Note: Your custom schedule will not be saved unless you create a new account or login to an existing account.
| Paper: | MLSP-P2.9 |
| Session: | Bioinformatics and Biomedical Applications |
| Time: | Wednesday, May 19, 13:00 - 15:00 |
| Presentation: |
Poster |
| Topic: |
Machine Learning for Signal Processing: Signal detection, Pattern Recognition and Classification |
| Title: |
PATTERN RECOGNITION OF CARDIAC ARRHYTHMIAS BASED ON MULTIVARIATE AUTOREGRESSIVE MODELING |
| Authors: |
Dingfei Ge; Zhejiang University of Science and Technology | | |
| | Zhegen Zhang; Zhejiang University of Science and Technology | | |
| Abstract: |
Abstract-Computer-assisted automatic diagnosis will play an important role in diagnosis and treatment of critical ill patients.Multivariate autoregressive modeling (MAR) has been performed on two-lead ECG signals in this research. MAR coefficients and K-L transformation of MAR coefficients have been used as ECG features for classification. Five types of ECG signals were obtained from MIT-BIH database, namely normal sinus rhythm, atria premature contraction, premature ventricular contraction, ventricular tachycardia, and ventricular fibrillation. A quadratic discriminant function (QDF) based classification algorithm was employed in this study. The results show MAR coefficients produced slightly better results than K-L transformation of MAR coefficients. The accuracy of classification based on MAR coefficients was 96.6% to 99.3%.Key words: ECG signals, Multivariate Autoregressive Modeling, Quadratic discriminant function, Classification |
| |
| Back | |