Edge AI on Constrained Devices for Binary Sleep-Wake Classification in Dynamic Environments

2026-09-24

AI Summary

This study addresses the challenges of sleep monitoring for resource-constrained devices in dynamic environments, where motion interference and limited computational and energy budgets pose significant obstacles. To this end, we propose a multimodal edge AI system based on the ESP32-S3 microcontroller. The system integrates inertial sensing with lightweight vision models, employing a dual-core parallel architecture and a two-stage detection strategy. By leveraging FreeRTOS for hardware-software co-design, it enables privacy-preserving inference entirely on-device. Experimental results demonstrate that the proposed approach achieves 96.5% accuracy in motion detection and 89% in posture classification. These findings validate the feasibility of deploying robust, low-power, and privacy-secure sleep monitoring solutions at the edge.

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.

Problem

• Edge AI
• Sleep-Wake Classification
• Resource-Constrained Devices
• Motion Artifacts
• Dynamic Environments

Innovation

• Edge AI
• Multimodal pipeline
• ESP32-S3
• Sleep-wake classification
• FreeRTOS