Automatic arrhythmia detection using support vector machine based on discrete wavelet transform /
Ibrahim Hamed Ibrahim
Automatic arrhythmia detection using support vector machine based on discrete wavelet transform / الكشف الأتوماتيكى عن عدم إنتظام ضربات القلب بإستخدام مصنف آلى محدد مبنى على التحويل المتقطع المويجى Ibrahim Hamed Ibrahim ; Supervised Mohamed Emad Mousa Rasmy , Abd Allah Sayed Ahmed , Mohamed Ibrahim Ismail Owis - Cairo : Ibrahim Hamed Ibrahim , 2014 - 99 P. : charts , facsimiles ; 30cm
Thesis (M.Sc.) - Cairo University - Faculty of Engineering - Department of Systems and Biomedical Engineering
Arrhythmia is abnormality in the way electricity moves through the heart. The symptoms of arrhythmia are not present all the time; several examination hours of ECG records are needed. Even so, there is a high percentage of missing vital information. Automated arrhythmia detection of normal sinus rhythm and three types of arrhythmia (AF, VF, and SVT) was introduced by extracting the main features of the signal through DWT followed by PCA. These features were reduced through statistical analysis to be used as input to SVM that resulted in overall accuracy of 96.89%. The aim is to minimize the risk of missing vital information and to give physicians the confidence of making sound decisions with indistinct symptoms
Arrhythmia detection Principal component analysis Wavelet
Automatic arrhythmia detection using support vector machine based on discrete wavelet transform / الكشف الأتوماتيكى عن عدم إنتظام ضربات القلب بإستخدام مصنف آلى محدد مبنى على التحويل المتقطع المويجى Ibrahim Hamed Ibrahim ; Supervised Mohamed Emad Mousa Rasmy , Abd Allah Sayed Ahmed , Mohamed Ibrahim Ismail Owis - Cairo : Ibrahim Hamed Ibrahim , 2014 - 99 P. : charts , facsimiles ; 30cm
Thesis (M.Sc.) - Cairo University - Faculty of Engineering - Department of Systems and Biomedical Engineering
Arrhythmia is abnormality in the way electricity moves through the heart. The symptoms of arrhythmia are not present all the time; several examination hours of ECG records are needed. Even so, there is a high percentage of missing vital information. Automated arrhythmia detection of normal sinus rhythm and three types of arrhythmia (AF, VF, and SVT) was introduced by extracting the main features of the signal through DWT followed by PCA. These features were reduced through statistical analysis to be used as input to SVM that resulted in overall accuracy of 96.89%. The aim is to minimize the risk of missing vital information and to give physicians the confidence of making sound decisions with indistinct symptoms
Arrhythmia detection Principal component analysis Wavelet