Variant Combination of Multiple Classifiers Methods for Classifying the EEG Signals in Brain-Computer Interface

Controlling the environment with EEG signals is known as brain computer interface is the new subject researchers are interested in. The aim in such systems is to control the machine without using muscle, and we should control the machine using signals recorded from the surface of the cortex. In this project our focus is on pattern recognition phase in which we use multiple classifier fusion to improve the classification accuracy. We have applied various feature extraction methods and combined their results. Two methods, greedy algorithms and genetic algorithms, are used for selecting the pair feature extractor-classifier (we called expert) between the existed pair. Experiments show that with using some combination method such as majority vote, product, mean, median we have obtained better result than best existing result and Fuzzy integral method and decision template have shown the similar result with the best result in BCI competition 2003 [15].