Classification of motor imagery EEG signals using SVM, k-NN and ANN

Presently, the brain mechanisms are still far from being fully understood, and a considerable amount of neuroscience research is still required to achieve this goal. Brain signals once decoded can be used to control devices and help people in locked-in state to live a better life. The present investigation deals with the processing and classification of left hand motor imagery and foot motor imagery EEG based brain signals. These signals have a very high dimensionality which possess problem for classifiers. In the present investigation, dimensionality reduction methods PCA and LDA have been implemented and state vector machine, k-nearest neighbour and artificial neural network (ANN) classifiers have been compared for their accuracy and speed of classification. It has been concluded that the combination of LDA and ANN can be treated as a strong candidate for processing and classification of Motor Imagery EEG based brain signals.