Convolution Neural Network Based Ecg Classifier

  • Sharanya S Department of Electronics and Instrumentation Engineering, SRM Institute of Science and Technology, Kattankulathur, Kancheepuram-603203 India.
  • Sridhar PA Department of Electronics and Instrumentation Engineering, SRM Institute of Science and Technology, Kattankulathur, Kancheepuram-603203 India.
  • Poornakala J Department of Electronics and Instrumentation Engineering, SRM Institute of Science and Technology, Kattankulathur, Kancheepuram-603203 India.
  • Muppala Vasishta Department of Electronics and Instrumentation Engineering, SRM Institute of Science and Technology, Kattankulathur, Kancheepuram-603203 India.
  • Tharani U Department of Electronics and Instrumentation Engineering, SRM Institute of Science and Technology, Kattankulathur, Kancheepuram-603203 India.

Abstract

Classification of Electrocardiogram (ECG) signals plays a significant role in the identification of the functioning of the heart. This work pertains with the ECG signals, where the classifier is developed for identification of normal or abnormal conditions of the heart. The raw ECG signals are collected from an online database (www.physioNet.org) for classification. The raw ECG signal is pre-processed for noise removal, and the frequency spectrum is analysed to compare raw and denoised ECG signal. Attributes (P, Q, R, S, T time intervals) from denoised ECG signal is analysed and classified using Convolution Neural Network (CNN). The paper reports a classification technique to differentiate ECG signals from the MIT-BIH database (arrhythmia database, arrhythmia p-wave annotations, atrial fibrillation). The CNN analyses the deviation between nominal ranges of attributes (amplitude and time interval) and classifies between the abnormality and normal ECG wave. This work provides a simple method for interpreting ECG related condition for the clinician and helps medical practitioners to make diagnostic decisions.

Keywords: Electrocardiogram (ECG), attributes, ConvolutionNeural Network (CNN), MIT-BIH database

Downloads

Download data is not yet available.
Published
2019-07-12
Citations
How to Cite
Sharanya S, Sridhar PA, Poornakala J, Muppala Vasishta, & Tharani U. (2019). Convolution Neural Network Based Ecg Classifier. International Journal of Research in Pharmaceutical Sciences, 10(3), 1626-1630. https://doi.org/10.26452/ijrps.v10i3.1327
Section
Original Articles
Article Level Metrix
Abstract Views: 371
PDF Downloaded: 123           LaTeX Downloaded: 291           HTML Downloaded: 0           ePUB Downloaded: 278