Seamless Monitoring of Stress Levels Leveraging a Universal Model for Time Sequences

2024-07-04

arXiv.org

AI Summary

This study addresses the need for unobtrusive, continuous stress monitoring in patients with neurodegenerative diseases. We propose a personalized stress anomaly detection method leveraging low-fidelity heart rate variability (HRV) signals acquired from wrist-worn wearables. Departing from conventional classification paradigms, we formulate stress recognition as an individualized time-series anomaly detection task and pioneer the adaptation of the universal time-series model UniTS to resource-constrained wearable platforms. Our approach integrates HRV feature enhancement, noise-robust learning, attention-based attribution for interpretability, and a clinically calibratable mechanism—ensuring both clinical controllability and seamless daily integration. Experiments demonstrate that our method significantly outperforms 12 state-of-the-art baselines across three benchmark datasets; achieves stress detection accuracy on par with electrocardiogram (ECG)-derived HRV; and supports plug-and-play cross-device deployment.

Technology Category

• Machine Learning: Hardware-aware ML
• Data Mining & Knowledge Management: Anomaly/Outlier Detection
• Computer Vision: Video Understanding & Activity Analysis

Application Category

• User Modeling, Personalization and Recommendation: On-Device user modeling, personalization, and recommendation
• Responsible Web: Machine-in-the-loop, human agency and autonomy
• Search and Retrieval-Augmented AI: Personalized, context-aware and across-device search

Abstract

Monitoring the stress level in patients with neurodegenerative diseases can help manage symptoms, improve patient's quality of life, and provide insight into disease progression. In the literature, ECG, actigraphy, speech, voice, and facial analysis have proven effective at detecting patients' emotions. On the other hand, these tools are invasive and do not integrate smoothly into the patient's daily life. HRV has also been proven to effectively indicate stress conditions, especially in combination with other signals. However, when HRV is derived from less invasive devices than the ECG, like wristbands and smartwatches, the quality of measurements significantly degrades. This paper presents a methodology for stress detection from a wristband based on a universal model for time series, UniTS, which we finetuned for the task and equipped with explainability features. We cast the problem as anomaly detection rather than classification to favor model adaptation to individual patients and allow the clinician to maintain greater control over the system's predictions. We demonstrate that our proposed model considerably surpasses 12 top-performing methods on three benchmark datasets. Furthermore, unlike other state-of-the-art systems, UniTS enables seamless monitoring, as it shows comparable performance when using signals from invasive or lightweight devices.

Problem

• Detecting stress levels non-invasively using wearable devices
• Improving measurement accuracy from wristbands and smartwatches
• Enabling seamless stress monitoring with adaptive anomaly detection

Innovation

• Universal time series model for stress detection
• Anomaly detection approach for patient adaptation
• Explainable and seamless monitoring with lightweight devices