Subband Decomposition Methods for two leads Electrocardiogram Beat Discrimination
碩士 === 國立中正大學 === 電機工程所 === 98 === Electrocardiogram (ECG) beat discrimination plays an important role in the clinical diagnosis of heart diseases. Although many ECG beat classification methods have been provided in the literature, there still leave room for improvement in view of different issues....
| Main Authors: | , |
|---|---|
| Other Authors: | |
| Format: | Others |
| Language: | zh-TW |
| Published: |
2010
|
| Online Access: | http://ndltd.ncl.edu.tw/handle/42676652558894815641 |
| Summary: | 碩士 === 國立中正大學 === 電機工程所 === 98 === Electrocardiogram (ECG) beat discrimination plays an important role in the clinical diagnosis of heart diseases. Although many ECG beat classification methods have been provided in the literature, there still leave room for improvement in view of different issues. The purpose of this study is to add the second lead to the system and study the influence on the recognition rates and the ability to tolerate noises.
The discrete wavelet transformation is employed to decompose the ECG signals into different subband components in the first stage, and higher order statistics is recruited to accompany with the discrete wavelet decomposition to characterize the ECG signals as an attempt to elevate the noise-resistibility of heartbeat discrimination. A feed –forward back-propagation neural network (FFBNN) is employed as classifier. We select multiple beat types form records for study. When compared with the system that uses one the first lead, the second lead enhances the recognition rate from 97.5% to 98.1%.
We also study of the ability of the two-lead system in resisting noise of different kinds. More than 97.4% accuracy than be retained with the two-lead system even when the SNR is decreases to 10 dB. The results show that the second lead ECG’s information used in the proposed method does enhance the noise-tolerant.
|
|---|