ECG T Wave Detector Based on Neural Network Improved by Genetic Algorithms. Yu, S., C., Hu, Y., Yu, G., X., Jin, X., L., Zhang, L., N., & Shao, T., J. 2010 Second WRI Global Congress on Intelligent Systems, 1:355-358, 2010.
Paper abstract bibtex In order to improve the detection rate of T wave, and to solve the problem that the back propagate neural network (BPNN) is invalid when these initial weight and threshold values of BP neural network are chosen impertinently (Objective), Genetic Algorithms (GA)’s characteristic of getting whole optimization value was combined with BP’s characteristic of getting local precision value with gradient method. After getting an approximation of whole optimization value of weight and threshold values of BP NN by GA, the approximation was used as first parameter of BP neural network, to train (educate) the BPNN again (in other words, learning). The educated BPNN was used to recognize T wave of electrocardiogram (ECG). In order to improve the detection rate of T wave ,making full use of the character that multi-scales changing rules of Wavelet Transform (WT)’s mould max value pairs can indicate signal break points, combining with body physiology synthesis strategy practice, T wave in ECG signal was detected. At the same time, with the help of the educated BP neural network, T wave was confirmed (Methods). Experiment results shown that this method was useful and applicable, and the detection right rate of T wave was above 98% for the MIT database (Results). It is concluded that the combination (WT, GA, BPNN) makes BP neural network to recognition T wave better (Conclusions).
@article{
title = {ECG T Wave Detector Based on Neural Network Improved by Genetic Algorithms},
type = {article},
year = {2010},
identifiers = {[object Object]},
keywords = {T wave detection,back propagation neural network,genetic algorithms,global optimization value,wavelet transform},
pages = {355-358},
volume = {1},
id = {5df5779f-bbca-3bb2-84ed-2f904bc2cb86},
created = {2015-04-30T11:14:38.000Z},
file_attached = {true},
profile_id = {5e73f9af-1f10-3a70-a285-d3fbb699efe2},
group_id = {e134fb94-8118-3ebe-b82d-bfbf0a8ae633},
last_modified = {2015-04-30T12:41:31.000Z},
read = {false},
starred = {false},
authored = {false},
confirmed = {true},
hidden = {false},
abstract = {In order to improve the detection rate of T wave, and to solve the problem that the back propagate neural network (BPNN) is invalid when these initial weight and threshold values of BP neural network are chosen impertinently (Objective), Genetic Algorithms (GA)’s characteristic of getting whole optimization value was combined with BP’s characteristic of getting local precision value with gradient method. After getting an approximation of whole optimization value of weight and threshold values of BP NN by GA, the approximation was used as first parameter of BP neural network, to train (educate) the BPNN again (in other words, learning). The educated BPNN was used to recognize T wave of electrocardiogram (ECG). In order to improve the detection rate of T wave ,making full use of the character that multi-scales changing rules of Wavelet Transform (WT)’s mould max value pairs can indicate signal break points, combining with body physiology synthesis strategy practice, T wave in ECG signal was detected. At the same time, with the help of the educated BP neural network, T wave was confirmed (Methods). Experiment results shown that this method was useful and applicable, and the detection right rate of T wave was above 98% for the MIT database (Results). It is concluded that the combination (WT, GA, BPNN) makes BP neural network to recognition T wave better (Conclusions).},
bibtype = {article},
author = {Yu, Sheng Chen and Hu, Ying and Yu, Gui Xian and Jin, Xu Ling and Zhang, Li Nang and Shao, Tie Jun},
journal = {2010 Second WRI Global Congress on Intelligent Systems}
}
Downloads: 0
{"_id":"TvTmxGYgLtpzuriXe","bibbaseid":"yu-hu-yu-jin-zhang-shao-ecgtwavedetectorbasedonneuralnetworkimprovedbygeneticalgorithms-2010","downloads":0,"creationDate":"2016-05-08T13:37:39.639Z","title":"ECG T Wave Detector Based on Neural Network Improved by Genetic Algorithms","author_short":["Yu, S., C.","Hu, Y.","Yu, G., X.","Jin, X., L.","Zhang, L., N.","Shao, T., J."],"year":2010,"bibtype":"article","biburl":null,"bibdata":{"title":"ECG T Wave Detector Based on Neural Network Improved by Genetic Algorithms","type":"article","year":"2010","identifiers":"[object Object]","keywords":"T wave detection,back propagation neural network,genetic algorithms,global optimization value,wavelet transform","pages":"355-358","volume":"1","id":"5df5779f-bbca-3bb2-84ed-2f904bc2cb86","created":"2015-04-30T11:14:38.000Z","file_attached":"true","profile_id":"5e73f9af-1f10-3a70-a285-d3fbb699efe2","group_id":"e134fb94-8118-3ebe-b82d-bfbf0a8ae633","last_modified":"2015-04-30T12:41:31.000Z","read":false,"starred":false,"authored":false,"confirmed":"true","hidden":false,"abstract":"In order to improve the detection rate of T wave, and to solve the problem that the back propagate neural network (BPNN) is invalid when these initial weight and threshold values of BP neural network are chosen impertinently (Objective), Genetic Algorithms (GA)’s characteristic of getting whole optimization value was combined with BP’s characteristic of getting local precision value with gradient method. After getting an approximation of whole optimization value of weight and threshold values of BP NN by GA, the approximation was used as first parameter of BP neural network, to train (educate) the BPNN again (in other words, learning). The educated BPNN was used to recognize T wave of electrocardiogram (ECG). In order to improve the detection rate of T wave ,making full use of the character that multi-scales changing rules of Wavelet Transform (WT)’s mould max value pairs can indicate signal break points, combining with body physiology synthesis strategy practice, T wave in ECG signal was detected. At the same time, with the help of the educated BP neural network, T wave was confirmed (Methods). Experiment results shown that this method was useful and applicable, and the detection right rate of T wave was above 98% for the MIT database (Results). It is concluded that the combination (WT, GA, BPNN) makes BP neural network to recognition T wave better (Conclusions).","bibtype":"article","author":"Yu, Sheng Chen and Hu, Ying and Yu, Gui Xian and Jin, Xu Ling and Zhang, Li Nang and Shao, Tie Jun","journal":"2010 Second WRI Global Congress on Intelligent Systems","bibtex":"@article{\n title = {ECG T Wave Detector Based on Neural Network Improved by Genetic Algorithms},\n type = {article},\n year = {2010},\n identifiers = {[object Object]},\n keywords = {T wave detection,back propagation neural network,genetic algorithms,global optimization value,wavelet transform},\n pages = {355-358},\n volume = {1},\n id = {5df5779f-bbca-3bb2-84ed-2f904bc2cb86},\n created = {2015-04-30T11:14:38.000Z},\n file_attached = {true},\n profile_id = {5e73f9af-1f10-3a70-a285-d3fbb699efe2},\n group_id = {e134fb94-8118-3ebe-b82d-bfbf0a8ae633},\n last_modified = {2015-04-30T12:41:31.000Z},\n read = {false},\n starred = {false},\n authored = {false},\n confirmed = {true},\n hidden = {false},\n abstract = {In order to improve the detection rate of T wave, and to solve the problem that the back propagate neural network (BPNN) is invalid when these initial weight and threshold values of BP neural network are chosen impertinently (Objective), Genetic Algorithms (GA)’s characteristic of getting whole optimization value was combined with BP’s characteristic of getting local precision value with gradient method. After getting an approximation of whole optimization value of weight and threshold values of BP NN by GA, the approximation was used as first parameter of BP neural network, to train (educate) the BPNN again (in other words, learning). The educated BPNN was used to recognize T wave of electrocardiogram (ECG). In order to improve the detection rate of T wave ,making full use of the character that multi-scales changing rules of Wavelet Transform (WT)’s mould max value pairs can indicate signal break points, combining with body physiology synthesis strategy practice, T wave in ECG signal was detected. At the same time, with the help of the educated BP neural network, T wave was confirmed (Methods). Experiment results shown that this method was useful and applicable, and the detection right rate of T wave was above 98% for the MIT database (Results). It is concluded that the combination (WT, GA, BPNN) makes BP neural network to recognition T wave better (Conclusions).},\n bibtype = {article},\n author = {Yu, Sheng Chen and Hu, Ying and Yu, Gui Xian and Jin, Xu Ling and Zhang, Li Nang and Shao, Tie Jun},\n journal = {2010 Second WRI Global Congress on Intelligent Systems}\n}","author_short":["Yu, S., C.","Hu, Y.","Yu, G., X.","Jin, X., L.","Zhang, L., N.","Shao, T., J."],"urls":{"Paper":"http://bibbase.org/service/mendeley/5e73f9af-1f10-3a70-a285-d3fbb699efe2/file/13972485-13fc-36c5-5531-81b610920608/2010-ECG_T_Wave_Detector_Based_on_Neural_Network_Improved_by_Genetic_Algorithms.pdf.pdf"},"bibbaseid":"yu-hu-yu-jin-zhang-shao-ecgtwavedetectorbasedonneuralnetworkimprovedbygeneticalgorithms-2010","role":"author","keyword":["T wave detection","back propagation neural network","genetic algorithms","global optimization value","wavelet transform"],"downloads":0},"search_terms":["ecg","wave","detector","based","neural","network","improved","genetic","algorithms","yu","hu","yu","jin","zhang","shao"],"keywords":["t wave detection","back propagation neural network","genetic algorithms","global optimization value","wavelet transform"],"authorIDs":[]}