APPLYING DISCRETE WAVELET TRANSFORM FOR ECG SIGNAL ANALYSIS IN IOT HEALTH MONITORING SYSTEMS

Abstract

Continuous remote monitoring has been made possible by the recent integration of Internet of Things (IoT) technologies with healthcare monitoring systems, greatly improving patient care. In an Internet of Things (IoT)-based health monitoring system, this research investigates the use of Discrete Wavelet Transform (DWT) in the processing of electrocardiogram (ECG) signals. The excellent time-frequency localization capabilities of DWT are used since they are essential for the efficient analysis of non-stationary signals such as ECG. The process focuses on applying DWT to filter banks made up of High Pass Filters (HPF) and Low Pass Filters (LPF) in order to separate the ECG signal into its component frequencies. Denoising, compression, and feature extraction are aided by this procedure, which is vital for the diagnosis of cardiac abnormalities. Signal acquisition, preprocessing, feature extraction, and IoT-based transmission to cloud servers for real-time analysis are some of the components that make up the system architecture. Various performance metrics, including Signal-to-Noise Ratio (SNR), Mean Squared Error (MSE), and compression ratios, are used to assess the effectiveness of the proposed technique and show notable gains in signal clarity and data reduction.