User privacy prevention model using supervised federated learning-based block chain approach for internet of Medical Things

This research focuses on addressing the privacy issues in healthcare advancement monitoring with the rapid establishment of the decentralised communication system in the Internet of Medical Things (IoMT). An integrated blockchain homomorphic encryption standard with an in-build supervised learning-based smart contract is designed to improvise personal data prevention. The Internet of Medical Things (IoMT) has advanced in healthcare with the rapid establishment of decentralised communication systems. Distributed ledgers have resource constraints to leverage public, private, and hybrid blockchain transactions to facilitate heterogeneous operations. The authors propose a supervised learning strategy in healthcare to mitigate learning health-related issues, improvise clinical monitoring, and ensure secure communication. The proposed approach handles the vast IoMT data by adopting blockchain for IoMT as (BIoMT) to preserve sensitive clinical information. It incorporates hybrid encryption techniques to improve patient and health records' privacy protection. BIoMT also maintains secured and sustainable supply chain management with a highly confidential decentralised framework using blockchain-based smart contracts, which minimises data loss. Moreover, a framework is designed with a hybrid hashing that integrates a homomorphically encrypted algorithm to support a smart contract for decentralised applicability. The BIoMT approach is tested and compared with the relevant prevention mechanisms. The evaluation shows that the effects observed from the result analysis noted that the proposed method outperforms reliable prevention mechanisms compared to the existing approaches.