Wearable Sensor Data Fusion for Human Stress Estimation

Abstract: With the purpose of classifying and modelling stress, different sensors, signal features, machine learning methods, and stress experiments have been compared. Two databases have been studied: the MIT driver stress database and a new experimental database, where three stress tasks have been performed for 9 subjects: the Trier Social Stress Test, the Socially Evaluated Cold Pressor Test and the d2 test, of which the latter is not classically used for generating stress. Support vector machine, naive Bayes, k-nearest neighbor and probabilistic neural network classification techniques were compared, with support vector machines achieving the highest performance in general (99.5 ±0.6 %$on the driver database and 91.4 ± 2.4 % on the experimental database). For both databases, relevant features include the mean of the heart rate and the mean of the galvanic skin response, together with the mean of the absolute derivative of the galvanic skin response signal. A new feature is also introduced with great performance in stress classification for the driver database. Continuous models for estimating stress levels have also been developed, based upon the perceived stress levels given by the subjects during the experiments, where support vector regression is more accurate than linear and variational Bayesian regression.