EEG Signal Classification for Brain Computer Interface Applications. Jorge Bazta.pdf

EEG Signal Classification for Brain
Computer Interface Applications





ECOLE POLYTECHNIQUE FEDERALE DE LAUSANNE






















Jorge Baztarrica Ochoa

Responsible Assistant : Gary Garcia Molina.

Professor : Touradj Ebrahimi


March 28th, 2002
1
Abstract


Recent advances puter hardware and signal processing have made possible
the use of EEG signals or “brain waves” munication between humans and
computers. Locked-in patients have now a way municate with the outside world,
but even with the last modern techniques, such systems still munication rates
on the order of 2-3 tasks/minute. In addition, existing systems are not likely to be
designed with flexibility in mind, leading to slow systems that are difficult to improve.

This diploma project explores the effectiveness of Time – Frequency Analysis as
a technique of classifying different mental tasks through the use of the
electroencephalogram (EEG). EEG signals from several subjects through 6 channels
(electrodes) have been studied during the performance of five mental tasks (a baseline
resting task, mental multiplication, geometric figure rotation, mental position,
and counting). Improved off-line classification of two of them (“geometric figure
rotation” and “mental position”), for which poor results had been obtained with
autoregressive models before, were the principal objective of this project.

Different methods based on Time Frequency Representations have been
considered for the classification between the two tasks mentioned above. A non-iterative
method based on the Ambiguity Function was finally selected. The results indicate that
this method is able to extract in half-second, distinguishing features from the data, that
could be classified as belonging to one of the two tasks with an average percentage
accuracy which tends to zero. The same results were found when th