Abstract
EEG analysis has played a key role in the modeling of the brain's cortical dynamics, but relatively little effort has been devoted to developing EEG as a limited means of communication. If several mental states can be reliably distinguished by recognizing patterns in EEG, then a paralyzed person could communicate to a device such as a wheelchair by composing sequences of these mental states. EEG pattern recognition is a difficult problem and hinges on the success of finding representations of the EEG signals in which the patterns can be distinguished. In this article, we report on a study comparing three EEG representations, the unprocessed signals, a reduced-dimensional representation using the Karhunen – Loève transform, and a frequency-based representation. Classification is performed with a two-layer neural network implemented on a CNAPS server (128 processor, SIMD architecture) by Adaptive Solutions, Inc. Execution time comparisons show over a hundred-fold speed up over a Sun Sparc 10. The best classification accuracy on untrained samples is 73% using the frequency-based representation.
Highlights
Disabled people who have no control over their motor responses have no means of communicating to the outside world
Is there a wav for such people to use their mental capabilities t
Keirn and Aunon found that quarter-second segments of the 10-second data resulted in classification accuracy approximately the same as that obtained from 2-second segments
Summary
Disabled people who have no control over their motor responses have no means of communicating to the outside world. The work reported here has a different goal, to extract information from EEG signals with which we can discriminate mental states. The segment was chosen to be devoid of eye blinks and near the middle of the session, assuming during that period the subject was most likely concentrating on the requested mental task Another limitation is the use of a quadratic Bayesian classifier. Lin et al used Kohonen·,- algorithm [12] to train a matrix of units to identify clusters of :-;imilar patterns and associate each cluster with a particular mental task Thev trained their classifier on data for all tasks performed by one subject in one recording session and tested the resulting classifier on data from other sessions and other subjects.
Sign-in/Register to view highlights & summary Sign-in/Register to access full text options 
Talk to us
Join us for a 30 min session where you can share your feedback and ask us any queries you have
Schedule a call
