimuli may provide a recognition response in the brain's electrical activity which may be recorded by an electroencephalogram (EEG) to act as a control signal. Additionally an auditory BCI does not require the user to avert their visual attention away from the task at hand and is thus more practical in a real environment than other visual stimulus BCIs.
The increased amplitude of a target P300 determines the extent to which it may be separately distinguished and thus its efficiency as a signal controller in a P300 BCI. The computational effectiveness of the paradigm may be enhanced by a combination of principal component analysis (PCA) and independent component analysis (ICA) and the process whereby the target stimulus is presented to the subject.
The aim of this research is to evaluate an auditory P300 BCI using PCA and ICA techniques at ultimately operating a functional electrical stimulation (FES) device in people with neurological disorders. Accuracies of between 82 and 88% were obtained using a traditional auditory paradigm, whereas accuracies of up to 78% were obtained using a newly proposed two stimulus and one target paradigm.

• 出版日期2008