Classification of Perceived Human Stress using Physiological Signals
This work addresses stress classification for healthcare or monitoring applications, but it is incremental as it builds on existing methods without stress inducers.
The paper tackles the problem of classifying perceived human stress using non-invasive physiological signals like EEG, GSR, and PPG, achieving a best classification accuracy of 75% with an MLP classifier.
In this paper, we present an experimental study for the classification of perceived human stress using non-invasive physiological signals. These include electroencephalography (EEG), galvanic skin response (GSR), and photoplethysmography (PPG). We conducted experiments consisting of steps including data acquisition, feature extraction, and perceived human stress classification. The physiological data of $28$ participants are acquired in an open eye condition for a duration of three minutes. Four different features are extracted in time domain from EEG, GSR and PPG signals and classification is performed using multiple classifiers including support vector machine, the Naive Bayes, and multi-layer perceptron (MLP). The best classification accuracy of 75% is achieved by using MLP classifier. Our experimental results have shown that our proposed scheme outperforms existing perceived stress classification methods, where no stress inducers are used.