Federated Edge Intelligence for Adaptive Health Prediction in Elderly Care

Abstract

This research presents the development and evaluation of an IoT-based nursing home monitoring system designed to enhance elderly healthcare through real-time detection, predictive alerts, and caregiver support. The system integrates multimodal sensing with edge and server-level machine learning to monitor three critical areas: sleep quality, fall detection, and emotion recognition in dementia patients. Hardware components, including a Raspberry Pi and non-intrusive sensors, were combined with lightweight neural networks to ensure low-latency processing. Detailed model optimizations, including 8-bit quantized TensorFlow Lite MobileNetV2 and CNN-LSTM pipelines, enabled on-device inference within 80-120 ms. A caregiver dashboard and mobile application provided intuitive visualization of real-time alerts and long-term health reports. Benchmarking against threshold-based and classical ML baselines demonstrated 9-18% performance improvements and 56% lower alert latency. Experimental evaluation demonstrated promising outcomes, with fall detection achieving 95% accuracy, emotion detection 91%, and sleep monitoring 90% reliability. System uptime reached 98%, and alerts were delivered within two seconds in 96% of cases. These results indicate that the proposed solution can effectively reduce caregiver burden, improve resident safety, and establish a scalable framework for intelligent elderly healthcare monitoring.