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

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