Lightweight Cross-Device Sleep Tracking on the WeBe Wearable Platform

2026-05-15

AI Summary

This study addresses the limitations of current wearable devices for sleep tracking, which often rely on proprietary algorithms and device-specific representations, hindering generalizability and reliability. To overcome this, the authors propose a lightweight, cross-device compatible method that operates solely on raw accelerometer signals. The approach leverages epoch-level activity feature extraction, temporal smoothing, normalized scoring, and a globally calibrated threshold to classify sleep versus wake states—without requiring complex models or device-specific tuning. Evaluated on the MMASH dataset, the method achieves a mean absolute error of 41.6 minutes in total sleep time estimation; performance further improves to 27.4 minutes on the real-world WeBe dataset, outperforming commercial ActiGraph solutions. These results demonstrate significantly enhanced reproducibility and practical utility for real-world sleep monitoring.

Abstract

Wearable devices are widely used for continuous health monitoring, yet reliable sleep tracking on emerging platforms remains underexplored due to reliance on proprietary algorithms and device-specific activity representations. We present a lightweight and reproducible sleep tracking pipeline that operates directly on raw accelerometer signals. The method converts data into epoch-level activity features, applies temporal smoothing and normalized scoring, and performs sleep/wake classification using a globally calibrated threshold. We calibrate the model on the Multilevel Monitoring of Activity and Sleep in Healthy People (MMASH) dataset and evaluate it in a cross-device study using the WeBe wearable platform and a commercial ActiGraph device. On MMASH, the method achieves a mean absolute error of 41.6 minutes in Total Sleep Time (TST), with onset and offset errors of 6.3 and 7.4 minutes. On real-world WeBe data from three participants across five sessions, it achieves a mean TST error of 27.4 minutes and onset and offset errors of 13.9 and 8.0 minutes. In contrast, a commercial ActiGraph pipeline shows larger discrepancies relative to ground truth. These results demonstrate accurate and generalizable sleep tracking using a simple and reproducible pipeline.

Problem

• sleep tracking
• wearable devices
• cross-device
• health monitoring
• activity representation

Innovation

• lightweight sleep tracking
• cross-device generalization
• raw accelerometer signals
• globally calibrated threshold
• reproducible pipeline