TEANet: A Transpose-Enhanced Autoencoder Network for Stress Monitoring on Resource-Constrained Wearable Device

Mental stress poses a significant public health concern due to its detrimental effects on physical and mental well-being, necessitating the development of continuous stress monitoring tools for wearable devices. Blood volume pulse (BVP) signals, readily available in many smartwatches, offer a convenient and cost-effective solution for stress monitoring. This study presents a deep learning model, a Transpose-Enhanced Autoencoder Network (TEANet), for stress detection using BVP signals on resource-constrained devices. The proposed TEANet model was trained and validated utilizing a self-developed RUET SPML dataset, and the publicly available wearable stress and affect detection (WESAD) dataset. It achieves accuracies of 92.94% and 96.94%, F1 scores of 95.16% and 95.95%, and Cohen’s kappa values of 0.8181 and 0.9350 for RUET SPML, and WESAD datasets, respectively. The proposed model outperforms most of the existing models in the literature. Additionally, its performance is consistently superior when compared to state-of-the-art convolutional and transformer-based architectures. Additionally, integrated gradient attribution based explainability is explored to further explain the model’s transparency in decision-making across different frequency bands. The proposed TEANet effectively detects mental stress through BVP signals with high accuracy, making it a promising tool for continuous stress monitoring. Furthermore, deploying the proposed model on the Raspberry Pi 3B+ enhances its potential for reliable real-time stress monitoring using resource-constrained devices.