Feature extraction of human sleep EEG signals using wavelet transform and Fourier transform

Abstract

Electroencephalogram (EEG) is a complex signal resulting from postsynaptic potentials of cortical pyramidal cells and an important brain state indicator with specific state dependent features. Modern brain research is intimately linked to the feasibility to record the EEG and to its quantitative analysis. EEG spectral analysis is an important method to investigate the hidden properties and hence the brain activities. Spectral analysis of sleep EEG signal provides acute insight into the features of different stages of sleep which can be utilized to differentiate between normal and pathological conditions. This paper describes the process of extracting features of human sleep EEG signals through the use of multi resolution Discrete Wavelet Transform and Fast Fourier Transform. Discrete Wavelet Transform offers representations of the signals in the time-frequency plane giving information regarding the time localization of the spectral components at different stages of sleep in human beings and Fast Fourier Transform provides the spectral information. This paper also discusses the clinical correlation associated with sleep EEG signals in brief.