期刊文献+
任意字段
题名或关键词
题名
关键词
文摘
作者
第一作者
机构
刊名
分类号
参考文献
作者简介
基金资助
栏目信息

基于最大散度的特征搜索算法用于心搏分类的研究 被引量：1

ECG Pattern Classification by Feature Searching Algorithm Based on Maximal Divergence
下载PDF
导出
摘要 在对心电图进行离散小波变换获得特征空间的基础上,提出了基于最大散度的特征搜索算法。对特征空间进行搜索得到不同维数下的优化特征组合,通过研究这些优化特征组合的散度值随维数的变化趋势,最终确定特征向量的特征构成,并以此特征向量训练BP神经网络。取自MIT-BIH数据库的四类心电图(正常心搏、左束支传导阻滞心搏、右束支传导阻滞心搏和起搏心搏)的分类正确率达到93.9%,检出率较高。 This paper presents a method of using feature searching algorithm based on maximal divergence value to get the optimized feature combinations at different dimensions from feature space. Feature space is obtained through wavelet transform on ECG beat. Then the feature vector is determined by analyzing the changes of divergence value of those optimized feature combinations along with the dimensions. BP artificial neural network is trained by the feature vector and four types of ECG beats（normal beat, left bundle branch block beat, right bundle branch block beat and paced beat） obtained from MIT-BIH database are classified with a success of 93.9%.
作者 曹玉珍 范增飞
机构地区 天津大学精密仪器与光电子工程学院
出处 《生物医学工程学杂志》 EI CAS CSCD 北大核心 2008年第1期53-56,共4页 Journal of Biomedical Engineering
关键词 心电图分类 神经网络 小波变换 特征提取 散度 ECG classification Neural network Wavelet transform Feature extraction Divergence
分类号 R318 [医药卫生—生物医学工程]
  • 相关文献

参考文献10

  • 1Maglaveras N, Stamkopoulos T, Diamantaras K, etal. ECG pattern recognition and classification using non-linear transformations and neural networks:a review. Int J Med Inform, 1998; 52:191
  • 2Silipo R, Marchesi C. Artificial neural networks for automatic ECG analysis. IEEE Trans Signal Processing, 1998; 46(5) : 1417
  • 3Dokur Z, Olmez T, Yazgan E. Comparison of discrete wavelet and Fourier transforms for ECG beat classification. Electron Lett, 1999; 35(18) : 1502
  • 4Minami K, Nakajima H, Toyosima T. Real-time discrimination of ventricular tachyarrhythmia with fourier transform neural network. IEEE Trans. Biomed Eng, 1999; 46(2) :179
  • 5Dokur Z, Olmez T. ECG beat classification by a novel hybrid neural network. Comnputer Methods and Program in Biomedicine, 2001 ; 66 : 167
  • 6Guler i,Ubeyli ED. ECG beat classifier designed by combined neural network model. Pattern Recognition, 2005 ; 38 : 199
  • 7Addison PS, Watson JN, Clegg GR, et al. Evaluating arrhythmias in ECG signals using wavelet transforms. IEEE Eng Med Biol, 2000; 19(5):104
  • 8Saxena SC, Kumar V, Hamde ST. Feature extraction from ECG signals using wavelet transforms for disease diagnostics. Int J Systems Sci, 2002; 33(13):1073
  • 9葛丁飞,李时辉.基于ARMA模型的ECG分类和压缩[J].浙江科技学院学报,2004,16(1):7-13. 被引量：6
  • 10边肇棋,张学工.模式识别.第二版.北京:清华大学出版社,2000:202-204

二级参考文献18

  • 1[1]Caswell S A, Kluge K S, Chiang C M J. Pattern recognition of cardiac arrhythmias using two intracardiac channels[R]. Proc Comp Cardiol, 1993.181-184.
  • 2[2]Zhou S H, Rautaharju P M, Calhoun H P. Selection of a reduced set of parameters for classification of ventricular conduction defects by cluster analysis[R]. Proc Comp Cardiol, 1993.879-882.
  • 3[3]Minami K C, Nakajima H, Toyoshima T. Real-time discrimination of ventricular tachyarrythmia with fourier-transform neural network[J]. IEEE Trans Biomed Eng, 1999,46:179-185.
  • 4[4]Afonoso V X, Tompkins W J. Detecting ventricular fibrillation: Selecting the appropriate time-frequency analysis tool for the application[J]. IEEE Eng Med Biol Mag, 1995,14:152-159.
  • 5[5]Zhang X S, Zhu Y S, Thakor N V, et al. Detecting ventricular tachycardia and fibrillation by complexity measure[J]. IEEE Trans Biomed Eng, 1999, 46:548-555.
  • 6[6]Chen S W. Two-stage discrimination of cardiac arrhythmias using a total least squares-based prony modeling algorithm[J]. IEEE Trans Biomed Eng, 2000, 47:1317-1326.
  • 7[7]Arnold M, Miltner W H R, Witte H. Adaptive AR modeling of nonstationary time series by means of Kalman filtering[J]. IEEE Trans Biomed Eng, 1998,45:553-562.
  • 8[8]Ham F M, Han S. Classification of cardiac arrhythmias using fuzzy ARTMAP[J].IEEE Trans Biomed Eng, 1996,43:425-430.
  • 9[9]Duda R O, Hart P E. Pattern Classification[M]. New York: Wiley-Interscience Publication, 2001.
  • 10[10]Jalaleddine S M S, Hutchens C G, Strattan R D, et al. ECG data compression techniques-a unified approach[J]. IEEE Trans on BME, 1990,37:329-343.

共引文献5

同被引文献9

  • 1冯俊,邱雅竹,莫智文.基于改进射线拟合法的多导联心电图神经网络分类系统[J].生物医学工程学杂志,2006,23(5):956-959. 被引量：2
  • 2Daniel D L,Seung H S.Learning the Parts of Objects by Non-negative Matrix Factorization[J].Nature,1999,401(6755):788-791.
  • 3Gomes P R,Filomena O,Soares J H.ECG Data-acquisition andClassification System by Using Wavelet-domain Hidden MarkovModels[C]//Proc.of International Conference of IEEE Engineeringin Medicine and Biology Society.Buenos Aires,Argentina:[s.n.],2010:4670-4673.
  • 4Martis R J,Chakraborty C,Ray A K.A Two-stage Mechanism forRegistration and Classification of ECG Using Gaussian MixtureModel[J].Pattern Recognition,2009,42(11):2979-2988.
  • 5Zhang Leigang,Hu Peng,Yu Chenglong.An Approach for ECGClassification Based on Wavelet Feature Extraction and DecisionTree[C]//Proc.of 2010 International Conference on WirelessCommunications and Signal Processing.Suzhou,China:[s.n.],2010:1-4.
  • 6Yua Sung-Nien,Chou Kuan-To.Selection of SignificantIndependent Components for ECG Beat Classification[J].ExpertSystems with Applications,2009,36(2):2088-2096.
  • 7He Lin,Hou Wensheng,Zhen Xiaolin.Recognition of ECGPatterns Using Artificial Neural Network[C]//Proc.of the 6thInternational Conference on Intelligent Systems Design andApplications.Jinan,China:[s.n.],2006:477-481.
  • 8龙泓琳,皮亦鸣,曹宗杰.基于非负矩阵分解的SAR图像目标识别[J].电子学报,2010,38(6):1425-1429. 被引量：25
  • 9王丽苹,董军.心电图模式分类方法研究进展与分析[J].中国生物医学工程学报,2010,29(6):916-925. 被引量：15

引证文献1

二级引证文献3

生物医学工程学杂志
2008年 第1期

相关作者

内容加载中请稍等...

相关机构

内容加载中请稍等...

相关主题

内容加载中请稍等...

浏览历史

内容加载中请稍等...
;
使用帮助 返回顶部