An efficient Elman neural network classifier with cloud supported internet of things structure for health monitoring system

Abstract

To improve the strain on healthcare systems which happens through an aging population and a rise in chronic illness, Internet of Things (IoT) technology has attracted much attention in recent years. Cloud computing along with the IoT concept is a novel trend, for an efficient management and online processing of sensor data, and its major problem is the protection of privacy. Normally, the data is acquired from the users (i.e. patients) by the healthcare service provider and distributes them with authorized clinics or healthcare experts and these details were distributed to both pharmaceutical and life health insurance companies. Additionally the hackers have susceptible about the data of the patient, at the time of synchronization or cloud transfer is happening with the devices that are interconnected. An efficient Elman Neural Network (ENN) classifier based data protection is given in this work, which forms the cryptography and authentication. This suggested work has two varieties of process namely client side and cloud side. In client side, initially, the EEG signal is obtained from human and is processed with the help of the Hyper analytic Wavelet Transform (HWT) with Adaptive Noise Cancellation (ANC) method. Then, through the Elliptic Curve Cryptography (ECC) scheme, signal is safeguarded from forgery. The features were drawn-out from authenticated information in cloud side, and these details were divided as abnormal or not. The appropriateness of this work is validated by executing the technique called One Class Support Vector Machine (OCSVM) with IoT that drivens the ECG-dependent health monitoring system in the cloud on both experimental analysis and simulation.