Edge-AI Enabled Sustainable Consumer Electronics for Remote Health Monitoring

Abstract

To address the high energy consumption and network dependence issues of remote health monitoring devices, this study explores the integration of edge artificial intelligence and sustainable design in such devices, aiming to resolve these problems associated with existing solutions. A multi-level collaborative design framework is proposed, integrating algorithm lightweighting, hardware energy efficiency optimization, and intelligent energy management to achieve efficient processing of physiological data on the terminal device while improving environmental performance. Experiments show that the optimized model significantly reduces energy consumption and storage requirements while maintaining high detection accuracy; the dynamic energy scheduling strategy effectively enhances the device's self-sufficiency. This research provides a systematic technical path for developing high-performance, sustainable intelligent health devices.