Electrocardiogram classification of lead convolutional neural network based on fuzzy algorithm
Authors:
- 4 January 2020
- journal article
- research article
- Published by SAGE Publications in Journal of Intelligent & Fuzzy Systems: Applications in Engineering and Technology
- Vol. 38 (4) , 3539-3548
Abstract
With the development of society, health has attracted more and more attention. Heart disease is a common and frequently occurring disease, and it is fatal. Rapid and timely diagnosis and treatment of heart disease is very important. Electrocardiogram (ECG) reflects human heart health and is widely used in heart disease examination. Existing methods depending on doctors’ personal experience and diagnostic level are time-consuming and inefficient. Therefore, a classification method that can automatically analyze ECG is required. Aiming at the classification of 12-lead ECG, based on the good performance of convolution neural network, this paper proposes a method of ECG classification based on lead convolution neural network, which can effectively and accurately detect, recognize and classify ECG. First, the image features are extracted after the ECG is preprocessed, and then using the fuzzy set reduces the extracted ECG image features. Then, residual learning is used to optimize the convolutional neural network, and in order to ensure that the network is easy to train and fast convergence, a random parameter initialization method is introduced to achieve better classification results. The simulation results show that the proposed multi-lead filtering algorithm reduces the loss of useful information while eliminating noise; at the same time, the convolution neural network can effectively and accurately classify ECG images; and the introduction of residual network can improve the classification effect.Keywords
This publication has 12 references indexed in Scilit:
- Multi-label convolutional neural network based pedestrian attribute classificationImage and Vision Computing, 2017
- Feature selection for linear SVM with provable guaranteesPattern Recognition, 2016
- Wind speed forecasting based on the hybrid ensemble empirical mode decomposition and GA-BP neural network methodRenewable Energy, 2016
- Deep learning approach for active classification of electrocardiogram signalsInformation Sciences, 2016
- Estimating nocturnal opaque ice cloud optical depth from MODIS multispectral infrared radiances using a neural network methodJournal of Geophysical Research: Atmospheres, 2016
- Arrhythmia recognition and classification using combined linear and nonlinear features of ECG signalsComputer Methods and Programs in Biomedicine, 2016
- Multi-view facial landmark detector learned by the Structured Output SVMImage and Vision Computing, 2016
- Modeling urban growth with GIS based cellular automata and least squares SVM rules: a case study in Qingpu–Songjiang area of Shanghai, ChinaStochastic Environmental Research and Risk Assessment, 2015
- Fast and high-performance template matching method2011
- The Value of Electrocardiogram Monitoring in Diabetic KetoacidosisDiabetes Care, 1980