Affiliations: [a] Department of Computer Science and Engineering, V.R.S. College of Engineering and Technology, Arasur, India | [b] Department of Artificial Intelligence and Data Science, Panimalar Engineering College, Chennai, India
Correspondence:
[*]
Corresponding author: Ramesh Kuppusamy, Department of Computer Science and Engineering, V.R.S. College of Engineering and Technology, Arasur, Villupuram, India. E-mails: [email protected] and [email protected].
Abstract: BACKGROUND: In recent times, there has been widespread deployment of Internet of Things (IoT) applications, particularly in the healthcare sector, where computations involving user-specific data are carried out on cloud servers. However, the network nodes in IoT healthcare are vulnerable to an increased level of security threats. OBJECTIVE: This paper introduces a secure Electronic Health Record (EHR) framework with a focus on IoT. METHODS: Initially, the IoT sensor nodes are designated as registered patients and undergo initialization. Subsequently, a trust evaluation is conducted, and the clustering of trusted nodes is achieved through the application of Tasmanian Devil Optimization (STD-TDO) utilizing the Student’s T-Distribution. Utilizing the Transposition Cipher-Squared random number generator-based-Elliptic Curve Cryptography (TCS-ECC), the clustered nodes encrypt four types of sensed patient data. The resulting encrypted data undergoes hashing and is subsequently added to the blockchain. This configuration functions as a network, actively monitored to detect any external attacks. To accomplish this, a feature reputation score is calculated for the network’s features. This score is then input into the Swish Beta activated-Recurrent Neural Network (SB-RNN) model to classify potential attacks. The latest transactions on the blockchain are scrutinized using the Neutrosophic Vague Set Fuzzy (NVS-Fu) algorithm to identify any double-spending attacks on non-compromised nodes. Finally, genuine nodes are granted permission to decrypt medical records. RESULTS: In the experimental analysis, the performance of the proposed methods was compared to existing models. The results demonstrated that the suggested approach significantly increased the security level to 98%, reduced attack detection time to 1300 ms, and maximized accuracy to 98%. Furthermore, a comprehensive comparative analysis affirmed the reliability of the proposed model across all metrics. CONCLUSION: The proposed healthcare framework’s efficiency is proved by the experimental evaluation.
Keywords: Cluster Head (CH), Electronic Health Records (EHR), Student’s T-Distribution employed Tasmanian Devil Optimization (STD-TDO), Swish Beta activated-Recurrent Neural Network (SB-RNN), Neutrosophic Vague Set Fuzzy (NVS-Fu)
