1Research Scholar, Department of Computer Science and Engineering, ITER, Siksha ‘O’ Anusandhan (Deemed to be University), Bhubaneswar, India
2Professor, Department of Electronics and Communication Engineering, ITER, Siksha ‘O’ Anusandhan (Deemed to be University), Bhubaneswar, India
*Corresponding Author: Mihir Narayan Mohanty Professor, Department of Electronics and Communication Engineering, ITER, Siksha ‘O ’Anusandhan (Deemed to be University), Bhubaneswar, India. Email: mihirmohanty@soa.ac.in
Online published on 21 January, 2019.
Automated disease diagnosis system is an effective toll in health care system which can reduce the death rate. This automated prediction system can predict the disease at an early stage by analyzing the huge amount of data collected from different pathological tests. In this paper, ECG signal classification based on radial basis function network (RBFN) is proposed to classify arrhythmia. In the first step the signal is passed through different filters for removing noise. Before classification task discrete wavelet transform (DWT) is applied in the filtered signal to extract the QRS complex features. Proposed classifier is giving better result as compare to other classifiers as presented in result section
ECG, Radial basis function Neural Networks, High Pass Filter, Low Pass filter, Derivative filter, Discrete Wavelet Transform
