Electroencephalogram-based Stress Detection using Extreme Learning Machine

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