基于 WESAD 数据集的压力检测跨模态研究：单模态 Transformer 达 99.73%–99.95% 准确率

View PDF HTML (experimental)

Abstract:Deep learning's growing prevalence has driven its widespread use in healthcare, where AI and sensor advancements enhance diagnosis, treatment, and monitoring. In mobile health, AI-powered tools enable early diagnosis and continuous monitoring of conditions like stress. Wearable technologies and multimodal physiological data have made stress detection increasingly viable, but model efficacy depends on data quality, quantity, and modality. This study develops transformer models for stress detection using the WESAD dataset, training on electrocardiograms (ECG), electrodermal activity (EDA), electromyography (EMG), respiration rate (RESP), temperature (TEMP), and 3-axis accelerometer (ACC) signals. The results demonstrate the effectiveness of single-modality transformers in analyzing physiological signals, achieving state-of-the-art performance with accuracy, precision and recall values in the range of $99.73\%$ to $99.95\%$ for stress detection. Furthermore, this study explores cross-modal performance and also explains the same using 2D visualization of the learned embedding space and quantitative analysis based on data variance. Despite the large body of work on stress detection and monitoring, the robustness and generalization of these models across different modalities has not been explored. This research represents one of the initial efforts to interpret embedding spaces for stress detection, providing valuable information on cross-modal performance.

Subjects:	Machine Learning (cs.LG); Artificial Intelligence (cs.AI)
Cite as:	arXiv:2502.18733 [cs.LG]
	(or arXiv:2502.18733v2 [cs.LG] for this version)
	https://doi.org/10.48550/arXiv.2502.18733 arXiv-issued DOI via DataCite

Submission history

From: Sagnik Dakshit [view email]
[v1] Wed, 26 Feb 2025 01:04:58 UTC (1,219 KB)
[v2] Tue, 10 Nov 2026 14:59:21 UTC (885 KB)