心电信号智能分析关键技术研究
摘要
伴随着人们生活水平的逐步提高，人们的健康意识不断增强；而现今心脏病的发病率也在逐年升高，已严重地危害了人类的生存和健康。但由于心血管疾病的发病时期不规律，且发病现象较隐蔽；因此，人们试图通过各种方式来提前预防和治疗心血管疾病比较困难。而院外监护、初步诊断、积极预防与及时治疗是行之有效的心脏疾病处理手段，这也对研究心电信号分析、诊断技术及心电监护产品提出了更高的要求。
本文以珠海市高新技术领域科技攻关及高新技术产业化项目“院外多生理参数监护诊断系统”（2010B020102021）为背景。依据项目的研究内容，针对目前心电信号处理、分析和智能诊断算法中存在的不足，就心电信号的预处理（去噪）、波形检测、波形特征向量的选择与提取以及波形自动分类等关键技术进行研究。针对算法面向心电监护仪等硬件应用平台移植的关键技术也做了相应的探讨。旨在提高计算机智能分析的准确率和实用性，提高异常心电波形自动分类的精度和性能，这对于加快国内心电监护医疗器械的研制，取得具有自主知识产权的心电信号智能分析核心技术，提高心电智能监护的质量，普及心电智能监护的应用都具有非常重要的现实意义和很好的经济效益。
本文对心电信号智能分析关键技术的研究取得了一定的成果，主要工作集中在：
1、心电信号预处理（去噪）算法的研究
充分研究了心电信号中噪声的特性。依据小波去噪原理，构造了一种基于软、硬阈值之间的新阈值函数；构造了一种加权阈值收缩函数，并提出了基于两种新阈值函数的心电信号去噪算法。利用MIT-BIH数据库对两种去噪方法进行了实验，结果表明，两种方法都比以往小波阈值去噪法在心电信号去噪的效果上有所改善，并且提出的基于加权阈值收缩去噪法，可以更好地保留心电信号P、T波形的细节特征，满足心电信号波形特征识别的需要。
2、心电信号波形特征识别算法的研究
提出了基于连续小波变换的心电信号QRS波识别算法。该算法采用高斯函数一阶导数作为小波基函数，利用考察小波变换相应层次中的模极大值对位置作为搜索QRS波中R波顶点的范围；根据R波顶点位置，结合平均心电周期，提出了一种P、T波搜索窗口宽度自适应方法，在此窗口中利用原信号的差分值，确定P、T波形的关键点。该算法对QRS波和P、T波各关键点的检出准确率较以往算法有所提高。
3、面向硬件实现心电信号处理和分析快速算法的VLSI实现研究
提出了基于DB4小波提升的心电信号处理和识别快速算法。该算法利用小波提升速度快的特性，使算法整体执行速度大大提高。对于算法向硬件平台移植的关键难点DB4小波提升的VLSI实现问题进行了研究，提出了利用FPGA实现DB4小波提升分解和重构的方案，通过实验验证了以上算法的有效性和方案的可行性。
4、异常心电信号分类算法的研究
提出了一种对平均心电周期长度具有自适应性的心电波形向量提取算法，提出了一种利用逻辑判断提取正常心电波形的判断依据，并提出了一种将逻辑判断（Logic）、聚类（Clustering）和模糊聚类（FCM）三者结合对异常心电实现准确聚类的算法（LCFCM）。算法对存在个体差异的心电信号具有很好的适应性，依据提取的心电向量波形进行聚类和模糊聚类分析，保证了算法对象信息的完整性，使算法整体具有很好的准确性。最后利用MIT-BIH数据库作为样本进行实验，LCFCM算法对异常心率分类的准确率达到了93%。
With the gradual improvement of people's living standard, people have becomemore conscious about their health. The incidence of heart disease also increases year byyear, which seriously endangers human health and survival. The incidence ofcardiovascular disease does not occur regularly. And it is not easy to notice theincidence of the phenomenon. As a result, it is very difficult for people to make theearly prevention and treatment of cardiovascular disease. And the effective heartdisease treatments such as monitoring outside hospital, primary diagnosis, activeprevention and the timely treatment have higher demand toward the study on ECGsignal analysis, the diagnostic techniques and ECG monitoring products.
Multiple Physiological Parameter Monitoring and Diagnostic Systems Outside theHospital （2010B020102021）is one of the science research projects and high-techindustrialization projects in Zhu Hai high-tech field of science and technology. In thecontext, based on the research content of this project, as far as the weakness of ECGsignal processing, analysis and the intelligent diagnosis algorithm is concerned, thisthesis makes the study on the key technology of ECG signal preprocessing (denoising),waveform detection, the selection and extraction of the waveform feature vector andthe waveform automatically classification. This thesis also makes the relevant study onthe key technology of the transplantation for the hardware platform of thealgorithm-oriented ECG application. It aims at improving the accuracy andpracticability of computer intelligence analysis. It also aims at improving the accuracyand performance of abnormal ECG waveform automatic classification. This can speedup the development of ECG medical devices in China and make intelligent analysis ofECG signals with independent intellectual property core technology. In addition, thiscan improve the quality of ECG intelligent guardianship and make the application ofECG intelligent guardianship become universal. The study in this thesis has veryimportant significance and can bring enormous economic benefits.
The research on key technology of ECG signal intelligent analysis in this thesishas made some achievements. The achievements are focused on the following aspects.
1. The Study on the Algorithm of ECG Signal Preprocessing (Denoising)
After making research on the characteristics of noise in ECG signal, based onwavelet denoising principle, a new threshold function based between the soft and hardthreshold is created. And a weighted threshold shrinkage function is created. Inaddition, this thesis puts forward an ECG signal denoising algorithm based on two newthreshold functions. The two denoising methods are used to make experiments on thetypical data in MIT-BIH Data Base. The experimental results indicate that, comparedwith the previous wavelet threshold denoising methods, the two methods improve a lotin the effect of denoising. The proposed based on weighted threshold shrinkagedenoising method can preserve much more details of the waveform of P wave and Twave in ECG signal, which is much easier to satisfy the need of recognizing thefeatures of ECG signal waveform.
2. The Study on the Identification Algorithm of Features of ECG SignalWaveform
The QRS wave identification algorithm based on the continuous wavelettransform is proposed. This algorithm takes the first derivative of Gaussian function asthe wavelet basis function. The relative position of the modulus maximum is used todefine the range of searching the R wave vertex in QRS complex, by examining thewavelet transform in the corresponding levels. According to the position of R wavevertex and the average ECG cycle, a window width adaptive method of searching for Rand P wave is proposed. In this window, the differential values of the original signalsare used to identify the key points of the waveform of P and T wave. The detection rateof the key points in QRS complex, P wave and T wave improves a lot than the previousalgorithms.
3. The Study on the Hardware Oriented Implementation of ECG SignalProcessing, Analysis of the Fast Algorithm and VLSI Implementation
The fast algorithm of ECG signal processing and identification based on DB4wavelet lifting is created. The algorithm uses the wavelet lifting's characteristic ofpossessing fast speed, and greatly improves the algorithm's overall execution speed.After making the study on DB4wavelet lifting VLSI implementation issues, as far asthe key technical points of the algorithm's transplantation toward the hardwareplatform are concerned, the program of the lifting decomposition and reconstruction ofDB4wavelet by using FPGA is proposed. The effectiveness and the above algorithm and the feasibility of realizing FPGA program are proved by the experiments.
4. The Study on the Sorting Algorithm of the Abnormal ECG Signal
The ECG waveform vector extraction algorithm which is self adaptive to theaverage length of ECG cycle is created. The judgment of using the logical judgment toexact the normal ECG waveform is given. Accordingly, LCFCM algorithm whichcombines logical judgment, cluster analysis and fuzzy clustering together to realize theaccurate clustering of the abnormal ECG heart rate is proposed. The algorithm has agood adaptability to the ECG signal with individual differences. And the clusteranalysis and fuzzy clustering analysis based on the extracted ECG vector waveform canguarantee the integrity of algorithm's object information, which makes the wholealgorithm become very accurate. Finally, the experiment by using MIT-BIH databaseas the sample is made. The accuracy rate of the classification of the abnormal heart rateby LCFCM algorithm reaches93%.
本文以珠海市高新技术领域科技攻关及高新技术产业化项目“院外多生理参数监护诊断系统”（2010B020102021）为背景。依据项目的研究内容，针对目前心电信号处理、分析和智能诊断算法中存在的不足，就心电信号的预处理（去噪）、波形检测、波形特征向量的选择与提取以及波形自动分类等关键技术进行研究。针对算法面向心电监护仪等硬件应用平台移植的关键技术也做了相应的探讨。旨在提高计算机智能分析的准确率和实用性，提高异常心电波形自动分类的精度和性能，这对于加快国内心电监护医疗器械的研制，取得具有自主知识产权的心电信号智能分析核心技术，提高心电智能监护的质量，普及心电智能监护的应用都具有非常重要的现实意义和很好的经济效益。
本文对心电信号智能分析关键技术的研究取得了一定的成果，主要工作集中在：
1、心电信号预处理（去噪）算法的研究
充分研究了心电信号中噪声的特性。依据小波去噪原理，构造了一种基于软、硬阈值之间的新阈值函数；构造了一种加权阈值收缩函数，并提出了基于两种新阈值函数的心电信号去噪算法。利用MIT-BIH数据库对两种去噪方法进行了实验，结果表明，两种方法都比以往小波阈值去噪法在心电信号去噪的效果上有所改善，并且提出的基于加权阈值收缩去噪法，可以更好地保留心电信号P、T波形的细节特征，满足心电信号波形特征识别的需要。
2、心电信号波形特征识别算法的研究
提出了基于连续小波变换的心电信号QRS波识别算法。该算法采用高斯函数一阶导数作为小波基函数，利用考察小波变换相应层次中的模极大值对位置作为搜索QRS波中R波顶点的范围；根据R波顶点位置，结合平均心电周期，提出了一种P、T波搜索窗口宽度自适应方法，在此窗口中利用原信号的差分值，确定P、T波形的关键点。该算法对QRS波和P、T波各关键点的检出准确率较以往算法有所提高。
3、面向硬件实现心电信号处理和分析快速算法的VLSI实现研究
提出了基于DB4小波提升的心电信号处理和识别快速算法。该算法利用小波提升速度快的特性，使算法整体执行速度大大提高。对于算法向硬件平台移植的关键难点DB4小波提升的VLSI实现问题进行了研究，提出了利用FPGA实现DB4小波提升分解和重构的方案，通过实验验证了以上算法的有效性和方案的可行性。
4、异常心电信号分类算法的研究
提出了一种对平均心电周期长度具有自适应性的心电波形向量提取算法，提出了一种利用逻辑判断提取正常心电波形的判断依据，并提出了一种将逻辑判断（Logic）、聚类（Clustering）和模糊聚类（FCM）三者结合对异常心电实现准确聚类的算法（LCFCM）。算法对存在个体差异的心电信号具有很好的适应性，依据提取的心电向量波形进行聚类和模糊聚类分析，保证了算法对象信息的完整性，使算法整体具有很好的准确性。最后利用MIT-BIH数据库作为样本进行实验，LCFCM算法对异常心率分类的准确率达到了93%。
With the gradual improvement of people's living standard, people have becomemore conscious about their health. The incidence of heart disease also increases year byyear, which seriously endangers human health and survival. The incidence ofcardiovascular disease does not occur regularly. And it is not easy to notice theincidence of the phenomenon. As a result, it is very difficult for people to make theearly prevention and treatment of cardiovascular disease. And the effective heartdisease treatments such as monitoring outside hospital, primary diagnosis, activeprevention and the timely treatment have higher demand toward the study on ECGsignal analysis, the diagnostic techniques and ECG monitoring products.
Multiple Physiological Parameter Monitoring and Diagnostic Systems Outside theHospital （2010B020102021）is one of the science research projects and high-techindustrialization projects in Zhu Hai high-tech field of science and technology. In thecontext, based on the research content of this project, as far as the weakness of ECGsignal processing, analysis and the intelligent diagnosis algorithm is concerned, thisthesis makes the study on the key technology of ECG signal preprocessing (denoising),waveform detection, the selection and extraction of the waveform feature vector andthe waveform automatically classification. This thesis also makes the relevant study onthe key technology of the transplantation for the hardware platform of thealgorithm-oriented ECG application. It aims at improving the accuracy andpracticability of computer intelligence analysis. It also aims at improving the accuracyand performance of abnormal ECG waveform automatic classification. This can speedup the development of ECG medical devices in China and make intelligent analysis ofECG signals with independent intellectual property core technology. In addition, thiscan improve the quality of ECG intelligent guardianship and make the application ofECG intelligent guardianship become universal. The study in this thesis has veryimportant significance and can bring enormous economic benefits.
The research on key technology of ECG signal intelligent analysis in this thesishas made some achievements. The achievements are focused on the following aspects.
1. The Study on the Algorithm of ECG Signal Preprocessing (Denoising)
After making research on the characteristics of noise in ECG signal, based onwavelet denoising principle, a new threshold function based between the soft and hardthreshold is created. And a weighted threshold shrinkage function is created. Inaddition, this thesis puts forward an ECG signal denoising algorithm based on two newthreshold functions. The two denoising methods are used to make experiments on thetypical data in MIT-BIH Data Base. The experimental results indicate that, comparedwith the previous wavelet threshold denoising methods, the two methods improve a lotin the effect of denoising. The proposed based on weighted threshold shrinkagedenoising method can preserve much more details of the waveform of P wave and Twave in ECG signal, which is much easier to satisfy the need of recognizing thefeatures of ECG signal waveform.
2. The Study on the Identification Algorithm of Features of ECG SignalWaveform
The QRS wave identification algorithm based on the continuous wavelettransform is proposed. This algorithm takes the first derivative of Gaussian function asthe wavelet basis function. The relative position of the modulus maximum is used todefine the range of searching the R wave vertex in QRS complex, by examining thewavelet transform in the corresponding levels. According to the position of R wavevertex and the average ECG cycle, a window width adaptive method of searching for Rand P wave is proposed. In this window, the differential values of the original signalsare used to identify the key points of the waveform of P and T wave. The detection rateof the key points in QRS complex, P wave and T wave improves a lot than the previousalgorithms.
3. The Study on the Hardware Oriented Implementation of ECG SignalProcessing, Analysis of the Fast Algorithm and VLSI Implementation
The fast algorithm of ECG signal processing and identification based on DB4wavelet lifting is created. The algorithm uses the wavelet lifting's characteristic ofpossessing fast speed, and greatly improves the algorithm's overall execution speed.After making the study on DB4wavelet lifting VLSI implementation issues, as far asthe key technical points of the algorithm's transplantation toward the hardwareplatform are concerned, the program of the lifting decomposition and reconstruction ofDB4wavelet by using FPGA is proposed. The effectiveness and the above algorithm and the feasibility of realizing FPGA program are proved by the experiments.
4. The Study on the Sorting Algorithm of the Abnormal ECG Signal
The ECG waveform vector extraction algorithm which is self adaptive to theaverage length of ECG cycle is created. The judgment of using the logical judgment toexact the normal ECG waveform is given. Accordingly, LCFCM algorithm whichcombines logical judgment, cluster analysis and fuzzy clustering together to realize theaccurate clustering of the abnormal ECG heart rate is proposed. The algorithm has agood adaptability to the ECG signal with individual differences. And the clusteranalysis and fuzzy clustering analysis based on the extracted ECG vector waveform canguarantee the integrity of algorithm's object information, which makes the wholealgorithm become very accurate. Finally, the experiment by using MIT-BIH databaseas the sample is made. The accuracy rate of the classification of the abnormal heart rateby LCFCM algorithm reaches93%.
引文
[1] American Heart Association Statistics Committee and Stroke StatisticsSubcommittee, Heart Disease and Stroke Statistics—2009Update: A ReportFrom the American Heart Association[R]. American: AHA,2010.
[2]韦再华,谢学琴等.中华预防医学杂志[J],2009,1(43):68-70.
[3] Jiang He, Dongfeng Gu, Xigui Wu, etal. Major Causes of Death among men andwomen in China[J]. New England Journal of Medieine,2005,353(11):1124-1134.
[4]魏超.基于小波变换的心电信号自动分析技术[D].郑州：郑州大学，2011.
[5]卢喜烈,朱力华.纪念心电图临床应用100周年[J].中华心率失常学杂志,2002,6(3)：140-142.
[6]刘一平,杨亮亮,凌朝东,李国刚.远程心电医疗信号监测系统设计[J].现代电子技术,2008(21)：169-173.
[7]季虎.心电信号自动分析关键技术研究[D].长沙：国防科技大学，2006
[8]郭爽.心电信号消噪及特征识别算法的研究[D].长沙：中南大学,2009.
[9]白家莲.动态心电信号分析系统设计[D].南京：东南大学，2009.
[10]周群一. ECG心拍建模与分析识别[D].杭州：浙江大学，2004.
[11] Fei Zhang, Yong Lian. QRS Detection Based on Multiscale MathematicalMorphology for Wearable ECG Devices in Body Area Networks [J]. BiomedicalCircuits and Systems,2009,3(4):220–228.
[12] Oster J, Pietquin O, Kraemer M. Nonlinear Bayesian Filtering for Denoising ofElectrocardiograms Acquired in a Magnetic Resonance Environment [J].Biomedical Engineering,2010,57(7):1628–1638.
[13] Benmalek M, Charef A. Digital fractional order operators for R-wave detectionin electrocardiogram signal [J]. Signal Processing,2009,3(5):381-391.
[14] S.Poornachandra. Wavelet-based denosing using subband dependent thresholdfor ECG signals [J]. Digital Signal Processing,2008(18):49-55.
[15] Sigh, Brij N. Optimal selection of wavelet basis function applied to ECG signaldenoising [J], Digital Signal Processing: A review Journal,2006,16(3):275-287.
[16]李小燕，王涛，冯焕清等.基于小波变换的自适应滤波器消除ECG中基线漂移[J].中国科学技术大学学报，2000，30(4):450-454.
[17]王笑梅，王辉.基于小波的ECG信号噪声消除[J].上海师范大学学报(自然科学版)，2002，31(2):50-54.
[18] Ergun Ercelebi.Electrocardiogram signals denoising using lifting-based discretewavelet transform[J], Computers in Biology and Medicine,2004(34):479-493.
[19]李刚,刘巍等.抑制工频干扰及基线漂移的快速算法[J],中国生物医学工程学报,2005,19(1):99-103.
[20] Benmalek M, Charef A.Digital fractional order operators for R-wave detectionin electrocardiogram signal [J], ET Signal Processing,2009,3(5):381-391.
[21]龙兴明,周静.心电信号预处理中基于MATLAB的陷波器设计[J].重庆师范学院学报,2005,20(9):26-28.
[22] Wilfried Philips.Adaptive Noise Removal from Biomedical Signal UsingWarped Polynomials[J].IEEE Trans On BME,2001,43(3):480-492.
[23]孙京霞,白延强等.一种抑制心电信号50Hz工频干扰的改进Levkov方法[J].航天医学与医学工程,2004,13(3):196-199.
[24] XueQ HuYH, TomPkins WJ. Neural-network-based adaptive matched filteringfor QRS detection [J]. IEEE Transactions on Biomedieal Engineering,1992,39(4):317-329.
[25] Park KL，Khil MJ，LeeBC，etal. Design of a wavelet interpolation filter forenhancement of the ST-segment [J]. Medieal and Biological Engineering andComputing,2001,39(3):355-361.
[26] Donoho DL. De-noising by soft-thresholding [J].IEEE Transactions onInformation Theory,1995,41(3):613-627.
[27] Agante PM, Marques de Sa JP. ECG noise filtering using wavelets withsoft-thresholding methods[J]. Computers in Cardiology,1999,26:535-538.
[28] Ercelebi E. Electrocardiogram signals de-noising using lifting-based diseretewavelet transform[J]. Computers in Biology and Medicine,2004,34(6):479-493.
[29] Hamllton PS. A comparison of adaptive and nonadaptive filters for reduction ofPower line interference in the ECG[J]. IEEE Transactions on BiomedicalEngineering,1996,43(l):105-109.
[30]席涛,杨国胜,汤池等.基于自适应滤波的心电图中呼吸信号的提取方法[J].第四军医大学学报,2005,26(9):552-554.
[31]朱洪俊.心电信号波群的小波精确识别法[J].西南科技大学学报,2007,22(2):33-39.
[32] Afonso V X，Tompkins W J，Nguyen T Q，et a1．ECG beat detection using filterbanks[J]．Trans On BME，1999，46(2):192-202．
[33]刘海龙.生物医学信号处理.北京:化学工业出版社，2006.
[34] Rosaria S,Carlo M．Artificial neural networks for automatic ECG analysis[J]．IEEE Trans on Signal Processing，1998，46(5)：1417-1425．
[35] Min Soo Kim, Young Chang Cho, Suk-Tae Seo，etc. A new method of ECGfeature detection based on combined wavelet transform for u-health service[J].Biomedical Engineering Letters,2011,1(2):108-115
[36] Yüksel zbay, Rahime Ceylan, Bekir Karlik. Integration of type-2fuzzyclustering and wavelet transform in a neural network based ECG classifier [J].Expert Systems with Applications.2011,38(1):1004-1010
[37] Bhyri, Channappa, Hamde, S.T., Waghmare, L.M. ECG feature extraction anddisease diagnosis[J]. Journal of Medical Engineering and Technology,2011,35(6-7):354-361.
[38] R. K. Sunkaria, S. C. Saxena, V. Kumar, etc. Wavelet based R-peak detection forheart rate variability studies[J]. Journal of Medical Engineering&Technology,2010,34(2):108-115.
[39] Ching-En Tseng, Ching-Yu Peng, Ming-Wei Chang,etc. Novel Approach toFuzzy-Wavelet ECG Signal Analysis for a Mobile Device [J]. Journal ofMedical Systems,2010,34(1):71-81.
[40] Li C W，Zheng C X，Tai C F. Detection of ECG characteristic points usingwavelet transforms [J]．IEEE Tram on BME，1995，42(1)：21-28．
[41] Ramakrishnan A G． Saha supratim ECG coding by wavelet-based linearprediction [J]．IEEE Trans on BME，1997，44(12)：1253-1260．
[42] Kuzume K, Niijima K, Takano S．FPGA-based lifting wavelet processor forreal-time signal detection [J]．Elsevier Signal Processing,2004,84：1931-1940.
[43] Pande V N.Bedside ECG Monitor Using a Microcomputer[J].Med Boil.EngComput,1985,23(9):487-492.
[44] Y.Ferdi,J.P.Herbeuval.R Wave Detection Using Fractional DigitalDifferentiation[J]. ITBM-RBM,2006,24(8):273-280.
[45]黄敏,陈海燕,王益民,籍涛.基于小波变换的QRS波形检测方法[J].哈尔滨理工大学学报,2006,11(4):81-84.
[46] LI Cui-wei, ZHENG Chong-xun, TAI Chang-feng. Detection of ECGCharacteristic PointsUsingWaveletTransforms[J]. IEEE Trans. on BME,1995,42(1):21~28.
[47]于学鸿，许小汉等.基于神经网络的波形检测方法[J]。生物医学工程学杂志.2000,17(1):59-62.
[48]丁哨卫,张作生,彭虎,冯焕清.心电QRS波的非线性分类方法的研究[J].生物物理学报,2004,13(3):441-447.
[49]黄国言,邹沐昌.模糊模式识别算法在动态心电图QRS模板统计中的应用[J].燕山大学学报,2003,25(3):263-265.
[50]闰润强,詹永麒等.12导联同步心电信号自动检测技术的研究[J].中国医疗器械杂志,2005,26(2):126-129.
[51]杨海威,詹永麒等.12导联心电图P波检测算法[J].北京生物医学工程,2005,21(2):102-105.
[52]余辉,杜非,张力新.基于形态学的自动QT间期检测方法的研究[J].航空医学与医学工程.2010,2(1):63-68。
[53]毛玲,张国敏,孙即祥.基于位置估计与识别后处理的心电信号P波检测[J].信号处理.2009,25(6):948-952。
[54]季虎,孙即祥,王春光.基于小波变换的自适应QRS-T对消P波检测算法[J].电子与信息学报.2007,27(8):1868-1871。
[55]李坤阳,胡广书.基于心电图分析的心率失常分类[J].清华大学学报（自然科学版）,2009,49(3):418-421.
[56] Hosseini H Gholam, Luo D, Reynolds K.J. The comparison of different feedforward neural network architectures for ECG signal diagnosis [J]. MedicalEngineering and Physics,2006,28(4):372-378.
[57] Ubeyli Elif Derya. Analysis of ECG signals by diverse and composite features[J]. Istanbul University-Journal of Electrical and Electronics Engineering,2007,7(2):393-402.
[58] Yeh Yun-Chi, Wang Wen-June, Chiou Che-Wun. Cardiac arrhythmia diagnosismethod using linear discriminant analysis on ECG signals [J]. Journal of theInternational Measurement Confederation,2009,42(5):778-789.
[59] Polat Kemal, Akdemir Bayram, Günes Salih. Computer aided diagnosis of ECGdata on the least square support vector machine [J]. Digital Signal Processing: AReview Journal,2008,18(1):25-32.
[60] Krimi S, Ouni K, Ellouze N. ECG signal classification using hidden Markovtree [J]. International Review on Computers and Software,2009,5(6):615-619.
[61] Melgani Farid1, Bazi Yakoub. Classification of electrocardiogram signals withsupport vector machines and particle swarm optimization [J]. IEEE Transactionson Information Technology in Biomedicine,2008,12(5):667-677.
[62] Mitra Sucharita, Mitra Madhuchhanda, Chaudhuri B.B. A rough-set-basedinference engine for ECG classification [J]. IEEE Transactions onInstrumentation and Measurement,2006,55(6):2198-2206.
[63] Homaeinezhad M.R, Atyabi S.A, Tavakkoli E, etc al. ECG arrhythmiarecognition via a neuro-SVM-KNN hybrid classifier with virtual QRSimage-based geometrical features [J]. Expert Systems withApplications,2012,39(2):2047-2058.
[64] Mishra Amit K, Raghav Shantanu. Local fractal dimension based ECGarrhythmia classification [J]. Biomedical Signal Processing and Control,2010,5(2):114-123.
[65] Roopaei M, Boostani R, Sarvestani R. Rohani, etc al. Chaotic basedreconstructed phase space features for detecting ventricular fibrillation [J].Biomedical Signal Processing and Control,2010,5(4):318-327.
[66]李昕,洪文学,王秀清,王惠惠.基于云模型理论的心电信号分析方法研究[J].生物医学工程学杂志.2011,2(1):27-31.
[67] Sadiku Mattew N O, Akujuobi Cajetan M, Garcia Raymond C. An introductionto wavelets in electromagnetics [J]. IEEE Microwave Magazine,2005,6(2):63-72.
[68] Ku Cheng-Tung, Hung King-Chu, Wu Tsung-Ching, Wang, Huan-Sheng.Wavelet-based ECG data compression system with linear quality control scheme[J]. IEEE Transactions on Biomedical Engineering,2010,6(57):1399-1409.
[69] Wang Liping，Shen Mi，Tong Jiafei，et al. A uncertain reason method forabnormal ECG detection [A]. In: IEEE International Symposium on IT inMedicine&Education [C]. Jinan: IEEE Computer Society，2009.1091-1096.
[70] Rigatos GG. Fault detection and isolation based on fuzzy automata [J].Information Sciences Special Section: Web Search，2009，179(12):1893-1902.
[71] Uyar A，Gurgen F. Arrhythmia classification using serial fusion of supportvector machines and logistic regression [A]. In:Proceedings of the4th IEEEWorkshop on Intelligent Data Acquisition and Advanced Computing Systems:Technology and Applications [C]. Dortmund: IEEE Computer Society，2007.560-565.
[72] Polat K，Akdemir B，Gunes S. Computer aided diagnosis of ECG data on theleast square support vector machine [J].Digital Signal Processing，2008，18(1):25-32.
[73] Polat K， Gunes S. Detection of ECG arrhythmia using a differential expertsystem approach based on principal component analysis and least square supportvector machine [J]. Applied Mathematics and Computation，2007，186(1):898-906.
[74] Yu SN， Chou KT. Integration of independent component analysis and neuralnetworks for ECG beat classification [J]. Expert Systems with Applications，2008，34(4):2841-2846.
[75] Ubeyli ED. Combining recurrent neural networks with eigenvector methods forclassification of ECG beats [J]. Digital Signal Processing，2009，19(2):320-329.
[76] Talbi ML，Charef A. PVC discrimination using the QRS power spectrum andself-organizing maps [J]. Computer Methods and Programs in Biomedicine，2009，94(3):223-231.
[77] Moavenian M，Khorrami H. A qualitative comparison of artificial neuralnetworks and support vector machines in ECG arrhythmias classification [J].Expert Systems with Applications，2010，37(4):3088-3093.
[78] Exarchos TP，Papaloukas C，Fotiadis DI. An association rule mining-basedmethodlogy for automated detection of ischemic ECG beats [J]. IEEETransactions on Biomedical Engineering，2006，53(8):1531-1540.
[79] Exarchos TP， Tsipouras MG， Exarchos CP， et al. A methodology for theautomated creation of fuzzy expert systems for ischaemic and arrhythmic beatclassification based on a set of rules obtained by a decision tree [J]. ArtificialIntelligence in Medicine，2007，40(3):187-200.
[80] Dong Jun， Zhang Jiawei. Experiences-based intelligence simulation in ECGrecognition [A]. In: Proceedings of International Conference on ComputationalIntelligence for Modelling， Control and Automation[C]. Vienna: IEEEComputer Society，2008.796-801.
[81]薛JQ，罗兰森GI.用于心脏病学和病人监护数据分析的多层系统[P].中国专利:200710105373.5，2007-04-17.
[82]周S·，雷迪S·，格雷格RE·，等.病变冠状动脉的自动识别[P].中国专利:CN101795622，2010-08-04.
[83]唐晓初.小波分析及其应用[M].重庆：重庆大学出版社,2003.
[84]孙延奎.小波分析及其应用[M].北京：机械工业出版社,2005.
[85]李建平.小波分析方法的应用[M].重庆：重庆大学出版社,1999.
[86]梁崴巍.基于小波变换的心电信号预处理与特征识别算法[D].沈阳：中国医科大学,2007
[87] Kayhan Sema, Er elebi Ergun. ECG de-noising on bivariate shrinkage functionexploiting inter-scale dependency of wavelet coefficients [J]. Turkish Journal ofElectrical Engineering and Computer Sciences,2011,19(3):495-511.
[88] Shyu Liang-Yu, Hu Weichih. Intelligent hybrid methods for ECG classification-A review [J]. Journal of Medical and Biological Engineering,2008,28(1):1-10.
[89] Vansteenkiste E, Houben R, Pizurica A, Philips W. Classifyingelectrocardiogram peaks using new wavelet domain features [J]. Computers inCardiology,2008,(35):853-856.
[90] Khandoker Ahsan H, Kimura Y, Palaniswami M. Automated identification ofabnormal fetuses using fetal ECG and Doppler ultrasound signals [J].Computers in Cardiology,2009,(36):709-712.
[91] Singh Brij N, Tiwari, Arvind K. Optimal selection of wavelet basis functionapplied to ECG signal de-noising [J]. Digital Signal Processing: A ReviewJournal,2006,16(3):275-287.
[92] Charef A, Abdelliche F. Fractional wavelet for r-wave detection in ECG signal[J].Critcal Reviews in Biomedical Engineering,2008,36(2-3):79-91.
[93] Kumari R, Shantha Selva, Bharathis S, Sadasivam V. QRS complex detectionusing optimal discrete wavelet [J]. International Journal of ComputationalIntelligence and Applications,2009,8(2):97-109.
[94] Amoore, J.N. Noise and the recording of bioelectrical activity [J]. Elektron,1987,4(5):23-26.
[95] Boutaa M., Bereksi-Reguig F, Debbal S.M.A. ECG signal processing usingmultiresolution analysis [J]. Journal of Medical Engineering andTechnology,2008,32(6):466-478.
[96] Augustyniak Piotr. Adaptive wavelet discrimination of muscular noise in theECG [J]. Computers in Cardiology,2006,(33):481-484.
[97] Poornachandra S. Wavelet-based de-noising using sub-band dependent thresholdfor ECG signals [J].Digital Signal Processing: A Review Journal,2008,18(1):49-55.
[98] Ghaffari A, Homaeinezhad M.R, Akraminia M, Atarod M, Daevaeiha M. Arobust wavelet-based multi-lead electrocardiogram delineation algorithm [J].Medical Engineering and Physics,2009,31(10):1219-1227.
[99] Mateo J, Sánchez C, Vayá C, Cervigon R., Rieta J.J. A new adaptive approach toremove baseline wander from ECG recordings using madeline structure [J].Computers in Cardiology,2007,(34):533-536.
[100] Xu Lisheng, Zhang David, Wang Kuanquan, Li Naimin, Wang Xiaoyun.Baseline wander correction in pulse waveforms using wavelet-based cascadedadaptive filter [J]. Computers in Biology and Medicine,2007,37(5):716-731.
[101] Llamedo Soria M, Martínez J.P. An ECG classification model based onmultilead wavelet transform features [J]. Computers in Cardiology,2007,(34):105-108.
[102] Choi Samjin, Adnane Mourad Lee, Gi-Ja, Jang Hoyoung,etc. Development ofECG beat segmentation method by combining lowpass filter and irregular R-Rinterval checkup strategy [J]. Expert Systems with Applications,2010,37(7):5208-5218.
[103]孙轶.基于自适应提升小波的信号去噪技术研究[D].合肥:中国科技大学,2008.
[104] El-Sayed A, El-Dahshan. Genetic algorithm and wavelet hybrid scheme forECG signal de-noising [J]. Telecommunication Systems,2011,46(3):209-215.
[105] Matsuyama Aya, Jonkman M. The application of wavelet and feature vectors toECG signals [J]. Australasian Physical and Engineering Sciences in Medicine,2006,29(1):13-17.
[106] Li Suyi, Lin Jun. ECG signal de-noising using a combined wavelet transformalgorithm [J]. Yi Qi Yi Biao Xue Bao/Chinese Journal of Scientific Instrument,2009,30(4):689-693.
[107] DONOHO D L, JOHNSTONE IM. Adapting to unknown smoothness viawavelet shrinkage [J]. Journal of American StatAssoc,1995,12(90):1200-1224.
[108]苏丽,赵丽良,张仁广.基于改进小波阈值法的平移不变的心电信号去噪[J].哈尔滨工程大学学报,2006,27(4):840-844.
[109]苏丽.远程心电监护诊断系统心电信号处理方法研究[D].哈尔滨:哈尔滨工程大学,2006.
[110] Ghaffari A, Homaeinezhad M.R, Khazraee M, Daevaeiha M.M. Segmentation ofholter ECG waves via analysis of a discrete wavelet-derived multipleskewness-kurtosis based metric [J]. Annals of Biomedical Engineering,2010,38(4):1497-1510.
[111] Zhang Wei, Ge Linlin. ECG signal detection using adaptive matched filer instrong noise environment [J]. Journal of Information and Computational Science,2008,5(1):215-221.
[112] Kumari Shantha Selva, Sadasivam V. QRS complex detection using doubledensity discrete wavelet transform [J]. Biomedical Engineering-Applications,Basis and Communications,2008,20(2):65-73.
[113] Ghaffari A, Golbayani H, Ghasemi M. A new mathematical based QRS detectorusing continuous wavelet transform [J]. Computers and Electrical Engineering,2008,34(2):81-91.
[114] Madeiro Jo o P.V, Cortez Paulo C, Oliveira Francisco I,etc. A new approach toQRS segmentation based on wavelet bases and adaptive threshold technique [J].Medical Engineering and Physics,2007,29(1):26-37.
[115] Zheng Huabin1, Wu Jiankang. A real-time QRS detector based on discretewavelet transform and cubic spline interpolation [J]. Telemedicine and e-Health,2008,14(8):809-815.
[116]金怡果,刘艳斌.一种检测与分析心电波形的算法.福州大学学报(自然科学版)[J],1998,26(l):38~42.
[117]梁崴巍.基于小波变换的心电信号预处理与特征识别算法[D].沈阳：中国医科大学,2009.
[118] Shi Li, Yang Cenyu, Fei Minrui. Electrocardiogram R-wave and ST segmentextraction based on wavelet transform [J]. Yi Qi Yi Biao Xue Bao/ChineseJournal of Scientific Instrument,2008,29(4):804-809.
[119] Meyer Carsten, Gavela José Fernandez, Harris Matthew. Combining algorithmsin automatic detection of QRS complexes in ECG signals [J]. IEEETransactions on Information Technology in Biomedicine,2006,10(3):468-475.
[120] Zhu W.F, Zhao H.M. Design of a ST segment analysis system for ambulatoryischemia monitoring [J]. Journal of Information and Computational Science,2008,5(2):505-512.
[121] Chesnokov Yuriy C, Nerukh D, Glen R.C. Individually adaptable automaticQT detector [J]. Computers in Cardiology,2006,(33):337-340.
[122] Boix Macarena, Cantó Bego a, Cuesta David, Micó Pau. Using the WaveletTransform for T-wave alternans detection [J]. Source: Mathematical andComputer Modelling,2009,50(5-6):738-742.
[123] Chen Yong-li，Duan Hui-long. A QRS complex detection algorithm based onmathematical morphology and envelope [C]. Shanghai: Proceedings of the2005IEEE in Medicine and Biology27th Annual Conference,2005:4654-4657
[124]万相奎,徐杜,张军.心电信号小波消噪方法的研究[J].中国生物医学工程学报.2008,27(4):630-632.
[125]单立场，冀志华.基于小波消噪和自适应滤波器的FECG提取[J].重庆工学院学报(自然科学版).2007,21(6):74-78.
[126]季虎,孙即,祥毛玲.基于小波变换与形态学运的ECG自适应滤波法[J].信号处理.2006,22(3):334-337.
[127] Xin Liu; Yuanjin Zheng; Myint Wai Phyu, Multiple Functional ECG Signal isProcessing for Wearable Applications of Long-Term Cardiac Monitoring [J].Biomedical Engineering,2011,58(2):380–389.
[128] Peiro M M，Ballester F, Paya G,et a1．FPGA custom dsp for ecg signal analysisand compression [J]. FPL, LNCS2004,3203：954-958．
[129] Rosado A，Bataller M，Guerrero J F, eta1．High performance hardwarecorrelation coefficient assessment using programmable logic for ECG signals [J].Microprocessors and Microsystems,2003,,27(1):33-39.
[130] Kuzume K, Niijima K, Takano S．FPGA-based lifting wavelet processor forreal-time signal detection [J]．Elsevier,Signal Processing,2004,84：1931-1940
[131]杨永明,韦建敏,刘俊刚,黄晓博.基于FPGA的实时心电监护系统设计[J].电子技术应用,2007(7)：78-80.
[132]韦建敏,杨永明,郭巧惠.基于FPGA的实时心电信号处理系统设计[J].电子器件,2005(9)：581-583,588.
[133]杨秀增,黄灿胜,盘世准,韦树贡.基于FPGA的心电信号采集系统设计[J].南宁师范高等专科学校学报,2008(6)：127-128.
[134]刘成,刘娅琴.基于FPGA软核的佩戴式心电信号处理系统的设计[J].中国医疗设备,2010(3)：37-40.
[135]曹虎,王敏,董汉彬,徐安明.基于Fution模数混合FPGA芯片的心电仪片上系统开发[J].微型机与应用,2010(8)：92-94.
[136]钱江,凌朝东.基于小波变换的ECG信号压缩及其FPGA实现[J].电子技术应用,2009(1)：63-66.
[137]彭斌,王时胜,熊云峰.心率诊断的FPGA硬件实现及仿真[J].南昌大学学报（工科版）,2010(10)：405-408.
[138] Sweldens W. The lifting scheme: A construction of second generation wavelets[J]. SIAM J Math Anal，1997,29(2):511-546.
[139]张胜,吴仲光,李征.一种自适应R波检测算法实现[J].四川大学学报（自然科学版）.2008，45(8):498-502.
[140] Kuzume Koichi, Niijima Koichi, Takano Shigeru. Fpga-based lifting waveletprocessor for real-time signal detection[J].Signal Processing,2004,84(10):1931-1940.
[141] Ding Yuan-Yuan1, Si Yu-Juan, Lang Liu-Qi, Luo Si-Wei. VLSI implementationof image compression coding based on lifting wavelet transform [J]. Jilin DaxueXuebao (Gongxueban)/Journal of Jilin University (Engineering and TechnologyEdition),2007,37(3):675-680.
[142] Lan Xuguang, Zheng Nanning, Liu Yuehu. Low-power and high-speed VLSIarchitecture for lifting-based forward and inverse wavelet transform [J]. IEEETransactions on Consumer Electronics,2005,51(2):379-385.
[143] Shi Guangming, Liu Weifeng, Zhang Liu, Li Fu. An efficient foldedarchitecture for lifting-based discrete wavelet transform [J]. IEEE Transactionson Circuits and Systems II: Express Briefs,2009,56(4):290-294.
[144]闫润强.十二导同步心电图自动分析系统信号预处理及诊断逻辑的研究[D].上海：上海交通大学，2002.
[145]汤征.引入异常心电节律分析的心拍分类算法研究[D].杭州：浙江大学，2008.
[146] Ubeyli Elif Derya. ECG beats classification using multiclass support vectormachines with error correcting output codes [J]. Digital Signal Processing: AReview Journal,2007,17(3):675-684.
[147] Zhang Hongjun. The research of ECG diagnosis system based on support vectormachines [J]. Journal of Convergence Information Technology,2011,6(3):35-45.
[148] Froese Tom, Hadjiloucas Sillas, Galv o Roberto K.H, etc. Comparison ofextrasystolic ECG signal classifiers using discrete wavelet transforms [J].Pattern Recognition Letters,2006,27(5):393-407.
[149] Gubbi J, Khandoker A, Palaniswami M. Classification of obstructive and centralsleep apnea using wavelet packet analysis of ECG signals [J]. Computers inCardiology,2009,(36):733-736.
[150] Lin Chia-Hung. Classification enhancible grey relational analysis for cardiacarrhythmias discrimination [J]. Medical and Biological Engineering andComputing,2006,44(4):311-320.
[151] Sajedin Atena, Zakernejad Shokoufeh, Faridi Soheil, etc. A trainable neuralnetwork ensemble for ECG beat classification [J].2011,(70):788-794.
[152] Ubeyli, Elif Derya. Recurrent neural networks with composite features fordetection of electrocardiographic changes in partial epileptic patients [J].Computers in Biology and Medicine,2008,38(3):401-410.
[153] Ceylan Rahime. Ozbay Yüksel. Comparison of FCM, PCA and WT techniquesfor classification ECG arrhythmias using artificial neural network [J]. ExpertSystems with Applications,2007,33(2):286-295.
[154] Mehta S.S, Sharma Swati, Lingayat N.S. Development of FCM based algorithmfor the delineation of QRS-complexes in electrocardiogram [C]. Coimbatore,India:2009World Congress on Nature and Biologically Inspired Computing,2009:754-759.
[155] Ozbay,Yüksel; Ceylan, Rahime; Karlik, Bekir. Integration of type-2fuzzyclustering and wavelet transform in a neural network based ECG classifier [J].Expert Systems with Applications,2011,38(1):1004-1010.
[156]林泽涛,葛耀峥.心律失常的聚类分析研究[J].生物医学工程杂志,2006,23(5):999-1002.
[157]刘世雄.基于模糊聚类算法对心电数据典型特征分类研究[D].杭州：浙江大学,2006.
[158]岳清华.动态心电图波形聚类策略研究[D].天津:天津理工大学,2007.
[159]严峻.模糊聚类算法应用研究[D].杭州：浙江大学,2006.
[160] Zadeh L A. Fuzzy sets [J]. Inf. Control,1965,8:338-353.
[161] Zadeh J C. Cluster validity with fuzzy sets [J]. Journal of Cybernetics,1974,3(3):58-72.
[162] Shannon C E. A mathematical theory of communication [J]. Bell Syst Teeh,1948,XXVll(3):379-423.
[163] Ravi V.1, Bin Ma., Kumar P. Ravi. Threshold accepting based fuzzy clusteringalgorithms [J]. International Journal of Uncertainty, Fuzziness andKnowlege-Based Systems,2006,14(5):617-632.
[164] Vendramin L, Campello R.J.G.B, Coletta L.F.S, Hruschka E.R. Distributed fuzzyclustering with automatic detection of the number of clusters [J]. Advances inIntelligent and Soft Computing,2011,(91):133-140.
[165]彭勇,吴友情.一种新的聚类有效性函数[J].计算机工程与应用2010,46(6):124-126.
[166] Ruspini E H. A new approach to clustering [J]. Inf. cont.,1969,15(1):22-32.
[167] Bezdek J C, Hathaway R J, Sabin M J, et al. Convergence theory for fuzzyc-means: Counter-examples and repairs [J]. IEEE SMC1987，17(5):873-874.
[168] Pal N R, Bezdek J C,.On cluster validity for the fuzzy c-means model [J]. IEEEFuzzy System,1995，3(3):370.
[169] Chan K P, Cheung Y S. Modified fuzzy SODATA for the classification ofhandwritten Chinese charaeters [C]. Proc int conf Chinese comput,Singapore,1986,361-364.
[170] Wu, Kuo-Lung. Analysis of parameter selections for fuzzy c-means [J]. PatternRecognition,2012,45(1):407-415.
[171] Ghodsi, Ali. Efficient parameter selection for system identification [C]. AnnualConference of the North American Fuzzy Information Processing Society-NAFIPS,2004,2:750-755.
[172]严峻.模糊聚类算法应用研究[D].杭州：浙江大学,2006.
[173]林泽涛.心电信号在线数据知识化研究[D].杭州：浙江大学，2005
[174]陈兵兵.心电信号实时检测算法与应用研究[D].武汉：华中科技大学,2009.
[175]高彩虹.心电信号临床信息的自动识别研究[D].镇江：江苏大学,2010.
[2]韦再华,谢学琴等.中华预防医学杂志[J],2009,1(43):68-70.
[3] Jiang He, Dongfeng Gu, Xigui Wu, etal. Major Causes of Death among men andwomen in China[J]. New England Journal of Medieine,2005,353(11):1124-1134.
[4]魏超.基于小波变换的心电信号自动分析技术[D].郑州：郑州大学，2011.
[5]卢喜烈,朱力华.纪念心电图临床应用100周年[J].中华心率失常学杂志,2002,6(3)：140-142.
[6]刘一平,杨亮亮,凌朝东,李国刚.远程心电医疗信号监测系统设计[J].现代电子技术,2008(21)：169-173.
[7]季虎.心电信号自动分析关键技术研究[D].长沙：国防科技大学，2006
[8]郭爽.心电信号消噪及特征识别算法的研究[D].长沙：中南大学,2009.
[9]白家莲.动态心电信号分析系统设计[D].南京：东南大学，2009.
[10]周群一. ECG心拍建模与分析识别[D].杭州：浙江大学，2004.
[11] Fei Zhang, Yong Lian. QRS Detection Based on Multiscale MathematicalMorphology for Wearable ECG Devices in Body Area Networks [J]. BiomedicalCircuits and Systems,2009,3(4):220–228.
[12] Oster J, Pietquin O, Kraemer M. Nonlinear Bayesian Filtering for Denoising ofElectrocardiograms Acquired in a Magnetic Resonance Environment [J].Biomedical Engineering,2010,57(7):1628–1638.
[13] Benmalek M, Charef A. Digital fractional order operators for R-wave detectionin electrocardiogram signal [J]. Signal Processing,2009,3(5):381-391.
[14] S.Poornachandra. Wavelet-based denosing using subband dependent thresholdfor ECG signals [J]. Digital Signal Processing,2008(18):49-55.
[15] Sigh, Brij N. Optimal selection of wavelet basis function applied to ECG signaldenoising [J], Digital Signal Processing: A review Journal,2006,16(3):275-287.
[16]李小燕，王涛，冯焕清等.基于小波变换的自适应滤波器消除ECG中基线漂移[J].中国科学技术大学学报，2000，30(4):450-454.
[17]王笑梅，王辉.基于小波的ECG信号噪声消除[J].上海师范大学学报(自然科学版)，2002，31(2):50-54.
[18] Ergun Ercelebi.Electrocardiogram signals denoising using lifting-based discretewavelet transform[J], Computers in Biology and Medicine,2004(34):479-493.
[19]李刚,刘巍等.抑制工频干扰及基线漂移的快速算法[J],中国生物医学工程学报,2005,19(1):99-103.
[20] Benmalek M, Charef A.Digital fractional order operators for R-wave detectionin electrocardiogram signal [J], ET Signal Processing,2009,3(5):381-391.
[21]龙兴明,周静.心电信号预处理中基于MATLAB的陷波器设计[J].重庆师范学院学报,2005,20(9):26-28.
[22] Wilfried Philips.Adaptive Noise Removal from Biomedical Signal UsingWarped Polynomials[J].IEEE Trans On BME,2001,43(3):480-492.
[23]孙京霞,白延强等.一种抑制心电信号50Hz工频干扰的改进Levkov方法[J].航天医学与医学工程,2004,13(3):196-199.
[24] XueQ HuYH, TomPkins WJ. Neural-network-based adaptive matched filteringfor QRS detection [J]. IEEE Transactions on Biomedieal Engineering,1992,39(4):317-329.
[25] Park KL，Khil MJ，LeeBC，etal. Design of a wavelet interpolation filter forenhancement of the ST-segment [J]. Medieal and Biological Engineering andComputing,2001,39(3):355-361.
[26] Donoho DL. De-noising by soft-thresholding [J].IEEE Transactions onInformation Theory,1995,41(3):613-627.
[27] Agante PM, Marques de Sa JP. ECG noise filtering using wavelets withsoft-thresholding methods[J]. Computers in Cardiology,1999,26:535-538.
[28] Ercelebi E. Electrocardiogram signals de-noising using lifting-based diseretewavelet transform[J]. Computers in Biology and Medicine,2004,34(6):479-493.
[29] Hamllton PS. A comparison of adaptive and nonadaptive filters for reduction ofPower line interference in the ECG[J]. IEEE Transactions on BiomedicalEngineering,1996,43(l):105-109.
[30]席涛,杨国胜,汤池等.基于自适应滤波的心电图中呼吸信号的提取方法[J].第四军医大学学报,2005,26(9):552-554.
[31]朱洪俊.心电信号波群的小波精确识别法[J].西南科技大学学报,2007,22(2):33-39.
[32] Afonso V X，Tompkins W J，Nguyen T Q，et a1．ECG beat detection using filterbanks[J]．Trans On BME，1999，46(2):192-202．
[33]刘海龙.生物医学信号处理.北京:化学工业出版社，2006.
[34] Rosaria S,Carlo M．Artificial neural networks for automatic ECG analysis[J]．IEEE Trans on Signal Processing，1998，46(5)：1417-1425．
[35] Min Soo Kim, Young Chang Cho, Suk-Tae Seo，etc. A new method of ECGfeature detection based on combined wavelet transform for u-health service[J].Biomedical Engineering Letters,2011,1(2):108-115
[36] Yüksel zbay, Rahime Ceylan, Bekir Karlik. Integration of type-2fuzzyclustering and wavelet transform in a neural network based ECG classifier [J].Expert Systems with Applications.2011,38(1):1004-1010
[37] Bhyri, Channappa, Hamde, S.T., Waghmare, L.M. ECG feature extraction anddisease diagnosis[J]. Journal of Medical Engineering and Technology,2011,35(6-7):354-361.
[38] R. K. Sunkaria, S. C. Saxena, V. Kumar, etc. Wavelet based R-peak detection forheart rate variability studies[J]. Journal of Medical Engineering&Technology,2010,34(2):108-115.
[39] Ching-En Tseng, Ching-Yu Peng, Ming-Wei Chang,etc. Novel Approach toFuzzy-Wavelet ECG Signal Analysis for a Mobile Device [J]. Journal ofMedical Systems,2010,34(1):71-81.
[40] Li C W，Zheng C X，Tai C F. Detection of ECG characteristic points usingwavelet transforms [J]．IEEE Tram on BME，1995，42(1)：21-28．
[41] Ramakrishnan A G． Saha supratim ECG coding by wavelet-based linearprediction [J]．IEEE Trans on BME，1997，44(12)：1253-1260．
[42] Kuzume K, Niijima K, Takano S．FPGA-based lifting wavelet processor forreal-time signal detection [J]．Elsevier Signal Processing,2004,84：1931-1940.
[43] Pande V N.Bedside ECG Monitor Using a Microcomputer[J].Med Boil.EngComput,1985,23(9):487-492.
[44] Y.Ferdi,J.P.Herbeuval.R Wave Detection Using Fractional DigitalDifferentiation[J]. ITBM-RBM,2006,24(8):273-280.
[45]黄敏,陈海燕,王益民,籍涛.基于小波变换的QRS波形检测方法[J].哈尔滨理工大学学报,2006,11(4):81-84.
[46] LI Cui-wei, ZHENG Chong-xun, TAI Chang-feng. Detection of ECGCharacteristic PointsUsingWaveletTransforms[J]. IEEE Trans. on BME,1995,42(1):21~28.
[47]于学鸿，许小汉等.基于神经网络的波形检测方法[J]。生物医学工程学杂志.2000,17(1):59-62.
[48]丁哨卫,张作生,彭虎,冯焕清.心电QRS波的非线性分类方法的研究[J].生物物理学报,2004,13(3):441-447.
[49]黄国言,邹沐昌.模糊模式识别算法在动态心电图QRS模板统计中的应用[J].燕山大学学报,2003,25(3):263-265.
[50]闰润强,詹永麒等.12导联同步心电信号自动检测技术的研究[J].中国医疗器械杂志,2005,26(2):126-129.
[51]杨海威,詹永麒等.12导联心电图P波检测算法[J].北京生物医学工程,2005,21(2):102-105.
[52]余辉,杜非,张力新.基于形态学的自动QT间期检测方法的研究[J].航空医学与医学工程.2010,2(1):63-68。
[53]毛玲,张国敏,孙即祥.基于位置估计与识别后处理的心电信号P波检测[J].信号处理.2009,25(6):948-952。
[54]季虎,孙即祥,王春光.基于小波变换的自适应QRS-T对消P波检测算法[J].电子与信息学报.2007,27(8):1868-1871。
[55]李坤阳,胡广书.基于心电图分析的心率失常分类[J].清华大学学报（自然科学版）,2009,49(3):418-421.
[56] Hosseini H Gholam, Luo D, Reynolds K.J. The comparison of different feedforward neural network architectures for ECG signal diagnosis [J]. MedicalEngineering and Physics,2006,28(4):372-378.
[57] Ubeyli Elif Derya. Analysis of ECG signals by diverse and composite features[J]. Istanbul University-Journal of Electrical and Electronics Engineering,2007,7(2):393-402.
[58] Yeh Yun-Chi, Wang Wen-June, Chiou Che-Wun. Cardiac arrhythmia diagnosismethod using linear discriminant analysis on ECG signals [J]. Journal of theInternational Measurement Confederation,2009,42(5):778-789.
[59] Polat Kemal, Akdemir Bayram, Günes Salih. Computer aided diagnosis of ECGdata on the least square support vector machine [J]. Digital Signal Processing: AReview Journal,2008,18(1):25-32.
[60] Krimi S, Ouni K, Ellouze N. ECG signal classification using hidden Markovtree [J]. International Review on Computers and Software,2009,5(6):615-619.
[61] Melgani Farid1, Bazi Yakoub. Classification of electrocardiogram signals withsupport vector machines and particle swarm optimization [J]. IEEE Transactionson Information Technology in Biomedicine,2008,12(5):667-677.
[62] Mitra Sucharita, Mitra Madhuchhanda, Chaudhuri B.B. A rough-set-basedinference engine for ECG classification [J]. IEEE Transactions onInstrumentation and Measurement,2006,55(6):2198-2206.
[63] Homaeinezhad M.R, Atyabi S.A, Tavakkoli E, etc al. ECG arrhythmiarecognition via a neuro-SVM-KNN hybrid classifier with virtual QRSimage-based geometrical features [J]. Expert Systems withApplications,2012,39(2):2047-2058.
[64] Mishra Amit K, Raghav Shantanu. Local fractal dimension based ECGarrhythmia classification [J]. Biomedical Signal Processing and Control,2010,5(2):114-123.
[65] Roopaei M, Boostani R, Sarvestani R. Rohani, etc al. Chaotic basedreconstructed phase space features for detecting ventricular fibrillation [J].Biomedical Signal Processing and Control,2010,5(4):318-327.
[66]李昕,洪文学,王秀清,王惠惠.基于云模型理论的心电信号分析方法研究[J].生物医学工程学杂志.2011,2(1):27-31.
[67] Sadiku Mattew N O, Akujuobi Cajetan M, Garcia Raymond C. An introductionto wavelets in electromagnetics [J]. IEEE Microwave Magazine,2005,6(2):63-72.
[68] Ku Cheng-Tung, Hung King-Chu, Wu Tsung-Ching, Wang, Huan-Sheng.Wavelet-based ECG data compression system with linear quality control scheme[J]. IEEE Transactions on Biomedical Engineering,2010,6(57):1399-1409.
[69] Wang Liping，Shen Mi，Tong Jiafei，et al. A uncertain reason method forabnormal ECG detection [A]. In: IEEE International Symposium on IT inMedicine&Education [C]. Jinan: IEEE Computer Society，2009.1091-1096.
[70] Rigatos GG. Fault detection and isolation based on fuzzy automata [J].Information Sciences Special Section: Web Search，2009，179(12):1893-1902.
[71] Uyar A，Gurgen F. Arrhythmia classification using serial fusion of supportvector machines and logistic regression [A]. In:Proceedings of the4th IEEEWorkshop on Intelligent Data Acquisition and Advanced Computing Systems:Technology and Applications [C]. Dortmund: IEEE Computer Society，2007.560-565.
[72] Polat K，Akdemir B，Gunes S. Computer aided diagnosis of ECG data on theleast square support vector machine [J].Digital Signal Processing，2008，18(1):25-32.
[73] Polat K， Gunes S. Detection of ECG arrhythmia using a differential expertsystem approach based on principal component analysis and least square supportvector machine [J]. Applied Mathematics and Computation，2007，186(1):898-906.
[74] Yu SN， Chou KT. Integration of independent component analysis and neuralnetworks for ECG beat classification [J]. Expert Systems with Applications，2008，34(4):2841-2846.
[75] Ubeyli ED. Combining recurrent neural networks with eigenvector methods forclassification of ECG beats [J]. Digital Signal Processing，2009，19(2):320-329.
[76] Talbi ML，Charef A. PVC discrimination using the QRS power spectrum andself-organizing maps [J]. Computer Methods and Programs in Biomedicine，2009，94(3):223-231.
[77] Moavenian M，Khorrami H. A qualitative comparison of artificial neuralnetworks and support vector machines in ECG arrhythmias classification [J].Expert Systems with Applications，2010，37(4):3088-3093.
[78] Exarchos TP，Papaloukas C，Fotiadis DI. An association rule mining-basedmethodlogy for automated detection of ischemic ECG beats [J]. IEEETransactions on Biomedical Engineering，2006，53(8):1531-1540.
[79] Exarchos TP， Tsipouras MG， Exarchos CP， et al. A methodology for theautomated creation of fuzzy expert systems for ischaemic and arrhythmic beatclassification based on a set of rules obtained by a decision tree [J]. ArtificialIntelligence in Medicine，2007，40(3):187-200.
[80] Dong Jun， Zhang Jiawei. Experiences-based intelligence simulation in ECGrecognition [A]. In: Proceedings of International Conference on ComputationalIntelligence for Modelling， Control and Automation[C]. Vienna: IEEEComputer Society，2008.796-801.
[81]薛JQ，罗兰森GI.用于心脏病学和病人监护数据分析的多层系统[P].中国专利:200710105373.5，2007-04-17.
[82]周S·，雷迪S·，格雷格RE·，等.病变冠状动脉的自动识别[P].中国专利:CN101795622，2010-08-04.
[83]唐晓初.小波分析及其应用[M].重庆：重庆大学出版社,2003.
[84]孙延奎.小波分析及其应用[M].北京：机械工业出版社,2005.
[85]李建平.小波分析方法的应用[M].重庆：重庆大学出版社,1999.
[86]梁崴巍.基于小波变换的心电信号预处理与特征识别算法[D].沈阳：中国医科大学,2007
[87] Kayhan Sema, Er elebi Ergun. ECG de-noising on bivariate shrinkage functionexploiting inter-scale dependency of wavelet coefficients [J]. Turkish Journal ofElectrical Engineering and Computer Sciences,2011,19(3):495-511.
[88] Shyu Liang-Yu, Hu Weichih. Intelligent hybrid methods for ECG classification-A review [J]. Journal of Medical and Biological Engineering,2008,28(1):1-10.
[89] Vansteenkiste E, Houben R, Pizurica A, Philips W. Classifyingelectrocardiogram peaks using new wavelet domain features [J]. Computers inCardiology,2008,(35):853-856.
[90] Khandoker Ahsan H, Kimura Y, Palaniswami M. Automated identification ofabnormal fetuses using fetal ECG and Doppler ultrasound signals [J].Computers in Cardiology,2009,(36):709-712.
[91] Singh Brij N, Tiwari, Arvind K. Optimal selection of wavelet basis functionapplied to ECG signal de-noising [J]. Digital Signal Processing: A ReviewJournal,2006,16(3):275-287.
[92] Charef A, Abdelliche F. Fractional wavelet for r-wave detection in ECG signal[J].Critcal Reviews in Biomedical Engineering,2008,36(2-3):79-91.
[93] Kumari R, Shantha Selva, Bharathis S, Sadasivam V. QRS complex detectionusing optimal discrete wavelet [J]. International Journal of ComputationalIntelligence and Applications,2009,8(2):97-109.
[94] Amoore, J.N. Noise and the recording of bioelectrical activity [J]. Elektron,1987,4(5):23-26.
[95] Boutaa M., Bereksi-Reguig F, Debbal S.M.A. ECG signal processing usingmultiresolution analysis [J]. Journal of Medical Engineering andTechnology,2008,32(6):466-478.
[96] Augustyniak Piotr. Adaptive wavelet discrimination of muscular noise in theECG [J]. Computers in Cardiology,2006,(33):481-484.
[97] Poornachandra S. Wavelet-based de-noising using sub-band dependent thresholdfor ECG signals [J].Digital Signal Processing: A Review Journal,2008,18(1):49-55.
[98] Ghaffari A, Homaeinezhad M.R, Akraminia M, Atarod M, Daevaeiha M. Arobust wavelet-based multi-lead electrocardiogram delineation algorithm [J].Medical Engineering and Physics,2009,31(10):1219-1227.
[99] Mateo J, Sánchez C, Vayá C, Cervigon R., Rieta J.J. A new adaptive approach toremove baseline wander from ECG recordings using madeline structure [J].Computers in Cardiology,2007,(34):533-536.
[100] Xu Lisheng, Zhang David, Wang Kuanquan, Li Naimin, Wang Xiaoyun.Baseline wander correction in pulse waveforms using wavelet-based cascadedadaptive filter [J]. Computers in Biology and Medicine,2007,37(5):716-731.
[101] Llamedo Soria M, Martínez J.P. An ECG classification model based onmultilead wavelet transform features [J]. Computers in Cardiology,2007,(34):105-108.
[102] Choi Samjin, Adnane Mourad Lee, Gi-Ja, Jang Hoyoung,etc. Development ofECG beat segmentation method by combining lowpass filter and irregular R-Rinterval checkup strategy [J]. Expert Systems with Applications,2010,37(7):5208-5218.
[103]孙轶.基于自适应提升小波的信号去噪技术研究[D].合肥:中国科技大学,2008.
[104] El-Sayed A, El-Dahshan. Genetic algorithm and wavelet hybrid scheme forECG signal de-noising [J]. Telecommunication Systems,2011,46(3):209-215.
[105] Matsuyama Aya, Jonkman M. The application of wavelet and feature vectors toECG signals [J]. Australasian Physical and Engineering Sciences in Medicine,2006,29(1):13-17.
[106] Li Suyi, Lin Jun. ECG signal de-noising using a combined wavelet transformalgorithm [J]. Yi Qi Yi Biao Xue Bao/Chinese Journal of Scientific Instrument,2009,30(4):689-693.
[107] DONOHO D L, JOHNSTONE IM. Adapting to unknown smoothness viawavelet shrinkage [J]. Journal of American StatAssoc,1995,12(90):1200-1224.
[108]苏丽,赵丽良,张仁广.基于改进小波阈值法的平移不变的心电信号去噪[J].哈尔滨工程大学学报,2006,27(4):840-844.
[109]苏丽.远程心电监护诊断系统心电信号处理方法研究[D].哈尔滨:哈尔滨工程大学,2006.
[110] Ghaffari A, Homaeinezhad M.R, Khazraee M, Daevaeiha M.M. Segmentation ofholter ECG waves via analysis of a discrete wavelet-derived multipleskewness-kurtosis based metric [J]. Annals of Biomedical Engineering,2010,38(4):1497-1510.
[111] Zhang Wei, Ge Linlin. ECG signal detection using adaptive matched filer instrong noise environment [J]. Journal of Information and Computational Science,2008,5(1):215-221.
[112] Kumari Shantha Selva, Sadasivam V. QRS complex detection using doubledensity discrete wavelet transform [J]. Biomedical Engineering-Applications,Basis and Communications,2008,20(2):65-73.
[113] Ghaffari A, Golbayani H, Ghasemi M. A new mathematical based QRS detectorusing continuous wavelet transform [J]. Computers and Electrical Engineering,2008,34(2):81-91.
[114] Madeiro Jo o P.V, Cortez Paulo C, Oliveira Francisco I,etc. A new approach toQRS segmentation based on wavelet bases and adaptive threshold technique [J].Medical Engineering and Physics,2007,29(1):26-37.
[115] Zheng Huabin1, Wu Jiankang. A real-time QRS detector based on discretewavelet transform and cubic spline interpolation [J]. Telemedicine and e-Health,2008,14(8):809-815.
[116]金怡果,刘艳斌.一种检测与分析心电波形的算法.福州大学学报(自然科学版)[J],1998,26(l):38~42.
[117]梁崴巍.基于小波变换的心电信号预处理与特征识别算法[D].沈阳：中国医科大学,2009.
[118] Shi Li, Yang Cenyu, Fei Minrui. Electrocardiogram R-wave and ST segmentextraction based on wavelet transform [J]. Yi Qi Yi Biao Xue Bao/ChineseJournal of Scientific Instrument,2008,29(4):804-809.
[119] Meyer Carsten, Gavela José Fernandez, Harris Matthew. Combining algorithmsin automatic detection of QRS complexes in ECG signals [J]. IEEETransactions on Information Technology in Biomedicine,2006,10(3):468-475.
[120] Zhu W.F, Zhao H.M. Design of a ST segment analysis system for ambulatoryischemia monitoring [J]. Journal of Information and Computational Science,2008,5(2):505-512.
[121] Chesnokov Yuriy C, Nerukh D, Glen R.C. Individually adaptable automaticQT detector [J]. Computers in Cardiology,2006,(33):337-340.
[122] Boix Macarena, Cantó Bego a, Cuesta David, Micó Pau. Using the WaveletTransform for T-wave alternans detection [J]. Source: Mathematical andComputer Modelling,2009,50(5-6):738-742.
[123] Chen Yong-li，Duan Hui-long. A QRS complex detection algorithm based onmathematical morphology and envelope [C]. Shanghai: Proceedings of the2005IEEE in Medicine and Biology27th Annual Conference,2005:4654-4657
[124]万相奎,徐杜,张军.心电信号小波消噪方法的研究[J].中国生物医学工程学报.2008,27(4):630-632.
[125]单立场，冀志华.基于小波消噪和自适应滤波器的FECG提取[J].重庆工学院学报(自然科学版).2007,21(6):74-78.
[126]季虎,孙即,祥毛玲.基于小波变换与形态学运的ECG自适应滤波法[J].信号处理.2006,22(3):334-337.
[127] Xin Liu; Yuanjin Zheng; Myint Wai Phyu, Multiple Functional ECG Signal isProcessing for Wearable Applications of Long-Term Cardiac Monitoring [J].Biomedical Engineering,2011,58(2):380–389.
[128] Peiro M M，Ballester F, Paya G,et a1．FPGA custom dsp for ecg signal analysisand compression [J]. FPL, LNCS2004,3203：954-958．
[129] Rosado A，Bataller M，Guerrero J F, eta1．High performance hardwarecorrelation coefficient assessment using programmable logic for ECG signals [J].Microprocessors and Microsystems,2003,,27(1):33-39.
[130] Kuzume K, Niijima K, Takano S．FPGA-based lifting wavelet processor forreal-time signal detection [J]．Elsevier,Signal Processing,2004,84：1931-1940
[131]杨永明,韦建敏,刘俊刚,黄晓博.基于FPGA的实时心电监护系统设计[J].电子技术应用,2007(7)：78-80.
[132]韦建敏,杨永明,郭巧惠.基于FPGA的实时心电信号处理系统设计[J].电子器件,2005(9)：581-583,588.
[133]杨秀增,黄灿胜,盘世准,韦树贡.基于FPGA的心电信号采集系统设计[J].南宁师范高等专科学校学报,2008(6)：127-128.
[134]刘成,刘娅琴.基于FPGA软核的佩戴式心电信号处理系统的设计[J].中国医疗设备,2010(3)：37-40.
[135]曹虎,王敏,董汉彬,徐安明.基于Fution模数混合FPGA芯片的心电仪片上系统开发[J].微型机与应用,2010(8)：92-94.
[136]钱江,凌朝东.基于小波变换的ECG信号压缩及其FPGA实现[J].电子技术应用,2009(1)：63-66.
[137]彭斌,王时胜,熊云峰.心率诊断的FPGA硬件实现及仿真[J].南昌大学学报（工科版）,2010(10)：405-408.
[138] Sweldens W. The lifting scheme: A construction of second generation wavelets[J]. SIAM J Math Anal，1997,29(2):511-546.
[139]张胜,吴仲光,李征.一种自适应R波检测算法实现[J].四川大学学报（自然科学版）.2008，45(8):498-502.
[140] Kuzume Koichi, Niijima Koichi, Takano Shigeru. Fpga-based lifting waveletprocessor for real-time signal detection[J].Signal Processing,2004,84(10):1931-1940.
[141] Ding Yuan-Yuan1, Si Yu-Juan, Lang Liu-Qi, Luo Si-Wei. VLSI implementationof image compression coding based on lifting wavelet transform [J]. Jilin DaxueXuebao (Gongxueban)/Journal of Jilin University (Engineering and TechnologyEdition),2007,37(3):675-680.
[142] Lan Xuguang, Zheng Nanning, Liu Yuehu. Low-power and high-speed VLSIarchitecture for lifting-based forward and inverse wavelet transform [J]. IEEETransactions on Consumer Electronics,2005,51(2):379-385.
[143] Shi Guangming, Liu Weifeng, Zhang Liu, Li Fu. An efficient foldedarchitecture for lifting-based discrete wavelet transform [J]. IEEE Transactionson Circuits and Systems II: Express Briefs,2009,56(4):290-294.
[144]闫润强.十二导同步心电图自动分析系统信号预处理及诊断逻辑的研究[D].上海：上海交通大学，2002.
[145]汤征.引入异常心电节律分析的心拍分类算法研究[D].杭州：浙江大学，2008.
[146] Ubeyli Elif Derya. ECG beats classification using multiclass support vectormachines with error correcting output codes [J]. Digital Signal Processing: AReview Journal,2007,17(3):675-684.
[147] Zhang Hongjun. The research of ECG diagnosis system based on support vectormachines [J]. Journal of Convergence Information Technology,2011,6(3):35-45.
[148] Froese Tom, Hadjiloucas Sillas, Galv o Roberto K.H, etc. Comparison ofextrasystolic ECG signal classifiers using discrete wavelet transforms [J].Pattern Recognition Letters,2006,27(5):393-407.
[149] Gubbi J, Khandoker A, Palaniswami M. Classification of obstructive and centralsleep apnea using wavelet packet analysis of ECG signals [J]. Computers inCardiology,2009,(36):733-736.
[150] Lin Chia-Hung. Classification enhancible grey relational analysis for cardiacarrhythmias discrimination [J]. Medical and Biological Engineering andComputing,2006,44(4):311-320.
[151] Sajedin Atena, Zakernejad Shokoufeh, Faridi Soheil, etc. A trainable neuralnetwork ensemble for ECG beat classification [J].2011,(70):788-794.
[152] Ubeyli, Elif Derya. Recurrent neural networks with composite features fordetection of electrocardiographic changes in partial epileptic patients [J].Computers in Biology and Medicine,2008,38(3):401-410.
[153] Ceylan Rahime. Ozbay Yüksel. Comparison of FCM, PCA and WT techniquesfor classification ECG arrhythmias using artificial neural network [J]. ExpertSystems with Applications,2007,33(2):286-295.
[154] Mehta S.S, Sharma Swati, Lingayat N.S. Development of FCM based algorithmfor the delineation of QRS-complexes in electrocardiogram [C]. Coimbatore,India:2009World Congress on Nature and Biologically Inspired Computing,2009:754-759.
[155] Ozbay,Yüksel; Ceylan, Rahime; Karlik, Bekir. Integration of type-2fuzzyclustering and wavelet transform in a neural network based ECG classifier [J].Expert Systems with Applications,2011,38(1):1004-1010.
[156]林泽涛,葛耀峥.心律失常的聚类分析研究[J].生物医学工程杂志,2006,23(5):999-1002.
[157]刘世雄.基于模糊聚类算法对心电数据典型特征分类研究[D].杭州：浙江大学,2006.
[158]岳清华.动态心电图波形聚类策略研究[D].天津:天津理工大学,2007.
[159]严峻.模糊聚类算法应用研究[D].杭州：浙江大学,2006.
[160] Zadeh L A. Fuzzy sets [J]. Inf. Control,1965,8:338-353.
[161] Zadeh J C. Cluster validity with fuzzy sets [J]. Journal of Cybernetics,1974,3(3):58-72.
[162] Shannon C E. A mathematical theory of communication [J]. Bell Syst Teeh,1948,XXVll(3):379-423.
[163] Ravi V.1, Bin Ma., Kumar P. Ravi. Threshold accepting based fuzzy clusteringalgorithms [J]. International Journal of Uncertainty, Fuzziness andKnowlege-Based Systems,2006,14(5):617-632.
[164] Vendramin L, Campello R.J.G.B, Coletta L.F.S, Hruschka E.R. Distributed fuzzyclustering with automatic detection of the number of clusters [J]. Advances inIntelligent and Soft Computing,2011,(91):133-140.
[165]彭勇,吴友情.一种新的聚类有效性函数[J].计算机工程与应用2010,46(6):124-126.
[166] Ruspini E H. A new approach to clustering [J]. Inf. cont.,1969,15(1):22-32.
[167] Bezdek J C, Hathaway R J, Sabin M J, et al. Convergence theory for fuzzyc-means: Counter-examples and repairs [J]. IEEE SMC1987，17(5):873-874.
[168] Pal N R, Bezdek J C,.On cluster validity for the fuzzy c-means model [J]. IEEEFuzzy System,1995，3(3):370.
[169] Chan K P, Cheung Y S. Modified fuzzy SODATA for the classification ofhandwritten Chinese charaeters [C]. Proc int conf Chinese comput,Singapore,1986,361-364.
[170] Wu, Kuo-Lung. Analysis of parameter selections for fuzzy c-means [J]. PatternRecognition,2012,45(1):407-415.
[171] Ghodsi, Ali. Efficient parameter selection for system identification [C]. AnnualConference of the North American Fuzzy Information Processing Society-NAFIPS,2004,2:750-755.
[172]严峻.模糊聚类算法应用研究[D].杭州：浙江大学,2006.
[173]林泽涛.心电信号在线数据知识化研究[D].杭州：浙江大学，2005
[174]陈兵兵.心电信号实时检测算法与应用研究[D].武汉：华中科技大学,2009.
[175]高彩虹.心电信号临床信息的自动识别研究[D].镇江：江苏大学,2010.