Abstract
Mobile computing and technology are becoming more common in many parts of private life and public services, and they are playing an increasingly important role in healthcare, not just for sensory devices but also for communication, recording, and display. They are used for more than only sensory devices but also for communications, recording, and display. Numerous medical indications and postoperative days must be monitored carefully. As a result, the most recent development in Internet of Things- (IoT-) based healthcare communication has been embraced. The Internet of Things (IoT), which is employed in a wide range of applications, is a catalyst for the healthcare industry. Healthcare data is complicated, making it difficult to handle and evaluate in order to derive useful information for decision-making. On the other hand, data security is a vital requirement in a healthcare data systems. Determining the need for a smart and secure IoT platform for healthcare applications, we create one in this study. Here, a cutting-edge encryption algorithm is used to protect the health data. Normalization is first used to preprocess the data and remove any irrelevant information. Using principal component analysis and logistic regression, the data’s features are extracted (LR-PCA). To choose the pertinent features, a feature selection process based on genetic algorithms is used. We have put out a brand-new kernel homomorphism. To increase the security of the IoT network, use the two-fish Encryption algorithm (KHTEA). EBSMO (exponential Boolean spider monkey optimization) is used to further boost the encryption process’ effectiveness. Utilizing the MATLAB simulation tool, the proposed system is assessed, and the metrics are contrasted with the accepted practices. Our suggested solution has been shown to be effective in protecting medical healthcare data. The effectiveness of the proposed and existing approaches is assessed using metrics for encryption time, execution time, and security level. The security precautions we suggested for healthcare data worked well.