Using a New Hybrid Method for Characteristics Classifying of Limb Movements in Brain-Computer Interface Applications

The interface between brain and computer has received increasing attention in the last decade of scientific progress The most common use of this type of technology is the direct control of a computer cursor by a person or animal using brain computer interfaces (BCIs) based on electrophysiological signals. brain computer interface systems can benefit the elderly in many ways, such as: teaching motor/cognitive abilities, controlling household appliances, communicating with others, and controlling the exoskeleton. Exchange can be done between software, computer hardware, peripherals, humans and a combination of them. This paper presents a limb movement classification system based on the electroencephalogram signal. The system contains five parts: preprocessing using wavelet transform, feature extraction, feature reduction and classification. The experimental results are shown that the support vector machine classifier with non-linear kernel and nearest neighbor classifier has an efficiency higher than 80%. The best indicators for support vector machine classification with nonlinear kernel and nearest neighbor are shown by the simulation results.