Image based approach for cognitive classification using eeg signals

The EEG state classifier distinguishes different states and these information are used to understand the normal and abnormal states of users and to adapt their interfaces and add new functionalities. EEG classification is performed conventionally by extracting statistical parameters. But, this classification is affected more by artifacts and hence a better approach using image based is proposed. Typically, EEG signals are captured using multiple electrodes and subsequently used to map the cognitive states. It is useful for control applications, human machine interface, virtual reality concepts, etc suited to critically ill persons.] This paper deals with the classification of state based on standalone EEG signals using Hamming distance measure and assist the critically ill person to perform tasks. The cognitive states the brain can be studied at state space level and it is possible to discriminate between different tasks (though complex).