Classifier Based Detection of Myocardial Infarction and Atrial Fibrillation on ECG Signals
Author(s):
Dhanya V K, Chinchu S
Keywords:
AF, MI, Probabilistic neural network classifier, RMSSD,SE,TPR
Abstract
Myocardial Infarction (MI) and Atrial Fibrillation (AF) are serious heart diseases. The number of patients related to the heart failure due to MI and AF is increasing day by day. Early detection of MI and AF may reduce the risk of death due to the heart failure. In this, a novel technique is proposed for the detection of Atrial fibrillation and Myocardial infarction from electrocardiogram (ECG). In myocardial infarctioninversion of T-wave, changes occurring on ST elevation, hypercute T-waves or pathological Q-wave are the pathological characteristics seen in the ECG signals. Wavelet decomposition of the ECG signals segments the components at different sub bands for feature extraction. In this work, entropy and covariance values are used for diagnostic features. Probabilistic Neural Network (PNN) is used as a classifier to detect the MI. In atrial fibrillation, the irregularity in the R-R intervals and the absence of P-wave are the characteristics seen in ECG signals. For the detection of AF use the algorithm that follows the parametric statistic such as RMSSD, SE, and non-parametric statistic is TPR. Then check the result of RMSSD, TPRand SE of every beat, whether it crosses the threshold level or not. If all these parameters will cross the threshold level then the beat affected by AF. The accuracy, the sensitivity and the specificity values higher compared to other methods
Article Details
Unique Paper ID: 146373

Publication Volume & Issue: Volume 4, Issue 12

Page(s): 356 - 364
Article Preview & Download


Share This Article

Join our RMS



Conference Alert

NCSEM 2024

National Conference on Sustainable Engineering and Management - 2024

Last Date: 15th March 2024

Latest Publication

Call For Paper

Volume 10 Issue 10

Last Date for paper submitting for March Issue is 25 June 2024

About Us

IJIRT.org enables door in research by providing high quality research articles in open access market.

Send us any query related to your research on editor@ijirt.org

Social Media

Google Verified Reviews

Contact Details

Telephone:6351679790
Email: editor@ijirt.org
Website: ijirt.org

Policies

Important Links

Browse Rsearch papers