期刊名称：International Journal on Smart Sensing and Intelligent Systems
印刷版ISSN：1178-5608
出版年度：2018
卷号：11
期号：1
页码：1-15
DOI：10.21307/ijssis-2018-029
出版社：Massey University
摘要：The success of an Electrocardiogram (ECG) Decision Support System (DSS) requires the use of an optimum machine learning approach. For this purpose, this paper investigates the use of three feedforward neural networks; the Multilayer Perceptron (MLP), the Radial Basic Function Network (RBF), and the Probabilistic Neural Network (PNN) for recognition of normal and abnormal heartbeats. Feature sets were based on ECG morphology and Discrete Wavelet Transformer (DWT) coefficients. Then, a correlation between features was applied. After that, networks were configured and consequently used for the ECG classification. Next, with respect to the performance criteria fixed by the DSS users, a comparative study between them was deduced. Results show that for classifying the MIT-BIH arrhythmia database signals, the RBF (ACC = 99.9%) was retained as the most accurate network, the PNN (Tr_ttime = 0.070 s) as the rapidest network in the training stage and the MLP (Test_time = 0.096 s) as the rapidest network in testing stage.
其他关键词：Machine learning, Decision Support System, ECG, Arrhythmia classification, Neural Networks.
