Decentralized Security Architecture for Health IoT Leveraging TGA and ANN

Rapid adoption of Health Internet of Things (Health IoT) revolutionized healthcare by enabling continuous monitoring and real-time data analysis. However, the massive influx of data generated by Health IoT devices presents significant challenges in data processing, security, and efficient task management. This paper proposes a novel Task Group Aggregation-Based Overflow Handling with Artificial Neural Networks (TGA-ANN) framework utilizing Fog Computing to enhance security and efficiency in Health IoT systems. The TGA-ANN framework leverages TGA to manage and prioritize data tasks effectively, preventing overflow and ensuring timely processing. By integrating ANN within the fog layer, the framework enhances decision-making capabilities, enabling intelligent task distribution and anomaly detection to bolster security. This approach mitigates the risk of data breaches and unauthorized access, ensuring confidentiality and integrity sensitive health information. The obtained results demonstrate that the TGA-ANN framework significantly improves data processing efficiency, reduces latency, and enhances security measures compared to traditional cloud-based solutions. This research provides robust and scalable solution managing growing demands Health IoT, paving the way for more secure and efficient healthcare services.