Stress Detection from Multimodal Wearable Sensor Data

2025-08-14

AI Summary

This study addresses the lack of standardized data and benchmarks for automatic stress-state recognition from wearable multimodal physiological signals. We propose a standardized laboratory-based stress induction paradigm, synchronously acquiring multimodal time-series signals—including electrodermal activity, photoplethysmography, and triaxial acceleration—alongside participants’ psychological self-reports and fine-grained experimental metadata. The resulting Multimodal Stress Dataset (MPD) is the first publicly available, emotion-computing-oriented benchmark for wearable stress analysis, supporting binary (stress vs. non-stress) and four-class (neutral, physical, cognitive, and social-evaluative stress) classification tasks. Machine learning models achieve 89% accuracy in binary classification and 82% in four-class recognition. Key contributions include: (1) a reproducible, ecologically valid stress induction protocol; (2) the first open-source, multimodal stress benchmark dataset; and (3) rigorously evaluated, comparable baseline performance—collectively advancing standardization and reproducibility in wearable stress monitoring research.

Technology Category

• Machine Learning: Multimodal Learning
• Cognitive Modeling & Cognitive Systems: Affective Computing
• Data Mining & Knowledge Management: Mining of Visual, Multimedia & Multimodal Data

Application Category

• Web Mining and Content Analysis: Mining multimedia, multimodal, multilingual, cross-lingual Web data
• Security and Privacy: Large-scale security measurements
• User Modeling, Personalization and Recommendation: On-Device user modeling, personalization, and recommendation

Abstract

Human-Computer Interaction (HCI) is a multi-modal, interdisciplinary field focused on designing, studying, and improving the interactions between people and computer systems. This involves the design of systems that can recognize, interpret, and respond to human emotions or stress. Developing systems to monitor and react to stressful events can help prevent severe health implications caused by long-term stress exposure. Currently, the publicly available datasets and standardized protocols for data collection in this domain are limited. Therefore, we introduce a multi-modal dataset intended for wearable affective computing research, specifically the development of automated stress recognition systems. We systematically review the publicly available datasets recorded in controlled laboratory settings. Based on a proposed framework for the standardization of stress experiments and data collection, we collect physiological and motion signals from wearable devices (e.g., electrodermal activity, photoplethysmography, three-axis accelerometer). During the experimental protocol, we differentiate between the following four affective/activity states: neutral, physical, cognitive stress, and socio-evaluative stress. These different phases are meticulously labeled, allowing for detailed analysis and reconstruction of each experiment. Meta-data such as body positions, locations, and rest phases are included as further annotations. In addition, we collect psychological self-assessments after each stressor to evaluate subjects' affective states. The contributions of this paper are twofold: 1) a novel multi-modal, publicly available dataset for automated stress recognition, and 2) a benchmark for stress detection with 89% in a binary classification (baseline vs. stress) and 82% in a multi-class classification (baseline vs. stress vs. physical exercise).

Problem

• Detecting stress using multimodal wearable sensor data
• Addressing limited datasets for wearable affective computing
• Standardizing stress experiments and data collection protocols

Innovation

• Multimodal wearable sensor data collection
• Standardized stress experiment framework
• High-accuracy stress detection benchmarks