Intelligent Edge Healthcare Using Federated Learning and Clustering with Kepler-Optimized Steerable Graph Neural Networks

Abstract

Nowadays, people frequently use smart healthcare systems (SHS) to use a variety of smart devices to monitor their health. The SHS uses Internet of Things (IoT) and cloud infrastructure for data collection, transmission via smart devices, data processing, storage, and medical advice. It can be difficult to process so much data from so many IoT devices in a short period. Therefore, in SHS, technical frameworks like fog computing or edge computing can be utilized as mediators between the user and the cloud. It shortens response times for lower-level (edge-level) data processing. If anomalous data is generated, it will react quickly and securely to store and retrieve important data. This paper presents a smart health monitoring system architecture comprising three core layers: Data Generation, Edge Computing, and Cloud Storage. The Data Generation Layer utilizes IoMT devices, wearables, and sensors connected to an Edge-IoT Gateway for stream data acquisition. The Edge Computing Layer uses Z-score Min-Max normalization-based preprocessing, cascading residual graph convolutional networks to extract features, and the Steerable Graph Neural Network with Kepler Optimization Algorithm (SGNN-KOA) to improve the performance. The Cloud Storage Layer is provided to enhance the security feature of the cloud network using lightweight dynamic elliptic curve cryptography with Schoof’s algorithm for data deposit. As mentioned, the system is designed to support multi-modal learning, adaptive feedback, and secure access for facility comprehensive health management. With an accuracy rate of over 99%, convergence in fewer iterations, and high classification capabilities using measures like AUC of 0.99, the suggested method outperforms the others in terms of accuracy at epochs, reduced divergence, and improved accuracy.