Secure and Scalable IoT-Based Health Monitoring System using Deep Learning, Blockchain, and Decentralized Edge Computing

This paper introduces an IoT-based far-health monitoring system that integrates DL models, blockchain technology, and decentralized edge computing to enhance the accuracy of diagnostics and integrity in patient data. The system easily detects such conditions as diabetic retinopathy and glaucoma using the feature extraction from fundus images based on VGG16, as well as LSTM networks through the analysis of temporal health data for advanced predictive analytics in health. It guarantees an immutable and tamperproof logging data structure that enforces cooperation and respects privacy, and a quantum-resistant cryptography solution guards it against any dangers in the future. Local computation leading to a reduction in dependency on cloud use The Raspberry Pi device results in low-latency alerts to critical health metrics, ensuring real-time monitoring meets the needs of certain accuracy with long-term scalability to deal with insider risks and secure patient privacy as well. Increased specificity to 26.24% than existing methods.