{"title":"Identification of Cardiac Arrhythmias using Natural Resonance Complex Frequencies","authors":"Moustafa A. Bani-Hasan, Yasser M. Kadah, Fatma M. El-Hefnawi","country":null,"institution":"","volume":37,"journal":"International Journal of Biomedical and Biological Engineering","pagesStart":19,"pagesEnd":26,"ISSN":"1307-6892","URL":"https:\/\/publications.waset.org\/pdf\/5009","abstract":"An electrocardiogram (ECG) feature extraction system\r\nbased on the calculation of the complex resonance frequency\r\nemploying Prony-s method is developed. Prony-s method is applied\r\non five different classes of ECG signals- arrhythmia as a finite sum\r\nof exponentials depending on the signal-s poles and the resonant\r\ncomplex frequencies. Those poles and resonance frequencies of the\r\nECG signals- arrhythmia are evaluated for a large number of each\r\narrhythmia. The ECG signals of lead II (ML II) were taken from\r\nMIT-BIH database for five different types. These are the ventricular\r\ncouplet (VC), ventricular tachycardia (VT), ventricular bigeminy\r\n(VB), and ventricular fibrillation (VF) and the normal (NR). This\r\nnovel method can be extended to any number of arrhythmias.\r\nDifferent classification techniques were tried using neural networks\r\n(NN), K nearest neighbor (KNN), linear discriminant analysis (LDA)\r\nand multi-class support vector machine (MC-SVM).","references":null,"publisher":"World Academy of Science, Engineering and Technology","index":"Open Science Index 37, 2010"}