Privacy-aware quantum convolutional neural network for blockchain-based IoT health care data

Nowadays, the Internet of Things (IoT) is widely used in many applications, including healthcare to monitor the health condition of patients. However, it faces privacy and security issues due to the massive growth of hacking systems that provide illegal access to confidential health information. Blockchain (BC) is applied in IoT healthcare systems to manage healthcare data securely by using transparency features. In this research, a novel CAViaR Jellyfish Swarm Optimization enabled Quantum Convolutional Neural Network (CJSO-QCNN) is developed for the removal of noise in a privacy-aware BC-based IoT healthcare system. The CJSO is the combination of Conditional Autoregressive Value at Risk (CAViaR) and Jellyfish Search Optimizer (JSO). The data privacy is ensured according to the user preference by the service provider. The data is classified initially for identifying the sensitive data and is allowed for the treatment of noise, which is then stored in BC. Later, the user accesses the data by removing the noise using the CJSO-QCNN model. The valid data credentials are stored at the service provider according to user preferences. In addition, the superiority of the designed model is computed by comparing the performance with other prevailing approaches. The experimental results revealed that the CJSO-QCNN attained a maximum accuracy of 88.79%, a True Positive Rate (TPR) of 88.20%, and a True Negative Rate (TNR) of 88.61%.