Stress Detection from Different Environments for VIP Using EEG Signals and Machine Learning Algorithms

This paper proposes a method to detect stress for Visually Impaired People (VIP) when navigating indoor unfamiliar environments considering EEG signals. According to WHO, visual impairment is found in 285 million people around the world and 80% of visual impairment can be prevented or cured if proper treatment is served. However, VIP around the world have a concerning rate of living with stressful environments every day. Thus, this motivated researchers to seek a stress detection method which may be used further for supporting VIP and higher research purposes. This method refers to work with EEG Bands and detect stress by extracting different features from five EEG bands. After that, reliable machine learning algorithms are used for detection of stress based on multi-class classification. Experimental results show that Random Forest (RF) classifier achieved the best classification accuracy (i.e., 99%) for different environments where Support Vector Machine (SVM), K-Nearest Neighbors (KNN) and Linear Discriminant Analysis (LDA) secure more than 89% classification accuracy. Moreover, precision, recall and F1 score are considered to evaluate the performance of the proposed method.