Ensuring the privacy and security of IoT-medical data: a hybrid deep learning-based encryption and blockchain-enabled transmission

Ensuring the privacy and security of IoT-medical data: a hybrid deep learning-based encryption and blockchain-enabled transmission

연구 분야: Verification

학회: Multimedia Tools and Applications

E-health has emerged as a key research area as long as the advent of the Internet of Things (IoT). Maintaining patients' privacy seems complex because patient data is so sensitive. In medical uses, patient health information is often kept in the cloud, which bounds the user’s ability to fully control their data. To overcome the issues of privacy and security, medical data is collected from IoT sensors embedded in patients to the Personal Digital Assistant (PDA) for further processing. A hybrid encryption algorithm is used to ensure data security during transmission from the gathered medical-related data. The encrypted report is deposited in the cloud for later retrieval with appropriate access controls and encryption mechanisms in place. The use of blockchain for transmitting encrypted data further enhances the transmission of data securely and reduces the risk of data breaches. The generation of encryption and decryption keys using a hybrid deep learning model (LSTM and CNN) ensures the uniqueness and robustness of the keys. The selection of the optimal key using the Self-Improved Lion Optimization Algorithm (SI-LA) ensures the efficiency and effectiveness of the encryption and decryption process. Moreover, the execution of the model is equated with the existing technology; therefore, the proposed model is ensured as a more effective technique than the existing technique in terms of performance metrics.