Stress detection for visually impaired people using EEG signals based on extracted features from time-frequency domain

Abstract

Stress refers to body's physical, emotional and psychological reaction to any environmental change needing adjustment with major impact on human psychology. Stress is specially di cult to manage for visually impaired people (VIP) as they can become easily stressed in unknown situations. Electroencephalogram (EEG) signals can be used to detect stress as it basically represents the ongoing electrical signal changes in human brain. Literature shows that the stress detection techniques are mostly based on either time or frequency domain analysis. However, using either time or frequency domain analysis may not be su cient to provide appropriate outcome for stress detection. Hence, in this paper a method is proposed using empirical mode decomposition (EMD) and short-term Fourier transform (STFT) are used to extract features considering spatio-temporal information from EEG signals. In the EMD, the signal is rst decomposed into intrinsic mode functions (IMFs) representing a nite number of signals while maintaining the time domain and STFT is used to convert time domain to time-frequency domain. Support vector machine (SVM) is applied to classify the stress of VIP in unfamiliar indoor environments. The performance of the proposed method is compared with a state-of-the-art technique for stress detection. The experimental results demonstrate the superiority of the proposed technique over the existing technique.