EEG different frequency sound response identification using neural network and fuzzy techniques

Electroencephalographic (EEG) technology has enabled effective measurement of human brain activity, as functional and physiological changes within the brain may be registered by EEG signals. In this paper, electrical activity of human brain due to sound waves of different frequency, i.e. 40 Hz, 500 Hz, 5000 Hz and 15000 Hz, is studied based on EEG signals. Several signal processing techniques, i.e. Principle Component algorithm, Discrete Wavelet Transform and Fast Fourier Transform, are applied onto the raw EEG signal to extract useful information and specific characteristics from the EEG signals. This research has shown that the characteristics of EEG signals differ with respect to different frequency of sound waves, and hence the EEG signal can be identified with suitable characterization algorithm using artificial intelligent techniques, such as Artificial neural network, fuzzy logic and adaptive neuro-fuzzy system.