Feature Augmented Hybrid CNN for Stress Recognition Using Wrist-based Photoplethysmography Sensor

TL;DR

This paper introduces a hybrid CNN model that combines handcrafted features and automatic feature extraction from wrist-based PPG signals to improve stress detection accuracy, demonstrating significant performance gains on benchmark data.

Contribution

It proposes a novel hybrid CNN classifier that integrates handcrafted and CNN-extracted features for stress recognition using wrist-worn PPG sensors, outperforming existing methods.

Findings

H-CNN achieves 5-7% higher accuracy than traditional classifiers and CNN.

H-CNN improves macro F1 score by up to 10%.

Effective stress detection using wrist-based PPG signals for consumer devices.

Abstract

Stress is a physiological state that hampers mental health and has serious consequences to physical health. Moreover, the COVID-19 pandemic has increased stress levels among people across the globe. Therefore, continuous monitoring and detection of stress are necessary. The recent advances in wearable devices have allowed the monitoring of several physiological signals related to stress. Among them, wrist-worn wearable devices like smartwatches are most popular due to their convenient usage. And the photoplethysmography (PPG) sensor is the most prevalent sensor in almost all consumer-grade wrist-worn smartwatches. Therefore, this paper focuses on using a wrist-based PPG sensor that collects Blood Volume Pulse (BVP) signals to detect stress which may be applicable for consumer-grade wristwatches. Moreover, state-of-the-art works have used either classical machine learning algorithms to detect stress using hand-crafted features or have used deep learning algorithms like Convolutional Neural Network (CNN) which automatically extracts features. This paper proposes a novel hybrid CNN (H-CNN) classifier that uses both the hand-crafted features and the automatically extracted features by CNN to detect stress using the BVP signal. Evaluation on the benchmark WESAD dataset shows that, for 3-class classification (Baseline vs. Stress vs. Amusement), our proposed H-CNN outperforms traditional classifiers and normal CNN by 5% and 7% accuracy, and 10% and 7% macro F1 score, respectively. Also for 2-class classification (Stress vs. Non-stress), our proposed H-CNN outperforms traditional classifiers and normal CNN by 3% and ~5% accuracy, and ~3% and ~7% macro F1 score, respectively.