arXiv cs.AI· Eric Oliver, Sagnik Dakshit·· 10 小时前AI 评分22
基于 WESAD 数据集的压力检测跨模态研究
Cross-Modality Investigation on WESAD Stress Classification
AI 导读
研究用 Transformer 模型在 WESAD 数据集上基于 ECG、EDA、EMG、RESP、TEMP 和 3 轴 ACC 信号做压力检测，单模态模型取得 99.73% 至 99.95% 的准确率、精确率和召回率。研究进一步考察跨模态表现，并通过学习到的嵌入空间 2D 可视化和基于数据方差的定量分析加以解释。
正文 · 原文
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)
来源：arXiv cs.AI · arxiv.org