EEG signal based brain activity monitoring using adaptive wavelet transform and activity learning neural vector (ALNV) classification technique

The brain produces weak electrical signals that can be measured from the skull. There are different kind of techniques are accessible for brain monitoring system they are near-infrared spectroscopy, Functional MRI, Positron emission tomography, Magnetic resonance imaging, and Electroencephalography (EEG). The additional benefits of low system cost, efficient operation with low noninvasiveness the Electroenphalography (EEG) is mostly used in brain activity based signal recognition system. The EEG signal is also helps to evaluate the accurate signal from the organ. The proposed aims to recognize the brain activity from electroencephalography (EEG) signal using Adaptive Wavelet Transform and Activity Learning Neural Vector (ALNV) Classification techniques. The recognize the brain activity condition of the subjects under test with it feature are extracted using adaptive wavelet transform and its classified using ANLV classification technique. The performance of the proposed techniques were evaluated using simulated EEG signal under variation of different parameters such as the number of nominated regions, the signal to noise ratio, and the number of electrodes using MATLAB simulink environment. Under the test of different brain activity EEG signals in Matlab simulation are proposed adaptive wavelet transform and Activity Learning Neural Vector (ALNV) classification proves that the accuracy of those techniques is more than 95%.