Yang Shiyilin, Shao Jie, Yang Xin, Chen Xin, Wang Xingxing
{"title":"ECG arrhythmias Classification with a Graph Bispectrum method","authors":"Yang Shiyilin, Shao Jie, Yang Xin, Chen Xin, Wang Xingxing","doi":"10.1109/ISBP57705.2023.10061314","DOIUrl":null,"url":null,"abstract":"Heart disease is leading killers of human beings. Recognizing and categorizing Electrocardiogram (ECG) signals is crucial for early heart and cardiovascular disease prevention. A novel classification approach for ECG Arrhythmias based on Graph Bispectrum (GBispec) is proposed. First, the ECG signal is converted from the time domain to the Graph domain by using Graph Fourier Transform (GFT); Then, referring to the traditional bispectrum algorithm, the GFT results of ECG are converted into GBispec; Then, extract the graph features of Graph Integral Bispectrum (GIB), and use Deep Neural Networks(DNN) to process the GIB results. 4 different types of ECG signals are classified. Experiments results show that proposed method is effective in classification.","PeriodicalId":309634,"journal":{"name":"2023 International Conference on Intelligent Supercomputing and BioPharma (ISBP)","volume":"42 1","pages":"0"},"PeriodicalIF":0.0000,"publicationDate":"2023-01-06","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":"0","resultStr":null,"platform":"Semanticscholar","paperid":null,"PeriodicalName":"2023 International Conference on Intelligent Supercomputing and BioPharma (ISBP)","FirstCategoryId":"1085","ListUrlMain":"https://doi.org/10.1109/ISBP57705.2023.10061314","RegionNum":0,"RegionCategory":null,"ArticlePicture":[],"TitleCN":null,"AbstractTextCN":null,"PMCID":null,"EPubDate":"","PubModel":"","JCR":"","JCRName":"","Score":null,"Total":0}
引用次数: 0
Abstract
Heart disease is leading killers of human beings. Recognizing and categorizing Electrocardiogram (ECG) signals is crucial for early heart and cardiovascular disease prevention. A novel classification approach for ECG Arrhythmias based on Graph Bispectrum (GBispec) is proposed. First, the ECG signal is converted from the time domain to the Graph domain by using Graph Fourier Transform (GFT); Then, referring to the traditional bispectrum algorithm, the GFT results of ECG are converted into GBispec; Then, extract the graph features of Graph Integral Bispectrum (GIB), and use Deep Neural Networks(DNN) to process the GIB results. 4 different types of ECG signals are classified. Experiments results show that proposed method is effective in classification.