Cloud-Edge Synergy for Low-Latency Autism Intervention

Abstract

Proper response to behavioral symptoms promptly is essential when working with children who have Autism Spectrum Disorder (ASD), but the latency, connection, and privacy issues commonly hamper the existing cloud-based systems. In this work, it is suggested to implement a Cloud-Edge Synergy Framework (CESF) that incorporates edge analytics, federated learning, and cloud-based orchestration to implement real-time autism intervention. The system utilizes behavioral IoT sensors, edge-deployed AI agents, and cloud governance modules to support quick, interpretable, and ethically efficient reactions. Experimental assessment indicates that there is a 46 percent and 23 percent latency and accuracy improvement, respectively, compared to more traditional cloud-only models. The architecture facilitates the real-time behavioral analytics to be coupled with the reliable AI governance to provide immediate, privacy-safe, and clinically interpretable feedback loops to the autism care.