房性心律失常识别和房颤自发终止预测研究
|
摘要
心电信号是心脏兴奋的发生、传播和恢复过程的客观指标。通过分析心电信号自动区分不同类别的心律失常，对自动除颤器等治疗心律失常的设备至关重要。但是目前的大多数方法只提取单个特征参数，识别的错误率较高。而基于多参数的方法虽然其识别准确率有所提高，但由于往往只提取心电信号某一方面的特征信息，识别准确率的提高仍然十分有限。另一方面，在房性心律失常中，房颤是临床上最常见的心脏紊乱，它将加大病人中风和血栓的风险。预测房颤有可能自发终止或持续，不仅可以更好地了解房颤发作终止的机制，还可以避免不必要的治疗和更加有效地治疗持续房颤。但是目前预测房颤终止较成功的方法基本都是仅从频域的角度提取房颤信号的特征，预测准确率不高。
本论文主要研究了心电信号处理新方法及其在房性心律失常识别和预测房颤自发终止方面的应用，抓住特征提取和模式识别这两个心电信号分析中的关键问题，以提高房性心律失常识别和房颤自发终止预测的准确率为目标，重点研究了以下几个方面的问题：
1、在时间域、频率域和时频域三个方面提取心电信号及其RR间期的线性特征参数的基础上，用替代数据法证明了房性心律失常心电信号及其RR间期时间序列具有非线性，并重点从符号动力学、相空间、庞加莱图和递归图等非线性角度提取能反映心电信号特征的参数：1)、采用符号动力学研究心电信号特征时，先将心电信号符号化为符号串，然后对符号串序列编码得到符号码，取符号码的发生概率来描述心电信号的确定性结构。采用符号动力学研究RR间期差序列特征时，先对RR间期差二值符号化，由于其符号的改变反映了RR间期序列的局部极大或极小点，因此提取RR间期差符号序列的子串长度概率分布熵来反映RR间期变化的不规则程度，以更好地揭示心脏的动力学特性；2)、通过重构心电信号相空间，分别从几何和信息论的角度提取相空间点的密度分布熵作为特征，不仅减少了特征向量的冗余信息，而且大大减少了下一步模式识别的计算量；3)、通过构建心电信号的庞加莱图，从几何和计算机视觉的角度提取能反映庞加莱图特性的参数，加深了对房颤期间心率变化的生理理解；4)、研究定量递归分析技术量化心电信号递归图，指出房颤信号递归图特征能反映房颤时心房活动的动力学复杂特性，含有能区分不同终止类型房颤的信息。
2、从模糊支持向量机、模糊分类器、基于神经网络的融合分类器和基于灰关联度的k近邻法研究心电信号的模式识别：1)、为抑制噪声对分类器的影响，在支持向量机中引入模糊概念，在特征空间中对训练样本赋予不同的隶属度，更好地表示每个点对特征空间中决策面构造的贡献，提高了支持向量机的分类性能；2)、采用模糊分类器，最终输出结果用隶属度函数来表示观察对象属于特定类别的程度，避免了整个模式识别系统非此即彼的判别模式，结果更符合人类的思维习惯；3)、研究了将心电信号不同特征信息融合分类的方法，提出基于神经网络的多分类器融合方法，充分发挥单个分类器的长处并抑制其短处，性能与单个分类器相比有较大提高；4)、根据心电信号既含有确定信息又包含不确定信息、符合灰色系统研究对象的特点，提出基于灰关联度的k近邻法，分类性能明显高于常规k近邻法。
3、用两个心电数据库来研究论文提出的房性心律失常识别方法的性能，一个为MIT-BIH心律失常数据库，另一个为犬心外膜信号数据库。提取房性心律失常心电信号的时域、频域、时频域、相空间和符号动力学特征，基于这些特征分别建立模糊分类器和神经网络融合模糊分类器进行心律失常的识别，结果表明：非线性特征比线性特征含有更能反映及区分房性心律失常的特征，而神经网络融合分类器的方法能对单个分类器扬长避短，性能有提高。其识别MIT数据库中窦性、房颤和房扑信号的准确率分别为98％，99．3％和97．3％；识别犬数据库中窦性、房颤和房扑信号的准确率分别为98．3％，98．3％和99．3％。与已有算法相比，论文提出的算法通用性强，对不同类型数据库中心电信号识别均具有较高的正确率，有望用于治疗心律失常的自动装置。
4、用PhysioNet提供的房颤数据库来评价论文提出房颤自发终止预测算法的性能。提取房颤信号RR间期时域统计特征和庞加莱图特征作为一组特征，递归图特征作为另一组特征，基于这两组特征分别用模糊支持向量机和灰关联度k近邻法预测房颤的自发终止，结果表明：这两组特征预测房颤终止均具有较高的性能，但总体比较，基于递归图的特征略胜一筹，说明递归图携带了更多能区分不同终止类型房颤的信息。将模糊支持向量机、基于灰关联度的k近邻法分别与传统支持向量机、传统k近邻法相比，它们预测房颤自发终止的性能均有大幅提高。而模糊支持向量机比基于关联度k近邻法预测房颤终止的性能更好，因此最终选择了基于递归图特征的模糊支持向量机方法来预测房颤自发终止。其对训练集和测试集中不终止和立即终止房颤、马上终止和立即终止房颤的预测准确率均达到了100％；对训练集中不终止和马上终止房颤的预测准确率达到100％；对测试集中的不终止和马上终止房颤的预测准确率为96．2％。与已有方法相比，其性能有了较大的提高，可以较准确地预测房颤的自发终止。
Electrocardiogram (ECG) can objectively reflect the occurrence,the propagationand the recover process of the heart excitation.Some automatic devices such asimplantable cardioverter defibrillator (ICD) are used to cure cardiac arrhythmias.It isimportant for them to discriminate different cardiac arrhythmias based on the ECGanalysis.However,most of present methods only extract one feature which leads to ahigh error rate.Methods based on multi-features can improve the discriminationaccuracy but limitedly because they characterize ECG just from one aspect.On theother hand,atrial fibrillation (AF) is the most common atrial arrhythmias whichincreases risks of infarctions and stroke.It is important to predict whether paroxysmalAF is likely to terminate spontaneously or be sustained.This may lead to betterunderstanding of the lnechanism of the arrhythmia.It can also avoid unnecessarytherapy and provide effective therapy.However,present methods almost extractfeatures of AF just from the frequency aspect and the prediction accuracy is not high.
This dissertation mainly studies novel signal processing methods for the ECGanalysis and their application in the identification of atrial arrhythmias and predictionof spontaneous termination of AF.In order to improve the accuracy for atrialarrhythmias identification and AF termination,features extraction and patternrecognition,these two critical problems in the ECG analysis are focused in thisdissertation,and the following aspects are mainly studied.
1.Firstly,linear features of ECG signals and RR interval are extracted fromtime-domain,frequency-domain and time-frequency domain respectively.Then ECGand RR interval series of atrial arrhythmias are proved as nonlinear by surrogate datamethod.Nonlinear features that can reflect characters of ECG are mainly studied withsymbolic dynamics,state space,Poincare plot and recurrence plot methods.1).ECGis firstly symbolized to symbolic string when studied with symbolic dynamics.Thesymbolic string is coded as the symbolic code.The occurrence probability of thesymbolic code is extracted to characterize the determinate structure of ECG.Thedifference of RR interval is also studied.It is symbolized to two signs.Shannonentropy of the probability distribution of sign sequence's substring length is extractedto reflect the irregularity of RR intervals' variation because the change of signsrepresents local maximum and minimum of RR interval.It can reveal dynamiccharacters of the heart.2) The state space of ECG is reconstructed and the entropy ofthe distribution of point density in the state space is taken as the feature from geometric and informationic point of view.It not only reduces the redundantinformation of the feature vector but also reduce the computation complexity for thefollowing pattern recognition.3) Poincare plot of ECG is constructed and several newfeatures are proposed to reflect geometrical features of Poincare plot with computervision methods.They have potential ability for the physiological interpretation of theheart rate variation during AF.4) The recurrence plot analysis technique is introducedto characterize the recurrence plot of ECG,experiment demonstrates that recurrenceplot features give some insight into the dynamics and complex patterns of theactivation of atrium during AF,they contain discrimination information among AFwith different termination patterns.
2.The fuzzy support vector machine (FSVM),the fuzzy classifier,the fusionclassifier based on neural network and the k nearest neighbour based on the greycorrelation are studied for the pattern recognition of ECG.1) In order to inhibit theeffect of noise,the fuzzy concept is introduced into the support vector machine(SVM).Training samples in the feature space are given different membership valuesto represent the contribution of each sample to the construction of the decision planein the feature space more precisely.It improves the performance of the traditionalSVM.2) In the utilized fuzzy classifier,its final output is the membership functionwhich is used to represent the degree of objective belonging to a given class.Itcomplies with logic habits of human beings,3) The method to fuse different featuresof ECG is studied and the classifier fusion method based on the neural network isproposed.It can strengthen the advantage of individual classifiers and reduce theirweakness.It also leads to the greater performance improvement compared withindividual classifiers.4) ECG contains not only determinate but also undeterminateinformation.It complies with characters of the grey system's study objective.The knearest neighbour is proposed based on the grey correlation.It achieves the higherclassification performance compared with the traditional k nearest neighbour.
3.Two databases are used to evaluate the performance of proposed methods foratrial arrhythmias identification.One is the MIT-BIH arrhythmias database and theother is the canine endocardial database.Features based on time-domain,frequency-domain,time-frequency domain,state space and symbolic dynamics areextracted.Based on these features,the neural network based fusion classifier andindividual fuzzy classifier are respectively used for atrial arrhythmias identification.Results demonstrate that nonlinear features contain more information than linear ones that can distinguish different atrial arrhythnias.The neural network based fusionclassifier can strengthen individual classifier's advantage and inhibit their weakness toimprove the performance.Its accuracy to identify sinus rate (SR),AF and atrial flutter(AFL) in MIT database is 98%,99.3% and 97.3% respectively,while its accuracy toidentify SR,AF and AFL in canine database is 98.3%,98.3% and 99.3% respectively.It justifies that the proposed algorithm has the good generality compared to previousmethods.It can discriminate ECG signals from different type of databases with thehigher accuracy and is expected to be used in automatic devices for atrial arrhythmiastherapy.
4.AF database provided by PhysioNet is used to evaluate the performance ofproposed methods for AF termination prediction.Time-domain features of RR intervaland Poincare plot features are extracted as a feature group and recurrence plot featuresare extracted as the other feature group.The FSVM and the k nearest neighbour basedon the grey correlation are then utilized based on these two feature groups for AFtermination prediction.It justifies that these two feature groups achieve the goodperformance.The recurrence plot features perform better which demonstrates that theycan provide more information to distinguish AF with different termination properties.The FSVM and the k nearest neighbour based on the grey correlation achieve the higherperformance compared with the traditional SVM and the traditional k nearest neighbourrespectively.The FSVM's performance is higher than the k nearest neighbour based onthe grey correlation.Finally the FSVM is selected for AF termination prediction.Itsprediction accuracy for non-terminating (N) and immediately-terminating (T) AF,soon-terminating (S) and T AF in the training and testing data set all achieve 100%.Itsprediction accuracy for N and S AF in the training data set is 100%.Its predictionaccuracy for N and S AF in the testing data set is 96.2%.It achieves the higherperformance compared with previous methods and can predict the termination of AFaccurately.
本论文主要研究了心电信号处理新方法及其在房性心律失常识别和预测房颤自发终止方面的应用，抓住特征提取和模式识别这两个心电信号分析中的关键问题，以提高房性心律失常识别和房颤自发终止预测的准确率为目标，重点研究了以下几个方面的问题：
1、在时间域、频率域和时频域三个方面提取心电信号及其RR间期的线性特征参数的基础上，用替代数据法证明了房性心律失常心电信号及其RR间期时间序列具有非线性，并重点从符号动力学、相空间、庞加莱图和递归图等非线性角度提取能反映心电信号特征的参数：1)、采用符号动力学研究心电信号特征时，先将心电信号符号化为符号串，然后对符号串序列编码得到符号码，取符号码的发生概率来描述心电信号的确定性结构。采用符号动力学研究RR间期差序列特征时，先对RR间期差二值符号化，由于其符号的改变反映了RR间期序列的局部极大或极小点，因此提取RR间期差符号序列的子串长度概率分布熵来反映RR间期变化的不规则程度，以更好地揭示心脏的动力学特性；2)、通过重构心电信号相空间，分别从几何和信息论的角度提取相空间点的密度分布熵作为特征，不仅减少了特征向量的冗余信息，而且大大减少了下一步模式识别的计算量；3)、通过构建心电信号的庞加莱图，从几何和计算机视觉的角度提取能反映庞加莱图特性的参数，加深了对房颤期间心率变化的生理理解；4)、研究定量递归分析技术量化心电信号递归图，指出房颤信号递归图特征能反映房颤时心房活动的动力学复杂特性，含有能区分不同终止类型房颤的信息。
2、从模糊支持向量机、模糊分类器、基于神经网络的融合分类器和基于灰关联度的k近邻法研究心电信号的模式识别：1)、为抑制噪声对分类器的影响，在支持向量机中引入模糊概念，在特征空间中对训练样本赋予不同的隶属度，更好地表示每个点对特征空间中决策面构造的贡献，提高了支持向量机的分类性能；2)、采用模糊分类器，最终输出结果用隶属度函数来表示观察对象属于特定类别的程度，避免了整个模式识别系统非此即彼的判别模式，结果更符合人类的思维习惯；3)、研究了将心电信号不同特征信息融合分类的方法，提出基于神经网络的多分类器融合方法，充分发挥单个分类器的长处并抑制其短处，性能与单个分类器相比有较大提高；4)、根据心电信号既含有确定信息又包含不确定信息、符合灰色系统研究对象的特点，提出基于灰关联度的k近邻法，分类性能明显高于常规k近邻法。
3、用两个心电数据库来研究论文提出的房性心律失常识别方法的性能，一个为MIT-BIH心律失常数据库，另一个为犬心外膜信号数据库。提取房性心律失常心电信号的时域、频域、时频域、相空间和符号动力学特征，基于这些特征分别建立模糊分类器和神经网络融合模糊分类器进行心律失常的识别，结果表明：非线性特征比线性特征含有更能反映及区分房性心律失常的特征，而神经网络融合分类器的方法能对单个分类器扬长避短，性能有提高。其识别MIT数据库中窦性、房颤和房扑信号的准确率分别为98％，99．3％和97．3％；识别犬数据库中窦性、房颤和房扑信号的准确率分别为98．3％，98．3％和99．3％。与已有算法相比，论文提出的算法通用性强，对不同类型数据库中心电信号识别均具有较高的正确率，有望用于治疗心律失常的自动装置。
4、用PhysioNet提供的房颤数据库来评价论文提出房颤自发终止预测算法的性能。提取房颤信号RR间期时域统计特征和庞加莱图特征作为一组特征，递归图特征作为另一组特征，基于这两组特征分别用模糊支持向量机和灰关联度k近邻法预测房颤的自发终止，结果表明：这两组特征预测房颤终止均具有较高的性能，但总体比较，基于递归图的特征略胜一筹，说明递归图携带了更多能区分不同终止类型房颤的信息。将模糊支持向量机、基于灰关联度的k近邻法分别与传统支持向量机、传统k近邻法相比，它们预测房颤自发终止的性能均有大幅提高。而模糊支持向量机比基于关联度k近邻法预测房颤终止的性能更好，因此最终选择了基于递归图特征的模糊支持向量机方法来预测房颤自发终止。其对训练集和测试集中不终止和立即终止房颤、马上终止和立即终止房颤的预测准确率均达到了100％；对训练集中不终止和马上终止房颤的预测准确率达到100％；对测试集中的不终止和马上终止房颤的预测准确率为96．2％。与已有方法相比，其性能有了较大的提高，可以较准确地预测房颤的自发终止。
Electrocardiogram (ECG) can objectively reflect the occurrence,the propagationand the recover process of the heart excitation.Some automatic devices such asimplantable cardioverter defibrillator (ICD) are used to cure cardiac arrhythmias.It isimportant for them to discriminate different cardiac arrhythmias based on the ECGanalysis.However,most of present methods only extract one feature which leads to ahigh error rate.Methods based on multi-features can improve the discriminationaccuracy but limitedly because they characterize ECG just from one aspect.On theother hand,atrial fibrillation (AF) is the most common atrial arrhythmias whichincreases risks of infarctions and stroke.It is important to predict whether paroxysmalAF is likely to terminate spontaneously or be sustained.This may lead to betterunderstanding of the lnechanism of the arrhythmia.It can also avoid unnecessarytherapy and provide effective therapy.However,present methods almost extractfeatures of AF just from the frequency aspect and the prediction accuracy is not high.
This dissertation mainly studies novel signal processing methods for the ECGanalysis and their application in the identification of atrial arrhythmias and predictionof spontaneous termination of AF.In order to improve the accuracy for atrialarrhythmias identification and AF termination,features extraction and patternrecognition,these two critical problems in the ECG analysis are focused in thisdissertation,and the following aspects are mainly studied.
1.Firstly,linear features of ECG signals and RR interval are extracted fromtime-domain,frequency-domain and time-frequency domain respectively.Then ECGand RR interval series of atrial arrhythmias are proved as nonlinear by surrogate datamethod.Nonlinear features that can reflect characters of ECG are mainly studied withsymbolic dynamics,state space,Poincare plot and recurrence plot methods.1).ECGis firstly symbolized to symbolic string when studied with symbolic dynamics.Thesymbolic string is coded as the symbolic code.The occurrence probability of thesymbolic code is extracted to characterize the determinate structure of ECG.Thedifference of RR interval is also studied.It is symbolized to two signs.Shannonentropy of the probability distribution of sign sequence's substring length is extractedto reflect the irregularity of RR intervals' variation because the change of signsrepresents local maximum and minimum of RR interval.It can reveal dynamiccharacters of the heart.2) The state space of ECG is reconstructed and the entropy ofthe distribution of point density in the state space is taken as the feature from geometric and informationic point of view.It not only reduces the redundantinformation of the feature vector but also reduce the computation complexity for thefollowing pattern recognition.3) Poincare plot of ECG is constructed and several newfeatures are proposed to reflect geometrical features of Poincare plot with computervision methods.They have potential ability for the physiological interpretation of theheart rate variation during AF.4) The recurrence plot analysis technique is introducedto characterize the recurrence plot of ECG,experiment demonstrates that recurrenceplot features give some insight into the dynamics and complex patterns of theactivation of atrium during AF,they contain discrimination information among AFwith different termination patterns.
2.The fuzzy support vector machine (FSVM),the fuzzy classifier,the fusionclassifier based on neural network and the k nearest neighbour based on the greycorrelation are studied for the pattern recognition of ECG.1) In order to inhibit theeffect of noise,the fuzzy concept is introduced into the support vector machine(SVM).Training samples in the feature space are given different membership valuesto represent the contribution of each sample to the construction of the decision planein the feature space more precisely.It improves the performance of the traditionalSVM.2) In the utilized fuzzy classifier,its final output is the membership functionwhich is used to represent the degree of objective belonging to a given class.Itcomplies with logic habits of human beings,3) The method to fuse different featuresof ECG is studied and the classifier fusion method based on the neural network isproposed.It can strengthen the advantage of individual classifiers and reduce theirweakness.It also leads to the greater performance improvement compared withindividual classifiers.4) ECG contains not only determinate but also undeterminateinformation.It complies with characters of the grey system's study objective.The knearest neighbour is proposed based on the grey correlation.It achieves the higherclassification performance compared with the traditional k nearest neighbour.
3.Two databases are used to evaluate the performance of proposed methods foratrial arrhythmias identification.One is the MIT-BIH arrhythmias database and theother is the canine endocardial database.Features based on time-domain,frequency-domain,time-frequency domain,state space and symbolic dynamics areextracted.Based on these features,the neural network based fusion classifier andindividual fuzzy classifier are respectively used for atrial arrhythmias identification.Results demonstrate that nonlinear features contain more information than linear ones that can distinguish different atrial arrhythnias.The neural network based fusionclassifier can strengthen individual classifier's advantage and inhibit their weakness toimprove the performance.Its accuracy to identify sinus rate (SR),AF and atrial flutter(AFL) in MIT database is 98%,99.3% and 97.3% respectively,while its accuracy toidentify SR,AF and AFL in canine database is 98.3%,98.3% and 99.3% respectively.It justifies that the proposed algorithm has the good generality compared to previousmethods.It can discriminate ECG signals from different type of databases with thehigher accuracy and is expected to be used in automatic devices for atrial arrhythmiastherapy.
4.AF database provided by PhysioNet is used to evaluate the performance ofproposed methods for AF termination prediction.Time-domain features of RR intervaland Poincare plot features are extracted as a feature group and recurrence plot featuresare extracted as the other feature group.The FSVM and the k nearest neighbour basedon the grey correlation are then utilized based on these two feature groups for AFtermination prediction.It justifies that these two feature groups achieve the goodperformance.The recurrence plot features perform better which demonstrates that theycan provide more information to distinguish AF with different termination properties.The FSVM and the k nearest neighbour based on the grey correlation achieve the higherperformance compared with the traditional SVM and the traditional k nearest neighbourrespectively.The FSVM's performance is higher than the k nearest neighbour based onthe grey correlation.Finally the FSVM is selected for AF termination prediction.Itsprediction accuracy for non-terminating (N) and immediately-terminating (T) AF,soon-terminating (S) and T AF in the training and testing data set all achieve 100%.Itsprediction accuracy for N and S AF in the training data set is 100%.Its predictionaccuracy for N and S AF in the testing data set is 96.2%.It achieves the higherperformance compared with previous methods and can predict the termination of AFaccurately.
引文
[1] Benjamin EJ, Wolff PA, D'Agostino RB, Silbershatz H, Kannel WB, Levy D. Impact of atrial fibrillation on the risk of death: the Framingham Heart Study [J]. Circulation, 1998, 98: 946-952.
[2] Chugh SS, Blackshear JL, Shen WK, Hammill SC, Gersh BJ. Epidemiology and natural history of atrial fibrillation: clinical implications [J]. J Am Coll Cardiol, 2001, 37:371-377.
[3] Wellens HJ, Lau CP, Luderitz B, Akhtar M, Waldo AL, Camm AJ, Timmermans C, Tse HF,Jung W, Jordaens L, Avers G. Atrioverter: an implantable device for the treatment of atrial fibrillation [J]. Circulation, 1998,98:1651-1656.
[4] Al-Khatib SM, Wilkinson WE, Sanders LL, McCarthy EA, Pritchett EL. Observations on the transition from intermittent to permanent atrial fibrillation [J]. Am Heart J, 2000, 140:142-145.
[5] Botteron GW, Smith JM. Quantitative assessment of the spatial organization of atrial fibrillation in the intact human heart [J]. Circulation, 1996, 93: 513-518.
[6] Botteron Gw, Smith JM. A technique for measurement of the extent of spatial organization of atrial activation during atrial fibrillation in the intact human heart [J]. IEEE Trans Biomed Eng.1995,42:579-586.
[7] Chen SW, Clarksom PM, Fan Q. A robust sequential detection algorithm for cardiac arrhythmia classification [J]. IEEE Trans Biomed Eng, 1996, 43:1120-1125.
[8] Sih HJ, Zipes DP, Berbari EJ, Olgin JE. A high-temporal resolution algorithm for quantifying organization during atrial fibrillation [J]. IEEE Trans Biomed Eng, 1999, 46:440-450.
[9] Swerdlow CD, Schsls W, Dijkman B, Jung W, Sheth NV. Detection of atrial fibrillation and flutter by a dual-chamber implantable cardioverter defibrillator [J]. Circulation, 2000, 101:878-885.
[10] Faes L, Nolio G, Antolini R, Gaita F, Ravelli F. A method for quantifying atrial fibrillation organization based on wave-morphology similarity [J]. IEEE Trans Biomed Eng, 2002, 49:1504-1513.
[11] Narayan SM, Valmik B. Temporal and spatial phase analyses of the electrocardiogram stratify intra-atrial and intra-ventricular organization [J]. IEEE Trans Biomed Eng, 2004,51:1749-1764.
[12] Ropella KM, Sahakian AV, Baerman JM, Swiryn S. The coherence spectrum: a quantitative discriminator of fibrillatory and nonfibrillatory cardiac rhythms [J]. Circulation, 1989, 80:112-119.
[13] Chen SW. A two-stage discrimination of cardiac arrhythmias using a total least squares-based prony modeling algorithm [J]. IEEE Trans Biomed Eng, 2000, 47:1317-1327.
[14] Everett TH. KoK LC, Vaughn RH, Moorman JR., Haines DE. Frequency domain algorithm for quantifying atrial fibrillation organization to increase defibrillation efficacy [J]. IEEE Trans Biomed Eng, 2001, 48: 969 -978.
[15] Khadra L, Al-Fahoum AS, Binajjaj S. A quantitative analysis approach for cardiac arrhythmia classification using higher order spectral techniques [J]. IEEE Trans Biomed Eng,2005,52: 1840-1845.
[16] Lovett EG, Ropella KM. Time-frequency coherence analysis of atrial fibrillation termination during procainamide administration [J]. Ann Biomed Eng, 1997, 25: 975-984.
[17] Stridth M, Sornmo L, Meurling CJ, Olsson SB. Characterization of atrial fibrillation using the surface ECG: time-dependent spectral properties [J]. IEEE Trans Biomed Eng, 2001, 48: 19-27.
[18] Zhang XS, Zhu YS, Thakor NV, Wang ZZ. Detecting ventricular tachycardia and fibrillation by complex measure [J]. IEEE Trans Biomed Eng, 1999, 46:548-555.
[19]Hosseini HG, Luo D, Reynolds KJ. The comparison of different feed forward neural network architecture for ECG signal diagnosis [J]. Medical Engineering & Physics, 2006, 28(4):372-378.
[20] Ciaccio E, Dunn S, Akay M. Biosignal pattern recognition and interpretation systems [J].IEEE Eng in Med and Bio Mag, 1993, 12(3): 89-95.
[21] Langley P, Bourke JP, Murray A. Frequency analysis of atrial fibrillation [J]. Comput Cardiol,2000, 27: 65-72.
[22] Petrutiu S, Sahakian AV, Ng J, Swiryn S. Analysis of the surface electrocardiogram to predict termination of atrial fibrillation: the 2004 Computers in Cardiology/Physionet Challenge [J].Comput Cardiol, 2004, 31:105-108.
[23] Hayn D, Edegger K, Scherr D, Lercher P, Rotman B, Klein W, Schreier G. Automated prediction of spontaneous termination of atrial fibrillation from electrocardiograms [J]. Comput Cardiol, 2004, 31:117-120.
[24] Cantini F, Conforti F, Varanini M, Chiarugi F, Vrouchos G. Predicting the end of an atrial fibrillation episode: the PhysioNet challenge [J]. Comput Cardiol, 2004, 31: 121-124.
[25] Sih HJ, Zipes DP, Berbari EJ, Olgin JE. A high-temporal resolution algorithm for quantifying organization during atrial fibrillation [J]. IEEE Trans Biomed Eng, 1999, 46: 440-450.
[26] Kao T, Su YY, Tso HW, Lin YC, Chen SA, Tai CT. Nonlinear analysis of human atrial flutter and fibrillation using the surface electrocardiogram [J]. Comput Cardiol, 2004, 31:441-444.
[27] Roberts FM, Povinelli RJ. A statistical feature based approach to predicting termination of atrial fibrillation [J]. Comput Cardiol, 2004, 31: 673-676.
[28] Mainardi LT, Matteucci M, Sassi R. On predicting the spontaneous termination of atrial fibrillation episodes using linear and non-linear parameters of ECG signals and RR series [J].Comput Cardiol, 2004, 31: 665-668.
[29] Nilsson F, Stridh M, Bollmann A, Sornmo L. Predicting spontaneous termination of atrial fibrillation using the surface ECG [J]. Med Eng Phys, 2006, 28: 802-808.
[30] Langley P, Allen J, Bowers EJ, Drinnan MJ, Garcia EV, King ST, Olbrich T, Sims AJ, Smith FE, Wild J, Zheng D, Murray A. Analysis of RR interval and fibrillation frequency and amplitude for predicting spontaneous termination of atrial fibrillation [J]. Computers in Cardiology, 2004, 31:637-640.
[31] Stridh M, Sornmo L, Meurling CJ, Olsson SB. Sequential characterization of atrial tachyarrhythmias based on ECG time-frequency analysis [J]. IEEE Trans Biomed Eng, 2004, 51:110-114.
[32] Nilsson F, Stridh M, Bollmann A, Sornmo L. Predicting spontaneous termination of atrial fibrillation with time-frequency information [J]. Comput Cardiol, 2004, 31: 657-660.
[33] Goldberger AL, Amaral LAN, Hausdorff JM, Ivanov PCh, Mark RG, Mietus JE, Moody GB,Peng CK, Stanley HE. PhysioBank, PhysioToolkit, and PhysioNet: components of a new research resource for complex physiologic signals [J]. Circulation, 2000, 101: e215-220.
[34] Friesen GM, Jannett TC, Jadallah MA, Yates SL, Quint SR, Nagle HT. A comparision of the noise sensitivity of nine QRS detection algorithms [J]. IEEE Tran Biomed Eng, 1990, 37: 85-98.
[35] Shkurovich S, Sahakian AV, Swiryn S. Detection of atrial activity from high-voltage leads of implantable ventricular defibrillators using a cancellation technique [J]. IEEE Trans Biomed Eng,1998.45:229-234.
[36] Petretta M, Bonaduce D, Spinelli L, Vicario ML, Nuzzo V, Marciano F, Camuso P, De Sanctis V, Lupoli G. Cardiovascular hemodynamics and cardiac autonomic control in patients with subclinical and overt hyperthyroidism [J]. Eur J Endocrinol. 2001, 145: 691- 696.
[37] Osman F, Franklyn JA, Daykin J, Chowdhary S, Holder R, Sheppard M, Gammage M. Heart rate variability and turbulence in hyperthyroidism before, during, and after treatment [J]. Am J Cardiol, 2004, 94: 465-469.
[38] Xu W, Tse HF, Chan FY, Fung PW, Lee KF, Lau CP. New Bayesian discriminator for detection of atrial tachyarrhythmias [J]. Circulation, 2002, 105(12):1472-1479.
[39] Chen JL, Chiu HW, Tseng YJ, Chu WC. Hyperthyroidism is characterized by both increased sympathetic and decreased vagal modulation of heart rate: evidence from spectral analysis of heart rate variability [J]. Clin Endocrinol, 2006, 64: 611-616.
[40] Goldberger AL, Amaral LAN, Hausdorff JM, Ivanov PH, Peng CK, Stanley HE. Fractal dynamics in physiology; alterations with disease and aging [C]. Proceedings of the National Academy of Sciences of the United States of America,2002,99(suppl 1):2466-2472.
[41]Stein KM,Lippman N,Kligfield P.Fractal rhythms of the heart[J].J Electrocardiol,1992,24(suppl):72-76.
[42]Mainardi LT,Porta A,Calcagnini G,Bartolini P,Michelucci A,Cerutti S.Linear and nonlinear analysis of atrial signals and local activation period series during atrial fibrillation episodes[J].Med Biol Eng Comput,2001,39:249-254.
[43]Kao T,Su YY,Tso HW,Lin YC,Chen SA,Tai CT.Nonlinear analysis of human atrial flutter and fibrillation using the surface electrocardiogram[J].Comput Cardiol,2004,31:441-444
[44]张贤达．现代信号处理[M]．北京：清华大学出版社，1998．
[45]Daubechies I.Orthonormal bases of compactly supported wavelets[J].Comm Pure Appl Math,1988,41:909-996.
[46]Mallat SG.A theory for multiresolution signal decomposition:the wavelet represention[J].IEEE Trans Pattern Anal Mach Intell,1989,11:674-693.
[47]Chui CK,Wang JZ.A Cardinal Spline Approach to wavelets[J].Proc Amer Math Soc,1991,113:785-793.
[48]Melkonian D,Blumenthal TD,Meares R.High-resolution fragmentary decomposition-a model-based method of non-stationary electrophysiological signal,analysis[J].Journal of neuroscicnce methods,2003,131:149-159.
[49]洛伦兹EN．混沌的本质[M]．北京：气象出版社，1997．
[50]卢侃，孙建华，欧阳容百．混沌动力学[M]．上海：远东出版社，1990．
[51]Parker TS,Chua LO.Chaos:a tutorial for engineers[J].Processing of IEEE,1987,75:982-1008.
[52]Moon FC.Chaotic and fractal dynamics[M].Wiley,1992.
[53]Kantz H,Schreiber T.Nonlinear time series analysis[M].Cambridge University Press,1997.
[54]李颖洁．脑电信号动力学特性分析及其在精神分裂症中的应用研究[D]．上海：上海交通大学，2001．
[55]张绪省．心室纤颤动力学的动力学的非线性分析及应用研究[D]．上海：上海交通大学，1997．
[56]Goldberger AL.Non-linear dynamics for clinicians:chaos theory,fractals,and complexity at the bedside[J].Lancet,1996,347:1312-1314.
[57]Vibe K,Vesin JM.On chaos detection methods[J].International Journal of Bifurcation and Chaos,1996,6(3):529-543.
[58]Theiler J,Eubank S,Longtin A,Galdrikian B,Farmer JD.Testing for nonlinearity in time series:the method of surrogate data[J].Physica D,1992,58:77-94.
[59]刘秉正，彭建华．非线性动力学[M]．北京：高等教育出版社，2004：454-464．
[60]Devamey RL.Chaotic dynamical systems[M].New York:Addison-Wesley,1989.
[61]Jaclson EA.Perspectives of nonlinear dynamics[M].Cambridge England:Cambridge University Press,1989.
[62]Baumert M,Walther T,Hopfe J,Stepan H,Faber R,Voss A.Joint symbolic dynamic analysis of beat-to-beat interactions of heart rate and systolic blood pressure in normal pregnancy[J].Med Biol Eng Comput,2002,40:241-245.
[63]Crutchfield JP,Packaed NH.Symbolic dynamics of noisy chaos[J].Physica D,1983,7:201-223.
[64]Shannon CE,A mathematical theory of communication[J].The Bell System Technical Journal,1948,27:379-423.
[65]Packard NH,Crutchfield JP,Farmer JD,Shaw RS.Geometry from a time series[J].Phys Rev Lett,1980,45:712-716.
[66]Takens F.Detecting strange attractors in turbulence[J].Lect Notes Math,1981,898:366-381.
[67]吕金虎，陆君安，陈士华．混沌时间序列分析及其应用[M]．武昌：武汉大学出版社，2002．
[68]Hegger R,Kantz H,Schreiber T.Practical implementation of nonlinear time series methods:the TISEAN package[J].Chaos,1999,9:413-435.
[69]Piskorski J,Guzik P.Geometry of the Poincare plot of RR intervals and its asymmetry in healthy adults[J].Physiol Meas,2007,28:287-300.
[70]Gleik J.Chaos:making a new science[M].New York:Viking Penguin Inc,1987.
[71]Brennan M,Palaniswami M,Kamen P.Do existing measures of Poincare plot geometry reflect nonlinear features of heart rate variability?[J]IEEE Trans Biomed Eng,2001,48:1342-1347.
[72]Suyama AC,Sunagawa K,Sugimachi M,Anan T,Egashira K,Takeshita A.Differentiation between aberrant ventricular conduction and ventricular ectopy in atrial fibrillation using RR interval scattergram[J].Circulation,1993,88:2307-2314.
[73]Jolliffe I.Principal component analysis[M].New York:Springer-Verlag,1986.
[74]Gao JB.Detecting nonstationarity and state transitions in a time series[J].Physical Review E,2001,63:DOI:066202.
[75]Casdagli MC.Recurrence Plots Revisited[J].Physica D,1997,108:12-44.
[76]Riley MA,Balasubramaniam R,Turvey MT.Recurrence quantification analysis of postural fluctuations[J].Gait & Posture,1999,9:65-78.
[77] Marwan N, Wessel N, Meyerfeldt U, Schirdewan A, Kurths J. Recurrence-plot-based measures of complexity and their application to heart-rate-variability data [J]. Physical Review E,2002, 66: DOI: 026702.
[78] Faure P, Korn H. A new method to estimate the Kolmogorov entropy from recurrence plots: its application to neuronal signals [J]. Physica D-Nonlinear Phenomena, 1998, 122: 265-279.
[79] Tong H. Nonlinear time series analysis: a dynamical systems approach [M]. Oxford University Press, 1990.
[80] Eckmann JP, Ruelle D. Fundamental limitations for estimating dimensions and Lyapunov exponents in dynamical systems [J]. Physica (Amsterdam), 1992, 56: 185-185.
[81] Schreiber T. Interdisciplinary application of nonlinear time series methods [J]. Physics Reports-Review Section of Physics Letters, 1999, 308: 2-64.
[82] Eckmann JP, Kamphorst SO, Ruelle D. Recurrence plots of dynamical systems [J]. Europhys Lett, 1987, 5: 973-977.
[83] Zbilut JP, Webber J, Charles L. Embeddings and delays as derived from quantification of recurrence plots [J]. Physics Letters A, 1992,171: 199-203.
[84] Webber CL, Zbilut JP. Dynamical assessment of physiological systems and states using recurrence plot strategies [J]. J Appl Physiol, 1994, 76: 965-973.
[85] Gao JB, Cai HQ. On the structures and quantification of recurrence plots [J]. Physics Letters A, 2000, 270: 75-87.
[86] Gao JB. Recurrence time statistics for chaotic systems and their applications [J]. Physical Review letters, 1999, 83(16): 3178-3181.
[87] Cortes C, Vapnik VN. Support-vector networks [J]. Machine learning, 1995, 20:273-297.
[88] Lin CF, Wang SD. Fuzzy support vector machines [J]. IEEE Transaction on neural networks,2002, 13(2): 464-471.
[89] Zaden LA. Fuzzy sets [J]. Inf Control, 1965, 8: 338-353.
[90] Mitra S, Pal SK, Mitra P. Data mining in soft computing framework: a survey [J]. IEEE Trans Neural Networks, 2002, 13(1): 3-14.
[91] Kwan HK, Cai Y. A fuzzy neural network and its application to pattern recognition [J]. IEEE Trans Fuzzy Systems, 1994,2 (3): 185-193.
[92] Jiang XF, Yi Z, Lv JC. Fuzzy SVM with a new membership function [J]. Neural Comput & Applic, 2006, 15:268-276.
[93] Gupta L, Chung B, Srinath MD, Molfese DL, Kook H. Multichannel fusion models for the parametric classification of differential brain activity [J]. IEEE Transactions on Biomedical Engineering, 2005, 52 (11):1869-1881.
[94]Kimura F,Shridhar M.Handwritten numerical recognition based on multiple algorithms[J].Pattern Recognition,1991,24(10):969-983.
[95]Rogova G.Combining the results of several neural network classifiers[J].Neural Networks,1994,7(5):777-781.
[96]Keller JM,Gader P,Tahani H.Advances in fuzzy integration for pattern recognition[J].Fuzzy Sets and Systems,1994,65:273-283．
[97]Ting KM,Witten IH.Issues in stacked generalization[J].Journal of Artificial Intelligence Research,1999,10(5):271-289.
[98]Toh KA.A reduced multivariate polynomial model for multimodal biometrics and classifiers fusion[J].IEEE Trans on Systems,Man and Cybernetics,2004,14(2):224-233.
[99]张立明．人工神经网络的模型及其应用[M]．上海：复旦大学出版社，1994．
[100]徐秉铮，张白灵．神经网络及其在信号处理中的应用[J]．信号处理，1992，8(2)：65-73．
[101]楼顺天，施阳．基于MATLAB的系统分析与设计—神经网络[M]．西安：西安电子科技大学出版社，1998．
[102]刘思峰，郭天榜，党耀国．灰色系统理论及其应用[M]．北京：科学出版社，1999．1-3．
[103]易德生，郭萍．灰色理论与方法[M]．北京：石油工业出版社，1991．53-74．
[104]Massey FJ.The Kolmogorov-Smirnov test for goodness of fit[J].Journal of the American Statistical Association,1951,46:68-78.
[105]Min S,Yong X,Ainai M.3D visualization of large DEM data set based on grid division.Journal of computer aided design and computer graphics,2002,6:566-570.
[2] Chugh SS, Blackshear JL, Shen WK, Hammill SC, Gersh BJ. Epidemiology and natural history of atrial fibrillation: clinical implications [J]. J Am Coll Cardiol, 2001, 37:371-377.
[3] Wellens HJ, Lau CP, Luderitz B, Akhtar M, Waldo AL, Camm AJ, Timmermans C, Tse HF,Jung W, Jordaens L, Avers G. Atrioverter: an implantable device for the treatment of atrial fibrillation [J]. Circulation, 1998,98:1651-1656.
[4] Al-Khatib SM, Wilkinson WE, Sanders LL, McCarthy EA, Pritchett EL. Observations on the transition from intermittent to permanent atrial fibrillation [J]. Am Heart J, 2000, 140:142-145.
[5] Botteron GW, Smith JM. Quantitative assessment of the spatial organization of atrial fibrillation in the intact human heart [J]. Circulation, 1996, 93: 513-518.
[6] Botteron Gw, Smith JM. A technique for measurement of the extent of spatial organization of atrial activation during atrial fibrillation in the intact human heart [J]. IEEE Trans Biomed Eng.1995,42:579-586.
[7] Chen SW, Clarksom PM, Fan Q. A robust sequential detection algorithm for cardiac arrhythmia classification [J]. IEEE Trans Biomed Eng, 1996, 43:1120-1125.
[8] Sih HJ, Zipes DP, Berbari EJ, Olgin JE. A high-temporal resolution algorithm for quantifying organization during atrial fibrillation [J]. IEEE Trans Biomed Eng, 1999, 46:440-450.
[9] Swerdlow CD, Schsls W, Dijkman B, Jung W, Sheth NV. Detection of atrial fibrillation and flutter by a dual-chamber implantable cardioverter defibrillator [J]. Circulation, 2000, 101:878-885.
[10] Faes L, Nolio G, Antolini R, Gaita F, Ravelli F. A method for quantifying atrial fibrillation organization based on wave-morphology similarity [J]. IEEE Trans Biomed Eng, 2002, 49:1504-1513.
[11] Narayan SM, Valmik B. Temporal and spatial phase analyses of the electrocardiogram stratify intra-atrial and intra-ventricular organization [J]. IEEE Trans Biomed Eng, 2004,51:1749-1764.
[12] Ropella KM, Sahakian AV, Baerman JM, Swiryn S. The coherence spectrum: a quantitative discriminator of fibrillatory and nonfibrillatory cardiac rhythms [J]. Circulation, 1989, 80:112-119.
[13] Chen SW. A two-stage discrimination of cardiac arrhythmias using a total least squares-based prony modeling algorithm [J]. IEEE Trans Biomed Eng, 2000, 47:1317-1327.
[14] Everett TH. KoK LC, Vaughn RH, Moorman JR., Haines DE. Frequency domain algorithm for quantifying atrial fibrillation organization to increase defibrillation efficacy [J]. IEEE Trans Biomed Eng, 2001, 48: 969 -978.
[15] Khadra L, Al-Fahoum AS, Binajjaj S. A quantitative analysis approach for cardiac arrhythmia classification using higher order spectral techniques [J]. IEEE Trans Biomed Eng,2005,52: 1840-1845.
[16] Lovett EG, Ropella KM. Time-frequency coherence analysis of atrial fibrillation termination during procainamide administration [J]. Ann Biomed Eng, 1997, 25: 975-984.
[17] Stridth M, Sornmo L, Meurling CJ, Olsson SB. Characterization of atrial fibrillation using the surface ECG: time-dependent spectral properties [J]. IEEE Trans Biomed Eng, 2001, 48: 19-27.
[18] Zhang XS, Zhu YS, Thakor NV, Wang ZZ. Detecting ventricular tachycardia and fibrillation by complex measure [J]. IEEE Trans Biomed Eng, 1999, 46:548-555.
[19]Hosseini HG, Luo D, Reynolds KJ. The comparison of different feed forward neural network architecture for ECG signal diagnosis [J]. Medical Engineering & Physics, 2006, 28(4):372-378.
[20] Ciaccio E, Dunn S, Akay M. Biosignal pattern recognition and interpretation systems [J].IEEE Eng in Med and Bio Mag, 1993, 12(3): 89-95.
[21] Langley P, Bourke JP, Murray A. Frequency analysis of atrial fibrillation [J]. Comput Cardiol,2000, 27: 65-72.
[22] Petrutiu S, Sahakian AV, Ng J, Swiryn S. Analysis of the surface electrocardiogram to predict termination of atrial fibrillation: the 2004 Computers in Cardiology/Physionet Challenge [J].Comput Cardiol, 2004, 31:105-108.
[23] Hayn D, Edegger K, Scherr D, Lercher P, Rotman B, Klein W, Schreier G. Automated prediction of spontaneous termination of atrial fibrillation from electrocardiograms [J]. Comput Cardiol, 2004, 31:117-120.
[24] Cantini F, Conforti F, Varanini M, Chiarugi F, Vrouchos G. Predicting the end of an atrial fibrillation episode: the PhysioNet challenge [J]. Comput Cardiol, 2004, 31: 121-124.
[25] Sih HJ, Zipes DP, Berbari EJ, Olgin JE. A high-temporal resolution algorithm for quantifying organization during atrial fibrillation [J]. IEEE Trans Biomed Eng, 1999, 46: 440-450.
[26] Kao T, Su YY, Tso HW, Lin YC, Chen SA, Tai CT. Nonlinear analysis of human atrial flutter and fibrillation using the surface electrocardiogram [J]. Comput Cardiol, 2004, 31:441-444.
[27] Roberts FM, Povinelli RJ. A statistical feature based approach to predicting termination of atrial fibrillation [J]. Comput Cardiol, 2004, 31: 673-676.
[28] Mainardi LT, Matteucci M, Sassi R. On predicting the spontaneous termination of atrial fibrillation episodes using linear and non-linear parameters of ECG signals and RR series [J].Comput Cardiol, 2004, 31: 665-668.
[29] Nilsson F, Stridh M, Bollmann A, Sornmo L. Predicting spontaneous termination of atrial fibrillation using the surface ECG [J]. Med Eng Phys, 2006, 28: 802-808.
[30] Langley P, Allen J, Bowers EJ, Drinnan MJ, Garcia EV, King ST, Olbrich T, Sims AJ, Smith FE, Wild J, Zheng D, Murray A. Analysis of RR interval and fibrillation frequency and amplitude for predicting spontaneous termination of atrial fibrillation [J]. Computers in Cardiology, 2004, 31:637-640.
[31] Stridh M, Sornmo L, Meurling CJ, Olsson SB. Sequential characterization of atrial tachyarrhythmias based on ECG time-frequency analysis [J]. IEEE Trans Biomed Eng, 2004, 51:110-114.
[32] Nilsson F, Stridh M, Bollmann A, Sornmo L. Predicting spontaneous termination of atrial fibrillation with time-frequency information [J]. Comput Cardiol, 2004, 31: 657-660.
[33] Goldberger AL, Amaral LAN, Hausdorff JM, Ivanov PCh, Mark RG, Mietus JE, Moody GB,Peng CK, Stanley HE. PhysioBank, PhysioToolkit, and PhysioNet: components of a new research resource for complex physiologic signals [J]. Circulation, 2000, 101: e215-220.
[34] Friesen GM, Jannett TC, Jadallah MA, Yates SL, Quint SR, Nagle HT. A comparision of the noise sensitivity of nine QRS detection algorithms [J]. IEEE Tran Biomed Eng, 1990, 37: 85-98.
[35] Shkurovich S, Sahakian AV, Swiryn S. Detection of atrial activity from high-voltage leads of implantable ventricular defibrillators using a cancellation technique [J]. IEEE Trans Biomed Eng,1998.45:229-234.
[36] Petretta M, Bonaduce D, Spinelli L, Vicario ML, Nuzzo V, Marciano F, Camuso P, De Sanctis V, Lupoli G. Cardiovascular hemodynamics and cardiac autonomic control in patients with subclinical and overt hyperthyroidism [J]. Eur J Endocrinol. 2001, 145: 691- 696.
[37] Osman F, Franklyn JA, Daykin J, Chowdhary S, Holder R, Sheppard M, Gammage M. Heart rate variability and turbulence in hyperthyroidism before, during, and after treatment [J]. Am J Cardiol, 2004, 94: 465-469.
[38] Xu W, Tse HF, Chan FY, Fung PW, Lee KF, Lau CP. New Bayesian discriminator for detection of atrial tachyarrhythmias [J]. Circulation, 2002, 105(12):1472-1479.
[39] Chen JL, Chiu HW, Tseng YJ, Chu WC. Hyperthyroidism is characterized by both increased sympathetic and decreased vagal modulation of heart rate: evidence from spectral analysis of heart rate variability [J]. Clin Endocrinol, 2006, 64: 611-616.
[40] Goldberger AL, Amaral LAN, Hausdorff JM, Ivanov PH, Peng CK, Stanley HE. Fractal dynamics in physiology; alterations with disease and aging [C]. Proceedings of the National Academy of Sciences of the United States of America,2002,99(suppl 1):2466-2472.
[41]Stein KM,Lippman N,Kligfield P.Fractal rhythms of the heart[J].J Electrocardiol,1992,24(suppl):72-76.
[42]Mainardi LT,Porta A,Calcagnini G,Bartolini P,Michelucci A,Cerutti S.Linear and nonlinear analysis of atrial signals and local activation period series during atrial fibrillation episodes[J].Med Biol Eng Comput,2001,39:249-254.
[43]Kao T,Su YY,Tso HW,Lin YC,Chen SA,Tai CT.Nonlinear analysis of human atrial flutter and fibrillation using the surface electrocardiogram[J].Comput Cardiol,2004,31:441-444
[44]张贤达．现代信号处理[M]．北京：清华大学出版社，1998．
[45]Daubechies I.Orthonormal bases of compactly supported wavelets[J].Comm Pure Appl Math,1988,41:909-996.
[46]Mallat SG.A theory for multiresolution signal decomposition:the wavelet represention[J].IEEE Trans Pattern Anal Mach Intell,1989,11:674-693.
[47]Chui CK,Wang JZ.A Cardinal Spline Approach to wavelets[J].Proc Amer Math Soc,1991,113:785-793.
[48]Melkonian D,Blumenthal TD,Meares R.High-resolution fragmentary decomposition-a model-based method of non-stationary electrophysiological signal,analysis[J].Journal of neuroscicnce methods,2003,131:149-159.
[49]洛伦兹EN．混沌的本质[M]．北京：气象出版社，1997．
[50]卢侃，孙建华，欧阳容百．混沌动力学[M]．上海：远东出版社，1990．
[51]Parker TS,Chua LO.Chaos:a tutorial for engineers[J].Processing of IEEE,1987,75:982-1008.
[52]Moon FC.Chaotic and fractal dynamics[M].Wiley,1992.
[53]Kantz H,Schreiber T.Nonlinear time series analysis[M].Cambridge University Press,1997.
[54]李颖洁．脑电信号动力学特性分析及其在精神分裂症中的应用研究[D]．上海：上海交通大学，2001．
[55]张绪省．心室纤颤动力学的动力学的非线性分析及应用研究[D]．上海：上海交通大学，1997．
[56]Goldberger AL.Non-linear dynamics for clinicians:chaos theory,fractals,and complexity at the bedside[J].Lancet,1996,347:1312-1314.
[57]Vibe K,Vesin JM.On chaos detection methods[J].International Journal of Bifurcation and Chaos,1996,6(3):529-543.
[58]Theiler J,Eubank S,Longtin A,Galdrikian B,Farmer JD.Testing for nonlinearity in time series:the method of surrogate data[J].Physica D,1992,58:77-94.
[59]刘秉正，彭建华．非线性动力学[M]．北京：高等教育出版社，2004：454-464．
[60]Devamey RL.Chaotic dynamical systems[M].New York:Addison-Wesley,1989.
[61]Jaclson EA.Perspectives of nonlinear dynamics[M].Cambridge England:Cambridge University Press,1989.
[62]Baumert M,Walther T,Hopfe J,Stepan H,Faber R,Voss A.Joint symbolic dynamic analysis of beat-to-beat interactions of heart rate and systolic blood pressure in normal pregnancy[J].Med Biol Eng Comput,2002,40:241-245.
[63]Crutchfield JP,Packaed NH.Symbolic dynamics of noisy chaos[J].Physica D,1983,7:201-223.
[64]Shannon CE,A mathematical theory of communication[J].The Bell System Technical Journal,1948,27:379-423.
[65]Packard NH,Crutchfield JP,Farmer JD,Shaw RS.Geometry from a time series[J].Phys Rev Lett,1980,45:712-716.
[66]Takens F.Detecting strange attractors in turbulence[J].Lect Notes Math,1981,898:366-381.
[67]吕金虎，陆君安，陈士华．混沌时间序列分析及其应用[M]．武昌：武汉大学出版社，2002．
[68]Hegger R,Kantz H,Schreiber T.Practical implementation of nonlinear time series methods:the TISEAN package[J].Chaos,1999,9:413-435.
[69]Piskorski J,Guzik P.Geometry of the Poincare plot of RR intervals and its asymmetry in healthy adults[J].Physiol Meas,2007,28:287-300.
[70]Gleik J.Chaos:making a new science[M].New York:Viking Penguin Inc,1987.
[71]Brennan M,Palaniswami M,Kamen P.Do existing measures of Poincare plot geometry reflect nonlinear features of heart rate variability?[J]IEEE Trans Biomed Eng,2001,48:1342-1347.
[72]Suyama AC,Sunagawa K,Sugimachi M,Anan T,Egashira K,Takeshita A.Differentiation between aberrant ventricular conduction and ventricular ectopy in atrial fibrillation using RR interval scattergram[J].Circulation,1993,88:2307-2314.
[73]Jolliffe I.Principal component analysis[M].New York:Springer-Verlag,1986.
[74]Gao JB.Detecting nonstationarity and state transitions in a time series[J].Physical Review E,2001,63:DOI:066202.
[75]Casdagli MC.Recurrence Plots Revisited[J].Physica D,1997,108:12-44.
[76]Riley MA,Balasubramaniam R,Turvey MT.Recurrence quantification analysis of postural fluctuations[J].Gait & Posture,1999,9:65-78.
[77] Marwan N, Wessel N, Meyerfeldt U, Schirdewan A, Kurths J. Recurrence-plot-based measures of complexity and their application to heart-rate-variability data [J]. Physical Review E,2002, 66: DOI: 026702.
[78] Faure P, Korn H. A new method to estimate the Kolmogorov entropy from recurrence plots: its application to neuronal signals [J]. Physica D-Nonlinear Phenomena, 1998, 122: 265-279.
[79] Tong H. Nonlinear time series analysis: a dynamical systems approach [M]. Oxford University Press, 1990.
[80] Eckmann JP, Ruelle D. Fundamental limitations for estimating dimensions and Lyapunov exponents in dynamical systems [J]. Physica (Amsterdam), 1992, 56: 185-185.
[81] Schreiber T. Interdisciplinary application of nonlinear time series methods [J]. Physics Reports-Review Section of Physics Letters, 1999, 308: 2-64.
[82] Eckmann JP, Kamphorst SO, Ruelle D. Recurrence plots of dynamical systems [J]. Europhys Lett, 1987, 5: 973-977.
[83] Zbilut JP, Webber J, Charles L. Embeddings and delays as derived from quantification of recurrence plots [J]. Physics Letters A, 1992,171: 199-203.
[84] Webber CL, Zbilut JP. Dynamical assessment of physiological systems and states using recurrence plot strategies [J]. J Appl Physiol, 1994, 76: 965-973.
[85] Gao JB, Cai HQ. On the structures and quantification of recurrence plots [J]. Physics Letters A, 2000, 270: 75-87.
[86] Gao JB. Recurrence time statistics for chaotic systems and their applications [J]. Physical Review letters, 1999, 83(16): 3178-3181.
[87] Cortes C, Vapnik VN. Support-vector networks [J]. Machine learning, 1995, 20:273-297.
[88] Lin CF, Wang SD. Fuzzy support vector machines [J]. IEEE Transaction on neural networks,2002, 13(2): 464-471.
[89] Zaden LA. Fuzzy sets [J]. Inf Control, 1965, 8: 338-353.
[90] Mitra S, Pal SK, Mitra P. Data mining in soft computing framework: a survey [J]. IEEE Trans Neural Networks, 2002, 13(1): 3-14.
[91] Kwan HK, Cai Y. A fuzzy neural network and its application to pattern recognition [J]. IEEE Trans Fuzzy Systems, 1994,2 (3): 185-193.
[92] Jiang XF, Yi Z, Lv JC. Fuzzy SVM with a new membership function [J]. Neural Comput & Applic, 2006, 15:268-276.
[93] Gupta L, Chung B, Srinath MD, Molfese DL, Kook H. Multichannel fusion models for the parametric classification of differential brain activity [J]. IEEE Transactions on Biomedical Engineering, 2005, 52 (11):1869-1881.
[94]Kimura F,Shridhar M.Handwritten numerical recognition based on multiple algorithms[J].Pattern Recognition,1991,24(10):969-983.
[95]Rogova G.Combining the results of several neural network classifiers[J].Neural Networks,1994,7(5):777-781.
[96]Keller JM,Gader P,Tahani H.Advances in fuzzy integration for pattern recognition[J].Fuzzy Sets and Systems,1994,65:273-283．
[97]Ting KM,Witten IH.Issues in stacked generalization[J].Journal of Artificial Intelligence Research,1999,10(5):271-289.
[98]Toh KA.A reduced multivariate polynomial model for multimodal biometrics and classifiers fusion[J].IEEE Trans on Systems,Man and Cybernetics,2004,14(2):224-233.
[99]张立明．人工神经网络的模型及其应用[M]．上海：复旦大学出版社，1994．
[100]徐秉铮，张白灵．神经网络及其在信号处理中的应用[J]．信号处理，1992，8(2)：65-73．
[101]楼顺天，施阳．基于MATLAB的系统分析与设计—神经网络[M]．西安：西安电子科技大学出版社，1998．
[102]刘思峰，郭天榜，党耀国．灰色系统理论及其应用[M]．北京：科学出版社，1999．1-3．
[103]易德生，郭萍．灰色理论与方法[M]．北京：石油工业出版社，1991．53-74．
[104]Massey FJ.The Kolmogorov-Smirnov test for goodness of fit[J].Journal of the American Statistical Association,1951,46:68-78.
[105]Min S,Yong X,Ainai M.3D visualization of large DEM data set based on grid division.Journal of computer aided design and computer graphics,2002,6:566-570.