IoT Enabled Heart Disease Accuracy Prediction of Healthcare Dataset Using Deep Belief Network

Fog is a data management and analytics service. This paper derives the most effective new approach for providing IoT-enabled services in healthcare applications using Fog Computing. In this study, data are collected from Google Scholar, Science Director, and MEDLINE databases. IoT-based Fog Computing techniques are proposed to provide quality services to users. An optimal resource provisioning method for boundary discovery, service level agreements, and administration services for an IoT client is proposed. The DeepQ residual information processing technique is applied to cloud data center connectivity, and the computing paradigm technique is to find the reference depth of fog levels. The proposed optimal resource provisioning algorithm studies the dataset and the TensorFlow tool is used to simulate the environment. The Deep Belief network is generated based on the above input using a 512 × 512 × 3-layer system and 3000 trained data, 1000 test data are taken for simulation. Each dataset simulation is recorded using supervised and unsupervised learning techniques. Based on the above results, IoT enables Fog Computing's data management and analytics systems to provide 95% accuracy, and compared to existing computing methods, our proposed systems show better performance in terms of security and convenience.