Investigation and classification of ECG beat using Input Output Additional Weighted Feed Forward Neural Network

Citations Over Time

Abstract

Arrhythmia is an irregular heart beat which affects the heart rate causing irregular rhythms. The irregular rhythms either slow down or increase the heart beat. This paper investigates soft computing techniques for ECG classification based on the type of arrhythmia using RR interval. Features are extracted from the time series Electro Cardiogram (ECG) data using Discrete Cosine Transform (DCT) and the distance between RR waves are computed. The extracted RR interval of the beat is used as feature. Features extracted in the frequency domain are classified using Classification and Regression Tree (CART), Radial Basis Function (RBF), Multi Layer Perceptron Neural Network (MLP-NN), and proposed Feed Forward Neural Network (FF-NN). Experiments were conducted using MIT-BIT arrhythmia database.

Related Papers

• → Performance Comparison of Multi-layer Perceptron (Back Propagation, Delta Rule and Perceptron) algorithms in Neural Networks(2009)113 cited
• → Prediction of significant wave height using geno-multilayer perceptron(2012)48 cited
• → Multi-layer radial basis function networks. An extension to the radial basis function(2002)16 cited
• → From multilayer perceptrons to radial basis function networks: a comparative study(2005)14 cited
• → <title>Comparison of sinusoidal perceptron with multilayer classical perceptron</title>(1991)