DEVELOPMENT OF SECURE AND ENERGY EFFICIENT REMOTE HEALTH MONITORING SYSTEM AND IMPROVED NETWORK PERFORMANCE

Abstract

A novel approach to cyber protection with intelligent defence capabilities is the health prevention concept. It has the ability to promptly respond to incursion activity in addition to detecting it. This study integrates health prevention technology with semi-supervised clustering and deep learning theory. The current direction in neural network development is represented by deep learning, which is based on deep structures. For achieving health prevention with a low recognition error rate, semi-supervised learning makes use of a bulk amount of unlabeled (cyber traffic data) and a less amount of labelled (cyber traffic data). Because of its low mistake rate, discriminative deep belief network (LSTM)-based cyber defence technology has becoming a latest research topic in the field of health prevention. Suggested a Remote health monitoring. In order to address the issue of the health prevention model's high classification error rates, this study suggests a technique for large-scale semi-supervised deep learning based on local and non-local regularization that uses LSTM. The proposed LSTM model ensure the lowest error rate, by making relationship with the results of the Hopfield, support vector machine (SVM), generative adversarial network (GAN) and a deep belief network random forest (DBN-RFS) classifiers in terms of health prevention. Therefore, the suggested approach improves the functionality of the health prevention system.