Classification of human electrocardiograms by multi-layer convolutional neural network and hyperparameter optimization

Issue title: Selected papers from the 9th International Multi-Conference on Engineering and Technology Innovation 2019 (IMETI2019)

Guest editors: Wen-Hsiang Hsieh

Article type: Research Article

Authors: Chen, Yao-Mei^{a; b} | Chen, Yenming J.^c | Tsai, Yun-Kai^d | Ho, Wen-Hsien^{e; f; *} | Tsai, Jinn-Tsong^{e; g; *}

Affiliations: [a] School of Nursing, Kaohsiung Medical University, Kaohsiung Taiwan | [b] Superintendent Office, Kaohsiung Medical University Hospital, Kaohsiung, Taiwan | [c] Department of Logistics Management, National Kaohsiung University of Science and Technology, Kaohsiung, Taiwan | [d] Department of Computer Science and Engineering, National Sun Yat-Sen University, Kaohsiung, Taiwan | [e] Department of Healthcare Administration and Medical Informatics, Kaohsiung Medical University, Kaohsiung, Taiwan | [f] Department of Medical Research, Kaohsiung Medical University Hospital, Kaohsiung, Taiwan | [g] Department of Computer Science, National Pingtung University, Pingtung, Taiwan

Correspondence: [*] Corresponding author. Jinn-Tsong Tsai, E-mail: [email protected]. and Wen-Hsien Ho, E-mail: [email protected].

Abstract: A multi-layer convolutional neural network (MCNN) with hyperparameter optimization (HyperMCNN) is proposed for classifying human electrocardiograms (ECGs). For performance tests of the HyperMCNN, ECG recordings for patients with cardiac arrhythmia (ARR), congestive heart failure (CHF), and normal sinus rhythm (NSR) were obtained from three PhysioNet databases: MIT-BIH Arrhythmia Database, BIDMC Congestive Heart Failure Database, and MIT-BIH Normal Sinus Rhythm Database, respectively. The MCNN hyperparameters in convolutional layers included number of filters, filter size, padding, and filter stride. The hyperparameters in max-pooling layers were pooling size and pooling stride. Gradient method was also a hyperparameter used to train the MCNN model. Uniform experimental design approach was used to optimize the hyperparameter combination for the MCNN. In performance tests, the resulting 16-layer CNN with an appropriate hyperparameter combination (16-layer HyperMCNN) was used to distinguish among ARR, CHF, and NSR. The experimental results showed that the average correct rate and standard deviation obtained by the 16-layer HyperMCNN were superior to those obtained by a 16-layer CNN with a hyperparameter combination given by Matlab examples. Furthermore, in terms of performance in distinguishing among ARR, CHF, and NSR, the 16-layer HyperMCNN was superior to the 25-layer AlexNet, which was the neural network that had the best image identification performance in the ImageNet Large Scale Visual Recognition Challenge in 2012.

Keywords: Convolutional neural network, hyperparameter, human electrocardiogram, PhysioNet, uniform experimental design approach

DOI: 10.3233/JIFS-189610

Journal: Journal of Intelligent & Fuzzy Systems, vol. 40, no. 4, pp. 7883-7891, 2021