|
KMID : 1137820090300040294
|
|
의공학회지
2009 Volume.30 No. 4 p.294 ~ p.305
|
|
|
An Adaptive Classification Algorithm of Premature Ventricular Beat With Optimization of Wavelet Parameterization
|
|
Kim Jin-Kwon
Kang Dae-Hoon
Lee Myoung-Ho
|
|
|
Abstract
|
|
|
|
The bio signals essentially have different characteristics in each person. And the main purpose of automatic diagnosis algorithm based on bio signals focuses on discriminating differences of abnormal state from personal differences. In this paper, we propose automatic ECG diagnosis algorithm which discriminates normal heart beats from premature ventricular contraction using optimization of wavelet parameterization to solve that problem. The proposed algorithm optimizes wavelet parameter to let energy of signal be concentrated on specific scale band. We can reduce the personal differences and consequently highlight the differences coming from arrhythmia via this process. The proposed algorithm using ELM as a classifier show high discrimination performance between normal beat and PVC. From the experimental results on MIT-BIH arrhythmia database the performances of the proposed algorithm are 98.1% in accuracy, 93.0% in sensitivity, 96.4% in positive predictivity, and 0.8% in false positive rate. This results are similar or higher then results of existing researches in spite of small human intervention.
|
|
|
KEYWORD
|
|
|
Premature Ventricular Beat, Wavelet Parameterization, arrhythmia classification, ECG
|
|
|
FullTexts / Linksout information
|
|
|
|
|
|
Listed journal information
|
|
 
|