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 |
id |
ndltd-TW-098CCU05442053 |
---|---|
record_format |
oai_dc |
spelling |
ndltd-TW-098CCU054420532015-10-13T18:25:32Z http://ndltd.ncl.edu.tw/handle/42676652558894815641 Subband Decomposition Methods for two leads Electrocardiogram Beat Discrimination 以次頻帶分解法進行雙導程心電圖搏動辨識之研究 Fang-Tsen Liu 劉芳岑 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. Sung-Nien Yu 余松年 2010 學位論文 ; thesis 58 zh-TW |
collection |
NDLTD |
language |
zh-TW |
format |
Others
|
sources |
NDLTD |
description |
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.
|
author2 |
Sung-Nien Yu |
author_facet |
Sung-Nien Yu Fang-Tsen Liu 劉芳岑 |
author |
Fang-Tsen Liu 劉芳岑 |
spellingShingle |
Fang-Tsen Liu 劉芳岑 Subband Decomposition Methods for two leads Electrocardiogram Beat Discrimination |
author_sort |
Fang-Tsen Liu |
title |
Subband Decomposition Methods for two leads Electrocardiogram Beat Discrimination |
title_short |
Subband Decomposition Methods for two leads Electrocardiogram Beat Discrimination |
title_full |
Subband Decomposition Methods for two leads Electrocardiogram Beat Discrimination |
title_fullStr |
Subband Decomposition Methods for two leads Electrocardiogram Beat Discrimination |
title_full_unstemmed |
Subband Decomposition Methods for two leads Electrocardiogram Beat Discrimination |
title_sort |
subband decomposition methods for two leads electrocardiogram beat discrimination |
publishDate |
2010 |
url |
http://ndltd.ncl.edu.tw/handle/42676652558894815641 |
work_keys_str_mv |
AT fangtsenliu subbanddecompositionmethodsfortwoleadselectrocardiogrambeatdiscrimination AT liúfāngcén subbanddecompositionmethodsfortwoleadselectrocardiogrambeatdiscrimination AT fangtsenliu yǐcìpíndàifēnjiěfǎjìnxíngshuāngdǎochéngxīndiàntúbódòngbiànshízhīyánjiū AT liúfāngcén yǐcìpíndàifēnjiěfǎjìnxíngshuāngdǎochéngxīndiàntúbódòngbiànshízhīyánjiū |
_version_ |
1718032555935006720 |