Towards a Lightweight Stress Prediction Model: A Study on Dimension Reduction and Individual Models in HRV Analysis

Occupational stress has emerged as an undeniable concern. Fortunately, leveraging IoT and AI technologies allows us to gather vital sign data and assess cardiovascular health, individual stress levels, physiological resilience, and emotional states. This study highlights the potential of Heart Rate Variability (HRV) analysis in constructing stress prediction models, with a specific focus on developing an efficient model with minimal data requirements. Convolutional Neural Networks (CNN) have been employed to process raw waveform data for feature extraction. Simultaneously, R-R Interval (RRI) analysis was conducted to derive a set of statistical features. Various dimension reduction algorithms Principal Component Analysis (PCA), Independent Component Analysis (ICA), and Random Projection (RP) were tested, and PCA demonstrated its significance in reducing dataset complexity, enabling swift model training without compromising accuracy excessively. This research aims to explore the feasibility of predicting an individual's stress levels using minimal and simpler data. The objective is to pave the way for predictive models to be integrated onto lightweight platforms such as millimeter-wave chips. Our approach emphasizes non-contact monitoring of heartbeat variations, particularly beat-to-beat intervals (BBI), offering a novel method for non-invasive stress detection suitable for real-time applications on compact devices.