Stress Classification and Personalization: Getting the most out of the least
This addresses the problem of data-intensive and feature-dependent stress detection methods for individuals, offering a more practical approach, though it is incremental as it builds on existing CNN techniques.
The paper tackles stress detection by proposing a CNN-based framework that uses only one sensor modality without feature computation, achieving a classification accuracy of 92.85% and an f1 score of 0.89, and highlights the importance of personalizing models through leave-one-subject-out analysis.
Stress detection and monitoring is an active area of research with important implications for the personal, professional, and social health of an individual. Current approaches for affective state classification use traditional machine learning algorithms with features computed from multiple sensor modalities. These methods are data-intensive and rely on hand-crafted features which impede the practical applicability of these sensor systems in daily lives. To overcome these shortcomings, we propose a novel Convolutional Neural Network (CNN) based stress detection and classification framework without any feature computation using data from only one sensor modality. Our method is competitive and outperforms current state-of-the-art techniques and achieves a classification accuracy of $92.85\%$ and an $f1$ score of $0.89$. Through our leave-one-subject-out analysis, we also show the importance of personalizing stress models.