


Volume 20 No 20 (2022)
Download PDF
ADAPTIVE ECG SIGNAL TIME FREQUENCY ANALYSIS AND SIGNAL QUALITY ASSESSMENT USING AI
Swapnil Khare
Abstract
The combination of P-wave, QRS-complex and T-wave is known as one cardiac cycle of Electrocardiogram (ECG)
signal. It shows the electrical activity of the heart during polarization and depolarization activity. It is acquired by
standard lead arrangement through electrodes pasted on specified locations on the body during ECG test. It is
plotted on chart paper and stored in computer for analyzing in the future. Any change in the standard ECG signal
leads to heart disease (abnormal). During the acquisition of the ECG datasets different noises involve. These
noises hide the important characteristic of the ECG signal that misleads the signal analysis. Therefore,
morphological technique is not sufficient for analyzing such types of ECG datasets. Moreover, cost of ECG test is
very high. It requires automated ECG signal analysis technique using computerized classification that gives
accurate, fast and reliable detection of the disease. Time domain techniques work well in the cleaned signal
analysis and Frequency domain techniques are prone to spectral leakage problems. For analyzing ECG signals,
Time frequency analysis (TFA) methods offer simultaneous interpretation of the signal in both time and
frequency domain. Among existing TFA techniques, Auto-regressive Time Frequency Analysis (ARTFA) offers good
time frequency resolution. ARTFA were used for finding the coefficients in first step and time-frequency,
description in the second step. Coefficients clearly states about the status of the patient heart. Time-Frequency
Analysis depicts the existing R-peak of the patient ECG dataset. On the final stage, KNN were used.
Keywords
Feature Extraction, SVM, PSO, ECG, DWT
Copyright
Copyright © Neuroquantology
Creative Commons License
This work is licensed under a Creative Commons Attribution-NonCommercial-NoDerivatives 4.0 International License.
Articles published in the Neuroquantology are available under Creative Commons Attribution Non-Commercial No Derivatives Licence (CC BY-NC-ND 4.0). Authors retain copyright in their work and grant IJECSE right of first publication under CC BY-NC-ND 4.0. Users have the right to read, download, copy, distribute, print, search, or link to the full texts of articles in this journal, and to use them for any other lawful purpose.