Pratik Deb, Mohammad Nooruddin, Md. Shajahan Badshah
{"title":"Detection of Abnormal Electrocardiogram (ECG) Using Wavelet Decomposition and Support Vector Machine (SVM)","authors":"Pratik Deb, Mohammad Nooruddin, Md. Shajahan Badshah","doi":"10.1109/ICASERT.2019.8934588","DOIUrl":null,"url":null,"abstract":"Electrocardiogram (ECG) is a graphical representation of the electrical activity of the heart which is obtained by placing various electrodes on some specific positions of the body surface of the subject. Abnormalities in the ECG signal of a patient may indicate cardiac diseases that need to be attended by physicians on an urgent basis. Hence, it is necessary to detect an abnormal ECG for the betterment of the patient. Such a method to classify ECG signals whether they are normal or abnormal is developed in this work. Angina, Bundle Branch Block, Cardiomyopathy Heart Failure, Dysrhythmia, Myocardial Hypertrophy, Myocardial Infarction, Myocarditis, Valvular Heart Disease: all these cardiac conditions have been classified as abnormal ECG signal in our work. First, statistical features like skewness, kurtosis, standard deviation of detail and approximation coefficients of the Daubechies wavelet (db10) of order 5 for a number of abnormal and normal ECG signals obtained in the feature extraction stage. Secondly, Support Vector Machine (SVM) was used for classification which was trained by the features extracted in the first stage. Finally, the accuracy, sensitivity, specificity of this method was checked by testing the SVM with 36 signals obtained from MIT-BIH Normal Sinus Rhythm Database and 36 signals from PTB Diagnostic ECG Database which yielded an accuracy, sensitivity, specificity 98.61%, 97.37%, 97.22% respectively.","PeriodicalId":6613,"journal":{"name":"2019 1st International Conference on Advances in Science, Engineering and Robotics Technology (ICASERT)","volume":"91 1","pages":"1-8"},"PeriodicalIF":0.0000,"publicationDate":"2019-05-01","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":"1","resultStr":null,"platform":"Semanticscholar","paperid":null,"PeriodicalName":"2019 1st International Conference on Advances in Science, Engineering and Robotics Technology (ICASERT)","FirstCategoryId":"1085","ListUrlMain":"https://doi.org/10.1109/ICASERT.2019.8934588","RegionNum":0,"RegionCategory":null,"ArticlePicture":[],"TitleCN":null,"AbstractTextCN":null,"PMCID":null,"EPubDate":"","PubModel":"","JCR":"","JCRName":"","Score":null,"Total":0}
引用次数: 1
Abstract
Electrocardiogram (ECG) is a graphical representation of the electrical activity of the heart which is obtained by placing various electrodes on some specific positions of the body surface of the subject. Abnormalities in the ECG signal of a patient may indicate cardiac diseases that need to be attended by physicians on an urgent basis. Hence, it is necessary to detect an abnormal ECG for the betterment of the patient. Such a method to classify ECG signals whether they are normal or abnormal is developed in this work. Angina, Bundle Branch Block, Cardiomyopathy Heart Failure, Dysrhythmia, Myocardial Hypertrophy, Myocardial Infarction, Myocarditis, Valvular Heart Disease: all these cardiac conditions have been classified as abnormal ECG signal in our work. First, statistical features like skewness, kurtosis, standard deviation of detail and approximation coefficients of the Daubechies wavelet (db10) of order 5 for a number of abnormal and normal ECG signals obtained in the feature extraction stage. Secondly, Support Vector Machine (SVM) was used for classification which was trained by the features extracted in the first stage. Finally, the accuracy, sensitivity, specificity of this method was checked by testing the SVM with 36 signals obtained from MIT-BIH Normal Sinus Rhythm Database and 36 signals from PTB Diagnostic ECG Database which yielded an accuracy, sensitivity, specificity 98.61%, 97.37%, 97.22% respectively.