Stress State Classification Based on Deep Neural Network and Electrodermal Activity Modeling

• Published in: Sensors (Basel, Switzerland) Switzerland), 2023-02, Vol.23 (5), p.2504
• Main Authors: Vasile, Floriana, Vizziello, Anna, Brondino, Natascia, Savazzi, Pietro
• Format: Article
• Language: English
• Subjects: Accuracy; Aggression; Alexithymia; Anxiety; Arousal; Artificial intelligence; Autism; Autistic children; Care and treatment; Classification; Data augmentation; Data models; Datasets; Decomposition; deep learning; EDA; emotion recognition; Emotional factors; Emotions - physiology; Exocrine glands; Galvanic Skin Response; Humans; Machine Learning; Nervous system; Neural networks; Neural Networks, Computer; Patient monitoring; Physiology; Remote monitoring; Sensors; skin conductance; Stress; Support vector machines; Technology application; Variance analysis; wearable
• ISSN: 1424-8220; 1424-8220
• DOI: 10.3390/s23052504

Electrodermal Activity (EDA) has become of great interest in the last several decades, due to the advent of new devices that allow for recording a lot of psychophysiological data for remotely monitoring patients' health. In this work, a novel method of analyzing EDA signals is proposed with the ultimate goal of helping caregivers assess the emotional states of autistic people, such as stress and frustration, which could cause aggression onset. Since many autistic people are non-verbal or suffer from alexithymia, the development of a method able to detect and measure these arousal states could be useful to aid with predicting imminent aggression. Therefore, the main objective of this paper is to classify their emotional states to prevent these crises with proper actions. Several studies were conducted to classify EDA signals, usually employing learning methods, where data augmentation was often performed to countervail the lack of extensive datasets. Differently, in this work, we use a model to generate synthetic data that are employed to train a deep neural network for EDA signal classification. This method is automatic and does not require a separate step for features extraction, as in EDA classification solutions based on machine learning. The network is first trained with synthetic data and then tested on another set of synthetic data, as well as on experimental sequences. In the first case, an accuracy of 96% is reached, which becomes 84% in the second case, thus demonstrating the feasibility of the proposed approach and its high performance.