PRINCIPLES OF FORMING A DATABASE OF ECG SIGNALS AND THEIR FRAGMENTS FOR EVALUATING THE CHARACTERISTICS OF WEARABLE DIGITAL ON-LINE MONITORS

Abstract

Electrocardiographic (ECG) signals have several properties that can greatly complement the existing, and more established biometric modalities. Some of the most prominent properties are the fact that the signals can be continuously acquired using minimally intrusive setups, are not prone to produce latent patterns, and provide intrinsic liveliness detection, opening new opportunities within the area of biometric systems development. The paper proposes methods for forming a database of ECG signals and their fragments for assessing the characteristics of portable digital on-line monitors. In the method of discrete wavelet transform (DWT) it allows to determine with high accuracy the presence of RR-intervals and their segments. This makes it possible to use this method for classifying ECG signals, forming a database of signal data records and generating test signals designed to assess the characteristics of wearable digital ONLINE monitors. This article presents an improved and more efficient algorithm by Discrete Wavelet Transform for generating electrocardiogram (ECG) signals from the PhysioBank archive to test the performance of an ECG machine.