Electroencephalogram-based Stress Detection using Extreme Learning Machine

including sudden death. Various techniques have been used to evaluate stress in terms of questionnaire or by quantifying the changes of physiological signals. Electroencephalogram signals are highly useful in measuring human stress. Therefore, to solve and detect stress problem, this work had extracted electroencephalogram features of theta, alpha, and beta bands in the frequency domain by wavelet packet transform because these bands are concerned with stress. In this research four features have been supplied to extreme learning machine which gave accuracy of 98.56% of detecting stress from normal state based on db4 with an average sensitivity of 92.52% and specificity of 95.88%. This research studied the stress on 15 students due to mathematical exercises in a noisy environment with different stimulus.