A Comprehensive Review of Hybrid Graph Neural Networks for Wearable IoT Monitoring Systems with Adaptive Algorithms and Energy-Efficient WSN Integration

Abstract

The rapid advancement of wearable Internet of Things (IoT) technologies has significantly transformed modern healthcare monitoring systems by enabling continuous, real-time tracking of physiological parameters. However, challenges related to scalability, energy efficiency, data heterogeneity, and security remain critical in large-scale deployments. This review explores recent advancements in hybrid Graph Neural Networks (GNNs) integrated with adaptive algorithms and energy-efficient Wireless Sensor Networks (WSNs) for wearable IoT monitoring systems. GNNs have emerged as powerful tools for modelling complex relationships in sensor networks, enabling efficient data processing and improved predictive capabilities. The study examines hybrid GNN architectures, including graph convolutional networks (GCNs), graph attention networks (GATs), and spatio-temporal GNNs, along with adaptive optimization techniques such as reinforcement learning and evolutionary algorithms. Additionally, the role of energy-efficient WSN integration is analysed in minimizing power consumption and extending network lifetime. The review highlights emerging trends such as edge intelligence, federated learning, and graph-based anomaly detection. Comparative analysis indicates that hybrid approaches combining GNNs, adaptive algorithms, and IoT architectures provide improved accuracy, scalability, and energy efficiency. The paper concludes by identifying key challenges and future research directions for developing intelligent, low-power, and secure wearable healthcare systems.