Constructing RBF Networks for Classifying ECG Heartbeat Patterns

In this paper, we propose a method to construct radial basis function (RBF) networks for classifying ECG heartbeat patterns. The method consists of three parts. First, non-heartbeat components in the ECG are removed, and the completed PQRST waveforms are extracted. Second, a clustering technique is used to cluster the heartbeat patterns, and the resulting clusters form the radial basis functions of the hidden layer. Third, the least square method is used to compute the optimal weight values for the output layer. The good performance of the constructed networks are revealed from the experiments with the MIT-BIH datasets.

[1]  Manuel G. Penedo,et al.  Heartbeat classification fusing temporal and morphological information of ECGs via ensemble of classifiers , 2019, Biomed. Signal Process. Control..

[2]  Anand Godbole,et al.  A machine learning approach for the classification of cardiac arrhythmia , 2017, 2017 International Conference on Computing Methodologies and Communication (ICCMC).

[3]  Aditi Gavhane,et al.  Prediction of Heart Disease Using Machine Learning , 2018, 2018 Second International Conference on Electronics, Communication and Aerospace Technology (ICECA).

[4]  Qiao Li,et al.  Multi-source features and support vector machine for heart rhythm classification , 2017, 2017 Computing in Cardiology (CinC).

[5]  Kup-Sze Choi,et al.  Heartbeat classification using disease-specific feature selection , 2014, Comput. Biol. Medicine.

[6]  Philip de Chazal,et al.  Automatic classification of heartbeats using ECG morphology and heartbeat interval features , 2004, IEEE Transactions on Biomedical Engineering.

[7]  Jalal A. Nasiri,et al.  ECG Arrhythmia Classification Using Least Squares Twin Support Vector Machines , 2018, Electrical Engineering (ICEE), Iranian Conference on.

[8]  U. Rajendra Acharya,et al.  Automated detection of arrhythmias using different intervals of tachycardia ECG segments with convolutional neural network , 2017, Inf. Sci..

[9]  Sebastian Zaunseder,et al.  Optimization of ECG Classification by Means of Feature Selection , 2011, IEEE Transactions on Biomedical Engineering.