Journal Article

·2008

Classification of heart arrthymias by using wavelet and merged wavelet packet transforms

Erkan Uslu YTU , Gökhan Bilgin YTU

Abstract

In this work efficiency of feature extraction methods based on linear wavelet transform and merged wavelet packets technique are evaluated relatively with different supervised classification methods. Experimental heart arrthymia data has been obtained from MIT-BIH arrthymia database. Total of 1200 training and 1200 test samples have been chosen equally for 6 classes from the database. For the purpose of increasing the accuracy with chosen datasets, mixed noises from different sources in the ECG signals are removed with signal processing methods. Support vector machines (SVM) and statistical neural networks (RBF, PNN and GRNN) are utilized for classification purpose. In the experimental results it has been observed that the best accuracy is accomplished by RBF kernel SVM, trained with any of the two mentioned feature extraction methods.

Keywords

Pattern recognition (psychology) Support vector machine Computer science Artificial intelligence Feature extraction Wavelet Wavelet packet decomposition Wavelet transform Kernel (algebra) Artificial neural network Mathematics

Subject Areas

ECG Monitoring and Analysis ·Cardiology and Cardiovascular Medicine ·Health Sciences
Fault Detection and Control Systems ·Control and Systems Engineering ·Physical Sciences
EEG and Brain-Computer Interfaces ·Cognitive Neuroscience ·Life Sciences

Citations by Year