Edge AI detects sleep and wake states on low power devices
Edge AI on Constrained Devices for Binary Sleep-Wake Classification in Dynamic Environments
Machine Learning
Summary
Tracking when someone is asleep or awake can be tricky, especially when they move around a lot. The authors made a small computer device that uses both movement and pictures to tell if a person is sleeping or awake, even when things are changing around them. Their system works well without needing a lot of power or sending data elsewhere, protecting privacy. They showed it can work in real life on a tiny chip found in many gadgets.
What this means in practice
- •For wearable device developers: Build low-power sleep tracking features that combine movement and visual data locally on small chips without cloud dependence.$Commercial implications: Enables privacy-focused wearable sleep trackers with accurate local detection on affordable hardware.
- •For iot device engineers: Integrate robust sleep-wake detection in dynamic environments using lightweight sensors and embedded AI on constrained hardware.
Authors
Stefan Reitmann, Lena Oden
Abstract
This paper presents an Edge AI-based system for detecting sleep and wake states in non-stationary mobile environments using resource-constrained embedded hardware. Conventional approaches relying on accelerometer-based activity metrics are highly susceptible to motion and vibration artifacts and are limited by strict compute and energy budgets of wearable and IoT devices. To address these challenges, a multimodal pipeline is designed and implemented on an ESP32-S3 microcontroller. The system combines inertial sensing for head movement analysis and visual pose classification. A dual-core architecture with FreeRTOS enables parallel execution of real-time data acquisition and on-device inference. Sleep detection follows a two-stage strategy: low-movement detection over a temporal window, followed by visual validation of poses. Experimental results show accuracies of 96.5% for motion-based detection and 89% for pose classification, yielding robust binary sleep-wake classification. Field tests confirmed feasibility in representative mobile scenarios. The results demonstrate that privacy-preserving, local sleep detection is achievable on edge hardware through careful co-design, while highlighting limitations in sensing intrusiveness, dataset scale, and system integration.