基于数据挖掘技术的证素辨证方法研究
|
摘要
辨证论治是中医学的特点与精华,是中医在诊治疾病时应当遵循的原则。其科学性、优越性与必要性,已为长期的医疗实践所证实。无论疾病病种是否明确,辨证论治都能够根据每个人的具体病情进行灵活地处理,从而大大丰富了中医学对疾病的处理能力。然而长期以来,中医学对于“证”的规律性、系统性还研究不够,辨证方法有多种,辨证概念较为混乱,病情千变万化,证名异同难辨,临床不可能只按某一法进行辨证,而必须诸法综合起来运用。这给中医临床、科研、教学带来了很大的困难。辨证统一体系的创立,无疑为中医现代化奠定了基础。辨证统一体系是一种科学性强的中医辨证方法,它的核心思想是征素辨证。在证素辨证中,辨证过程由辨证要素推理和证名组合两个环节构成。辨证要素推理是依据病人的临床症状、体征等信息,判定相关的证素,然后由证素组合构成符合中医习惯的证名术语,以指导临床处方用药。在统一辨证体系下,建立科学的证素辨证定性、定量标准,不仅是中医临床医生的需要,也是信息社会中新的医疗模式建立的基础。当前,医生采用证素辨证方法时,对证素的确认知识主要来自文献、专家等各种途径,通过收集、总结形成的知识。由于文献记载长期以来对证候的辨识主要-是采取主观定性的方法,使得辨证论治带有较强的经验性和主观性,导致从文献或专家等多种途径得到的辨证知识具有模糊性和不一致性,因此,建立科学的证素辨证定性定量标准,是辨证统一体系推广应用的关键。自辨证统一体系提出以来,有不少研究人员以临床数据库为基础,通过模糊数学、统计分析、神经网络等方法在证素辨证规则的获取、症状对证素影响的定量分析等方面做了许多探索性工作,但由于所用学习方法自身的缺点和局限性,如泛化能力差,或对先验知识的要求高等,使得研究没有获得突破性进展。
本研究以临床信息为对象,从数据挖掘技术应用入手,在证素辨证体系的框架下,揭示中医辨证的规律,寻找确认证素的科学方法,明确证素、常见证的特征证候,各症状的诊断贡献度,建立体现辨证论治规律的数学模型,进一步将为中医电子病历、诊断决策支持研究等多学科与中医的交融奠定技术基础。具体研究内容有:通过分别采用目前公认的数据挖掘新方法:支持向量机与粗糙集的一些算法,对已收集的临床病历数据进行实验分析,探索利用这些方法解决中医证素辨证建模的可行性。同时,对朱文锋教授通过研究归纳而建立的一套专用于证素辨证的“双层频权剪叉算法”进行实验分析研究。最后,比较实验结果,并对实验结果进行分析。拟解决的问题为:寻找提高证素辨证准确率的方法,构建证素辨证基础研究平台。论文首先对证素辨证客观化研究的情况作了综述,然后对证素辨证客观化研究技术进行分析比较,概述了现有研究技术基本情况及存在的缺陷,并提出粗糙集、支持向量机技术应用的优点。然后对数据挖掘与中医诊断研究的关系进行了探讨,接着介绍了ROUGHSETS与证素辨证关联规则的获取、SVM与证素辨证预测模型的建立、“双层频权剪叉算法”与证素辨证量表的制定三项研究工作情况,最后,进行总结和讨论,并提出了今后工作的方向。
As the characteristic and essence of the traditional Chinese medicine, the treatment after syndrome differentiation is a binding principle in the medical practices.Its scientific nature,excellence,and necessity have been proved by extensive medical practices in the history.Syndrome differentiation provides a particular treatment according to the individual patient's particular symptoms in a flexible mode,no matter whether the type of disorder has been confirmed or not.However,in the past ages,insufficient effort has been devoted to the study of the rules and systems of differentiation in the TCM circle.As there were various differentiation methods,confusing concepts,thousands of syndrome descriptions and implicit syndrome names,medical practitioners could not merely adopt a single method for syndrome differentiation,but have to apply a number of methods comprehensively.That brought large difficulties in medical practices,research and education.The establishment of uniform syndrome differentiation architecture doubtlessly laid a foundation for TCM's modernization.As a highly scientific methodology,the essential of the uniform syndrome differentiation architecture is the element differentiation.In the element differentiation,the process was composed of two steps-element reasoning and the forming of the syndrome name.The syndrome element reasoning is to be conducted according to the patient's symptoms and signs to pin down relevant syndrome elements,then combine elements to form a syndrome name that is in accordance to the TCM's accepted practices,so as to guide the practical prescription and treatment.Establishing scientific qualitative and quantitative criteria for the element differentiation under the uniform syndrome differentiation architecture is demanded not only by the TCM practitioners,but also as a foundation of the new medical care system demanded by the information society.In current practices of element differentiation,TCM practitioners normally acquire knowledge about syndrome elements recognition through collecting and distilling information from relevant publications and comments of experts.As most of the records in the publications on syndrome differentiation cover mostly subjective and qualitative methods,the treatment practices based on syndrome differentiation was comparatively empirical and subjective.Thus the syndrome differentiation knowledge acquired from publications and experts' comments were normally ambiguous and inconsistent.Therefore,setting up a scientific qualitative and quantitative measurement standard for syndrome element differentiation is the corner stone for promoting the application of the uniform syndrome differentiation architecture.Since the emergence of the uniform syndrome differentiation,researchers,facilitated by use medical databases,have made a lot of explorative work on fields such as acquisition of syndrome element differentiation rules,quantitative analysis on the impact of symptoms to syndrome elements and so on.Nevertheless,due to the defects and constraints of the learning methods,such as low deduction and high standard for empirical knowledge acquisition,there has been no breakthrough development in the research.
Taking the information acquired in medical practices as research objective and employing data mining technologies,the research aims to explore for scientific methods of syndrome element recognition so as to provide technical support for finding a high speed and highly effective syndrome differentiation model for diseases prevention and treatment, and for solving some key technical issues in medical practices.Furthermore,the research aims to lay a foundation for convergence between the TCM and some inter-disciplinary studies such as the electronic medical record and the decision support system for diagnosis etc;and willlay a foundation for the studies on optimal disease treatment rules,optimal TCM prescription and specific therapy or medicine for a variety of complications.The research involves in using well acknowledged new data mining methods-some algorithms that support the SVM and the rough sets to conduct experimental analysis to collected data from medical cases,and hence to discuss on the feasibility of using those methods to establish a model for syndrome element differentiation in TCM practices.Meanwhile,the research will conduct experimental analysis on the double layer spectrum weighted cross cutting algorithm for syndrome element differentiation put forwarded by Prof.Zhu Wenfeng after he studied and distilled for scores of years.At last,a comparative analysis will be conducted to the results of the experiments.The problems to address are exploring for methods to improve the accuracy of the syndrome element differentiation and construct a platform for its fundamental research.The thesis begins with introductive summary to the research on objectivity of syndrome element differentiation.It follows with a summary of existing research techniques and a comparative analysis to them,and points out their defects,and hence put forward the advantages of applying fought set and SVM techniques.The paper then discusses the relationship between the data mining and studies on TCM diagnosis,acquisition of the rules for association between rough set and syndrome element differentiation,SVM and construction of a predictive model for syndrome element differentiation,the double layer spectrum weighted cross cutting algorithm,and construction of syndrome element table.In conclusion,a summary was made to wrap up the discussion and a direction was pointed out for future studies.
本研究以临床信息为对象,从数据挖掘技术应用入手,在证素辨证体系的框架下,揭示中医辨证的规律,寻找确认证素的科学方法,明确证素、常见证的特征证候,各症状的诊断贡献度,建立体现辨证论治规律的数学模型,进一步将为中医电子病历、诊断决策支持研究等多学科与中医的交融奠定技术基础。具体研究内容有:通过分别采用目前公认的数据挖掘新方法:支持向量机与粗糙集的一些算法,对已收集的临床病历数据进行实验分析,探索利用这些方法解决中医证素辨证建模的可行性。同时,对朱文锋教授通过研究归纳而建立的一套专用于证素辨证的“双层频权剪叉算法”进行实验分析研究。最后,比较实验结果,并对实验结果进行分析。拟解决的问题为:寻找提高证素辨证准确率的方法,构建证素辨证基础研究平台。论文首先对证素辨证客观化研究的情况作了综述,然后对证素辨证客观化研究技术进行分析比较,概述了现有研究技术基本情况及存在的缺陷,并提出粗糙集、支持向量机技术应用的优点。然后对数据挖掘与中医诊断研究的关系进行了探讨,接着介绍了ROUGHSETS与证素辨证关联规则的获取、SVM与证素辨证预测模型的建立、“双层频权剪叉算法”与证素辨证量表的制定三项研究工作情况,最后,进行总结和讨论,并提出了今后工作的方向。
As the characteristic and essence of the traditional Chinese medicine, the treatment after syndrome differentiation is a binding principle in the medical practices.Its scientific nature,excellence,and necessity have been proved by extensive medical practices in the history.Syndrome differentiation provides a particular treatment according to the individual patient's particular symptoms in a flexible mode,no matter whether the type of disorder has been confirmed or not.However,in the past ages,insufficient effort has been devoted to the study of the rules and systems of differentiation in the TCM circle.As there were various differentiation methods,confusing concepts,thousands of syndrome descriptions and implicit syndrome names,medical practitioners could not merely adopt a single method for syndrome differentiation,but have to apply a number of methods comprehensively.That brought large difficulties in medical practices,research and education.The establishment of uniform syndrome differentiation architecture doubtlessly laid a foundation for TCM's modernization.As a highly scientific methodology,the essential of the uniform syndrome differentiation architecture is the element differentiation.In the element differentiation,the process was composed of two steps-element reasoning and the forming of the syndrome name.The syndrome element reasoning is to be conducted according to the patient's symptoms and signs to pin down relevant syndrome elements,then combine elements to form a syndrome name that is in accordance to the TCM's accepted practices,so as to guide the practical prescription and treatment.Establishing scientific qualitative and quantitative criteria for the element differentiation under the uniform syndrome differentiation architecture is demanded not only by the TCM practitioners,but also as a foundation of the new medical care system demanded by the information society.In current practices of element differentiation,TCM practitioners normally acquire knowledge about syndrome elements recognition through collecting and distilling information from relevant publications and comments of experts.As most of the records in the publications on syndrome differentiation cover mostly subjective and qualitative methods,the treatment practices based on syndrome differentiation was comparatively empirical and subjective.Thus the syndrome differentiation knowledge acquired from publications and experts' comments were normally ambiguous and inconsistent.Therefore,setting up a scientific qualitative and quantitative measurement standard for syndrome element differentiation is the corner stone for promoting the application of the uniform syndrome differentiation architecture.Since the emergence of the uniform syndrome differentiation,researchers,facilitated by use medical databases,have made a lot of explorative work on fields such as acquisition of syndrome element differentiation rules,quantitative analysis on the impact of symptoms to syndrome elements and so on.Nevertheless,due to the defects and constraints of the learning methods,such as low deduction and high standard for empirical knowledge acquisition,there has been no breakthrough development in the research.
Taking the information acquired in medical practices as research objective and employing data mining technologies,the research aims to explore for scientific methods of syndrome element recognition so as to provide technical support for finding a high speed and highly effective syndrome differentiation model for diseases prevention and treatment, and for solving some key technical issues in medical practices.Furthermore,the research aims to lay a foundation for convergence between the TCM and some inter-disciplinary studies such as the electronic medical record and the decision support system for diagnosis etc;and willlay a foundation for the studies on optimal disease treatment rules,optimal TCM prescription and specific therapy or medicine for a variety of complications.The research involves in using well acknowledged new data mining methods-some algorithms that support the SVM and the rough sets to conduct experimental analysis to collected data from medical cases,and hence to discuss on the feasibility of using those methods to establish a model for syndrome element differentiation in TCM practices.Meanwhile,the research will conduct experimental analysis on the double layer spectrum weighted cross cutting algorithm for syndrome element differentiation put forwarded by Prof.Zhu Wenfeng after he studied and distilled for scores of years.At last,a comparative analysis will be conducted to the results of the experiments.The problems to address are exploring for methods to improve the accuracy of the syndrome element differentiation and construct a platform for its fundamental research.The thesis begins with introductive summary to the research on objectivity of syndrome element differentiation.It follows with a summary of existing research techniques and a comparative analysis to them,and points out their defects,and hence put forward the advantages of applying fought set and SVM techniques.The paper then discusses the relationship between the data mining and studies on TCM diagnosis,acquisition of the rules for association between rough set and syndrome element differentiation,SVM and construction of a predictive model for syndrome element differentiation,the double layer spectrum weighted cross cutting algorithm,and construction of syndrome element table.In conclusion,a summary was made to wrap up the discussion and a direction was pointed out for future studies.
引文
[1]朱文锋.辨证统一体系的创立[J].中国中医基础医学杂志.2001;7(4):4
[2]朱文锋.构建“证素辨证”新体系的意义[J].浙江中医药大学学报,2006,30(2):135-
[3]朱文锋,黄碧群,陈新宇.病性证素辨别的意义与方法[J].中医药学刊,2006,24(2):204-
[4]晏峻峰,朱文锋.粗糙集理论在中医证素辨证研究中的应用[J].中国中医基础医学杂志,2006,12(2):90-
[5]朱文锋.论中医症状的规范研究[J].中医杂志,2005,46(9):649-
[6]朱文锋,李灿东,甘慧娟.病位证素的特征[J].福建中医药,2005,36(4)
[7]朱文锋.制定全病域中医辨证量表的设计思路[J].辽宁中医杂志,2005,32(6):521-
[8]朱文锋,晏峻峰.证素辨证新体系的内容及科学意义[J].医学与哲学,2005,26(1):69-
[9]朱文锋,黄碧群.证、证候的辨析与规范[J].山西中医,2005,21(3):1-
[10]朱文锋,甘慧娟.证素内容的辨析[J].湖南中医药导报,2005,11(1):11-
[11]朱文锋,张华敏.“证素”的基本特征[J].中国中医基础医学杂志,2005,11(1):17-
[12]朱文锋,晏峻峰,黄碧群.贝叶斯网络在中医证素辨证体系中的应用[J].中西医结合学报,2006年06期
[13]林鹏,杨波.粗糙集理论与方法[M].科学出版社,2001-7-1
[14]邓乃扬,田英杰.数据挖掘中的新方法-支持向量机[M].科学出版社,2004-06
[15]陈水利,李敬功,王向公.模糊集理论及其应用[M].科学出版社,2005-9-1
[16]李士勇.工程模糊数学及应用[M].哈尔滨工业大学出版社,2004-8-1
[17]张青贵.人工神经网络导论[M].中国水利水电出版社,2004-10-1
[18]蔡自兴,徐光祜.人工智能及其应用(第三版)[M].清华大学出版社,2004-08
[19]Simon Haykin神经网络原理[M].机械工业出版社,2004-01
[20]王国胤.Rough集理论与知识获取[M].西安:西安交通大学出版社,2001.5.
[21]李男,邱天爽.基于粗糙集的数据挖掘技术及其在临床医学诊断中的应用[J].上海生物医学工程,2002,2(23):3-7.
[22]方积乾.卫生统计学[M].人民卫生出版社,2003-8-1
[23]Coulter DM,Bate A,Meyboom RH,etal.Anti psychotic drugs and heart muscle disorder in international pharmacovigi21ance: data mining study. BMJ , 2001; 322 (7296) : 1207
[24]DokurZ0 , lmez T. ECG beat classification by a novel hy2brid neural network. Computer Methods and Program sin Biomedicine, 2001; 66 : 167
[25]V efgh i L , LinkensDA. Dynamic monitoring and control of patient an aesthetic and do se levels: time2delay, moving average neural networks, and principal components analysis. Computer Methods and Program s in Biomedicine, 1999; 59 : 91
[26]Ying H, Wu Shyu L Y. Detection of V PC using wavelet transform and fuzzy neural network. Proceeding of The First Joint BM ES^ EMBS Conference Serving Humanity, Advancing Technology, 1999 Oct, Atlanta, GA, USA
[27]Pavlopoulo s S, Kyriacou E, Koutsouris D, et al. Fuzzy neurale two rkbased texture analysis of ultrasonic images. IEEE EngM ed Bio 1M ag, 2000; 19 (1) : 39
[28]Podgo relecV, Brest J, Koko 1 P. Power of heterogeneous computing as a vehicle for implementing E (3) medical decision support system. Int J M ed Inf, 2000; 58 : 59179
[29]Bo jarczuk CC, Lopes HS, F reitas AA. Genetic programming for knowledge discovery in chest pain diagnosis. IEEE Eng M ed Bio 1M ag, 2000; 19 (4): 38
[30]Wang ML, Wai L, Leung KS. Discovery know ledge from medical database using evolutionary algorithm s. IEEE Eng Med Biol M ag, 2000; 19(4)45
[31]Kusiak A , Kern JA , Kernstine KH, et al. Autonomous decision making: a data mining app roach. IEEE Trans Inf Techno 1Biomed, 2000; 4 (4): 274
[32]Oh rn A , Row land T. Rough sets: a knowledge discovery technique for multifactorial medical outcomes. Am J Phys Med Rehabil , 2000; 79(1): 100
[33]M itra P, M itra S, Pal SK. Staging of cervical cancer with soft computing. IEEE Trans Bio med Eng, 2000; 47 (7) : 934
[34]Pavlidis P, Furey TS, L iberto M , et al. Promoter region based classification of genes. Pac Symp Bio comput, 2001; 151
[35]Hua S, Sun Z. A novel method of protein secondary structure prediction with high segment overlap measure: support vector machine app roach.J Mo l Bio l,2001;308(2):397
[36]Cai YD,L iu XJ,Xu XB,et al.Support vector machines for prediction of protein sub cellular location.Mo 1 Cell Bio l Res Commun,2000;4(4):230
[37]田文敬.中医特色研究应借助现代数据挖掘技术[J].中医研究,2005(8)
[38]胡镜清,刘保延,王永炎.中医临床个体化诊疗信息特征与数据挖掘技术应用分析[J].世界科学技术-中医药现代化,2004;6(1)
[39]王波,张斌,魏伟杰.面向中医辨证规范的交互式数据挖掘框架[J].世界科学技术中医药现代化,2006 Vol.8 No.1 P.24-30
[40]王映辉,姜在旸,闫英杰.基于信息和数据挖掘技术的名老中医临床诊疗经验研究思路[J].世界科学技术-中医药现代化,2005年01期
[41]赵晓山,罗云坚,罗仁,等.基于数据挖掘的中医证候规范化研究方法学的建立[J].中华实用中西医杂志,2005年VOL.(18) NO.
[42]龚德平,高颖,唐涛.基于数据挖掘的数字化中医诊断系统[J].中国医学影像技术,2003年第19卷204号(P132-134)
[43]陈明,张书河.关联规则在中医疾病证候诊断中的应用[J].中华医学丛刊,2004年第4卷第5期(p14-16)
[44]刘晋平,黄宇虹,陆小左.数据挖掘在中医脉诊中的应用[J].天津中医学院学报,2003,22(3):9
[45]姚美村,艾路,袁月梅,乔延江.消渴病复方配伍规律的关联规则分析[J].北京中医药大学学报,2002年11月第25卷第6期(p48-50)
[46]刘强,刘璨,朱文锋.数据挖掘:心气虚证的鉴别诊断研究[J].福建中医药,2005年03期
[47]尚景盛,胡立胜,牛欣,司银楚.半夏泻心汤配伍应用的数据挖掘试验[J].中日友好医院学报,2005年04期
[48]徐蕾,贺佳,孟虹,等.基于信息熵的决策树在慢性胃炎中医辨证中的应用[J].第二军医大学学报,2004sep;25(9)
[49]秦中广,毛宗源,邓兆智.粗糙集在中医类风湿证候诊断中的应用[J].中国生物医学工程学报,2001;20(4):357-363.
[50]马廷淮,赵亚伟,张海盛,曾振柄.基于粗糙集的决策规则约简[J].计算机工程.2003,Vol.29,No.12,pp:5-7
[51]方敏,陈雁翔.基于模糊神经的机械故障诊断方法的研究[J].控制理论与应用,1998,15(3):460-465
[52]Z.Pawlak.Rough sets and intelligent data analysis[J].Information Sciences,2002,147:1-12
[53]杨燮,杨炳儒.一种属性与值约简简化算法[J].小型微型计算机系统,2004,25(2):245-247.
[54]Z.Pawlak,ROUGH SETS:Theoretical Aspects of Reasoning about Data[M].Kluwer Academic Publishers,1991
[55]黄梯云,卢涛,程岩.数据挖掘中一种基于粗糙集理论的属性集离散映射方法[J].情报学报,2002,21(4):391-396.
(56]刘清.Rough集及Rough推理[M].北京:科学出版社,2001.
[57]Pawlak Z.Rough Sets[J].International Journal of Information and Computer Science.1982,11:341-356.
[58]Zdizislaw Pawlak,Jerzy Grzymala-Busse,Roman Slowinski,Wojciech Ziarko.Rough sets[J].Communication of the ACM,1995,38(11):89-95.
[59]曾黄麟.粗糙集理论及其应用[M].重庆:重庆大学出版社,1996.
[60]钟波,肖智,周家启.组合预测中基于粗糙集理论的权值确定方法[J].重庆大学学报,2002,25(7):127-130
[61]张文修,仇国芳.基于粗糙集的不确定决策[M].清华大学出版社,2005-08
[62]林鹏,杨波.粗糙集理论与方法[M].科学出版社,2001-07
[63]徐袭,姚琼荟,石敏.基于粗糙集与支持向量机的故障智能分类方法[J].计算技术与自动化,2006.25(1).-32-34
[64]邓乃扬,田英杰.数据挖掘中的新方法-支持向量机[M].科学出版社,2004-6-1
[65]张铃.支持向量机理论与基于规划的神经网络学习算法[J].计算机学报,2001,24(2):113-118.
[66]马永军,李孝忠,王希雷.基于模糊支持向量机和核方法的目标检测方法研究[J].天津科技大学学报,2005,20(3);29-32.
[67]张莉.支撑向量机与核方法研究[D].西安:西安电子科技大学,2002.
[68](美)瓦普尼克.统计学习理论的本质[M].张学工译北京;清华大学出版社,2000.
[69]范昕炜.支持向量机算法的研究及其应用[D].浙江大学,2003-05.
[70]李建民,张钹林,福宗.支持向量机的训练算法[J].清华大学学报(自然科学版),2003,43(1):120-124.
[71]威武,常俊林,邵惠鹤.一种贝叶斯证据框架下支持向量机建模方法的研究[J].控制与决策,2004。19(5):525-533.
[72]刘向东,陈兆乾.基于支持向量机方法的人脸识别研究[J].小型微型计算 机系统,2004,25(12):2 261 2 263.
[73]张爱丽,刘广利,刘长宇.基于SVM的多类文本分类研究[J].情报杂志,2001,23(9):6-10.
[74]魏新,冯兴杰,刘山.基于支持向量机的多元文本分类研究[J].海军工程大学学报.2004,16(5):30-32.
[75]Vapnik V.Statistical learning theory[M],New York:John Wiley&Sons.1998.
[76]Domeniconi C,Gunopulos D.Incremental support vector ma-chine construction[A].Proceedings of IEEE International Conference on Data Mining[C].San Jose,USA:IEEE,2001:589-592.
[77]VAV GESTEL T,SUYKENS JAK BAESTAENS D,et al.Finch.cial time series prediction using least squares support vector machines within the evidence framework[J].IEEE Trans on Neural Networks,2001,12(4):809-821.
[78]KRUIF BJ VRIES TJA.On using a support vector machinein learning feed forward control[A]Proceedings of IEEE/ASME International Conference on Advanced Intelligent Mechatronics[C].Coma.Italy,2001.1:272-277.
[79]V N Vapnik.The Nature of Statistical Learning Theory[M].NewYork:Springer,1999.
[80]V N Vapnik.Statistical Learning Theory[M].New York:Wiley,1998.
[81]B E Boser,et al.A Training Algorithm for Optimal Margin Classifiers[C].Pittsburgh,PA:ACM Press,1992.144-152.
[82]EOsuna,R Freund,F Girosi.An Improved Trmmng Algorithm for Support Vector Machines[C].New York,1997.276-285.
[83]E Osuna,R Freund,F Gimsi.Supppo Vector Machines:Training and Application JR].Cambridge,MA:Massachusetts Institute of Technology,AILab,1997.
[84]Platt J.Fast Training of Support Vector Machines Using Sequential Minimal Optimization[C].Cambridge,MA:MIT Press,1999.1S5208.
[85]J Platt.Using Analytic QP and Sparseness tO Speed Training of Support VectorMachines[C].Cambridge,MA:MIT Press,1999.557-563.
[86]Vapnik V.The nature of statistical learning theory[M].New York:Springer-Verlag,1995.
[87]Cortes C,Vapnik V.Support vector networks[J].Machine learning,1995,20(1):273 297.
[88]Smola A,Scholkopf B.On a kernel based method for pattern recognition,regression,approximation and operator inversion[J].Algorithmica,1998,22(1):211-231.
[89]Chang C C,1.in C J.Training nu support vector regression:theory and algorithms E J].Neural Computati.n,2002,11(1):1959-1977.
[90]Gill PE,Murray,W,Wright M H.Practical optimization[M].New York:Academic Press,1981.
[91]Platt J.Fast Training of Support Vector Machines Using Sequential Minimal Optimization[A].Scholkopf B,Burges C,Smola h.Advances in Kernel Methods-Support Vector Learning[C].Cambridge MA:MIT Press,1999.
[92]Fei S,Lawrence K,Daniel D.Multiplicative updates for nonnegative quadratic programming in support vector machines[h],suztlnna B,Sebastian T,Klaus O.Advances in Neural Information Processing Systems[(?).Cambridge MA:MIrr Press,2003.
[93]常玉清,邹伟,王福利,毛志忠.基于支持向量机的软测量方法研究[J].控制与决策,2005.20(11).-1307-1310
[94]陈淋艳,封筠.支持向量机分类器若干核心问题的研究[J].包头钢铁学院学报,2005.24(4).-318-320
[95]高智勇,龚健雅,秦前清,林家瑞.支持向量机在早期癌症检测中的应用[J].生物医学工程学杂志,2005.22(5).-1045-1048
[96]沈利,杨杰,周越.基于支持向量机的室性早搏捡测[J].生物医学工程学杂志,2005.22(1).-78-81
[97]丁彦蕊,蔡宇杰,须文波.基于氨基酸组成预测蛋白质热稳定性的v-支持向量机方法[J].计算机与应用化学,2005.22(6).-459-465
[98]陈永义.支持向量机方法与模糊系统[J].模糊系统与数学,2005.19(1)1-11
[99]齐志泉,田英杰,徐志洁.支持向量机中的核参数选择问题[J].控制工程2005.12(4).-379-381
[100]杜晓东李岐强.支持向量机及其算法研究[J].信息技术与信息化,2005(3).-37-40
[101]胡国胜.支持向量机算法及应用[J].现代电子技术,2005.28(3).-106-109
[102]贾银山,贾传荧.一种加权支持向量机分类算法[J].计算机工程, 2005.31(12).-23-25
[103]刘向东,骆斌,陈兆乾.支持向量机最优模型选择的研究[J].计算机研究与发展,2005.42(4).-576-581
[104]白亮,老松杨,胡艳丽.支持向量机训练算法比较研究[J].计算机工程与应用,2005.41(17).-79-81
[105]朱文锋.证候辨证量表制定的科学性要求[J].中国中医药信息杂志,2005,12(8):93-
[106]朱文锋,黄碧群,朱镇华.借鉴量表法研制中医症状辨证量表[J].中华现代临床医学杂志,2005,3(23):2474-
[107]朱文锋.症状辨证调查表设计的特色性要求[J].湖南中医学院学报,2005,25(3):27-
[108]李雄飞,李军.数据挖掘与知识发现[M].高等教育出版社,2003-11-1
[109]林杰斌,刘明德,陈湘.数据挖掘与OLAP理论与实务[M].清华大学出版社,2003-1-1
[110]邓纳姆.数据挖掘教程[M].清华大学出版社,2005-5-1
[111]陈文伟,黄金才.数据仓库与数据挖掘[M].人民邮电出版社,2004-1-1
[112]康晓东.基于数据仓库的数据挖掘技术[M].机械工业出版社,2004-1-1
[113]林丹红.信息资源数字化建设的设想与探索--谈中医药文献资源建设[J].情报探索,2001,(4):1-4.
[114]李文林,赵国平.数据挖掘技术及其在中医药领域的应用[J].中华医学图书情报杂志,2004,13(6):4-6.
[115]曹晋军.基于HIS的循证医学支持系统的设想[J].中华医院管理杂志,2004.20(8).-487-488
[116]高小葵,张琼汉.数据仓库及其在医学领域中的应用[J].医学与计算机应用,2003.16(2).-58-59
[117]屈景辉,廖琪梅,等.医学信息数据库的建立与数据挖掘[J].第四军医大学学报,2001.22(1).-88-89
[118]王宁,王延章,于淼.面向一般决策过程的数据仓库系统研究[J].计算机集成制造系统,2006.12(1).-139-143
[119]王波,张斌,等.面向中医辨证规范的交互式数据挖掘框架[J].世界科学技术:中医药现代化-2006.8(1).-24-30
[120]梁循.数据挖掘:建模、算法、应用和系统[J].计算机技术与发展,2006.16(1):1-4
[121]胡彦.基于数据仓库的决策支持工具的比较研究[J].计算机应用,2000, 20(6):20-24.
[122]Evgeniou T,Pontil M,Poggio T.Regularization networks and support vector machines[J].Advances in Computational Mathematics,2000,13(1):1-50.
[123]Burges C,Scholkopf B.Improving the accuracy and speed of support vectbr learning machines[A].Mozer M.Jordan M。 Petsche T.Advances in Neural Informat ion Process ing Systems[C].Cambridge MA:MIT Press,1997.
[124]Suykens J,Vandewalle J.Least squares support vector machine classifiers[J].Neural Processing Letters,1999,9(3):293-300.
[125]Drucker H,Burges C J,Kaufman L.Support vector regression machines[A].Mozer M,Jordan M,Petsche T.Advances in Neural Information Processing Systems[C].Cambridge MA:MIT Press,1997.
[126]Davide M,Francesco P.Simon H.Simple and Robust Methods for Support Vector Expansions[J].IEEE Transactions on Neural Networks.1999.10(5):1 038-1047
[127]胡侃,夏绍玮.基于大型数据仓库的数据采掘:研究综述[J].软件学报,1998,9(1):53-117.
[128]刘明杰,张晓京,刘洪杰,王秀峰,王治宝.数据仓库在证券交易中的研究与应用[J].计算机工程,2000,26(2):47-49、94
[129]李竹平,吴相林.基于数据仓库的企业管理型会计信息系统研究[J].华中理工大学学报,28(9):10-12
[130]朱凌云,吴宝明.医学数据挖掘的技术、方法及应用.生物医学工程学杂志[J],2003,3(20):559-562
[131]刘莉,徐玉田,马志新.数据挖掘中数据预处理技术综述[J].甘肃科学学报,2003,1(12):117-119
[132]瞿爱珍,庄天戈.计算机辅助医学诊断系统的数据挖掘和知识发现研究[J].国外医学·生物医学工程分册,2002,3(25):97-103
[133]余辉,吕扬生.数据挖掘技术在生物医学领域的应用[J].国外医学·生物医学工程分册,2003,2(26):54-59
[134]吉旭,朱立嘉,赵丰,唐建华.面向知识管理的过程企业知识模型体系研究[J].计算机集成制造系统,2006.12(3).-382-388
[135]施伯乐,汪卫.数据仓库与数据挖掘研究进展[J].计算机应用与软件,2003(11):10-12
[1]Coulter DM,Batch,Meyboom RH,et al.Anti psychotic drugs and heart muscle disorder in international pharmacovigi21ance:data mining study.BMJ,2001;322(7296):1207
[2]DokurZO,Imez T.ECG beat classification by a novel hy2brid neural network.Computer Methods and Program sin Biomedicine,2001;66:167
[3]V efgh i L,LinkensDh.Dynamic monitoring and control of patient an aesthetic and do se levels:time2delay,moving average neural networks,and principal components analysis.Computer Methods and Program s in Biomedicine,1999;59:91
[4]Ying H,Wu Shyu L Y.Detection of V PC using wavelet transform and fuzzy neural network.Proceeding of The First Joint BM ES^EMBS Conference Serving Humanity,Advancing Technology,1999 Oct,Atlanta,GA,USA
[5]Pavlopoulo s S,Kyriacou E,Koutsouris D,et al.Fuzzy neurale two rkbased texture analysis of ultrasonic images.IEEE EngM ed Bio 1M ag,2000;19(1):39
[6]Podgo relecV,Brest J,Koko I P.Power of heterogeneous computing as a vehicle for implementing E(3) medical decision support system.Int J M ed Inf,2000;58:59179
[7]Bo jarczuk CC,Lopes HS,F reitas AA.Genetic programming for knowledge discovery in chest pain diagnosis.IEEE Eng M ed Bio 1M ag,2000;19(4):38
[8]Wang ML,W ai L,Leung KS.Discovery know ledge from medical database using evolutionary algorithm s.IEEE Eng M ed Bio 1M ag,2000;19(4):45
[9]KusiakA,Kern JA,KernstineKH,et al.Autonomous decision making:a data mining app roach.IEEE Trans Inf Techno 1Biomed,2000;4(4)274
[10]Oh rn A,Row land T.Rough sets:a know ledge discovery technique for multi factorial medical outcomes.Am J Phys Med Rehabil,2000;79(1):i00
[11]M itra P,M itra S,Pal SK.Staging of cervical cancer with soft computing.IEEE Trans Bio med Eng,2000;47(7):934
[12]Pavlidis P,Furey TS,L iberto M,et al.Promoter region based classification of genes.Pac Symp Bio comput,2001;151
[13]Hua S,Sun Z.h novel method of protein secondary structure prediction with high segment overlap measure:support vector machineapp roach.J Mo 1Bio 1,2001;308(2):397
[14]Cai YD,L iu XJ,Xu XB,et al.Support vector machines for prediction of protein sub cellular location.Mo 1 Cell Bio IRes Commun,2000;4(4)230
[15]田文敬.中医特色研究应借助现代数据挖掘技术.中医研究,2005年8期
[16]胡镜清,刘保延,王永炎.中医临床个体化诊疗信息特征与数据挖掘技术应用分析.世界科学技术-中医药现代化·中医理论的科学特点.2004第6卷第6期
[17]王波,张斌,魏伟杰.面向中医辨证规范的交互式数据挖掘框架.世界科学技术中医药现代化·思路与方法.P26-30
[18]基于信息和数据挖掘技术的名老中医临床诊疗经验研究思路
[19]赵晓山,罗云坚,罗仁,等.基于数据挖掘的中医证候规范化研究方法学的建立CJCM.中华实用中西医杂志,2005年VOL.(18)NO.
[20]龚德平,高颖,唐涛.基于数据挖掘的数字化中医诊断系统.中国医学影像技术,2003年第19卷204号(P132-134)
[21]陈明,张书河.关联规则在中医疾病证候诊断中的应用.中华医学丛刊2004年第4卷第5期(p14-16)
[22]徐蕾,贺佳,孟虹,等.基于信息熵的决策树在慢性胃炎中医辨证中的应用.第二军医大学学报2004sep:25(9)
[23]秦中广,毛宗源,邓兆智.粗糙集在中医类风湿证候诊断中的应用[J].中 国生物医学工程学报2001;20(4):357-363.
[24]刘晋平,黄宇虹,陆小左.数据挖掘在中医脉诊中的应用,第22卷 2003年第3期:(P9-10)
[25]姚美村,艾路,袁月梅,乔延江.消渴病复方配伍规律的关联规则分析北京中医药大学学报2002年11月第25卷第6期(p48-50)
[26]刘强,刘璨,朱文锋.数据挖掘:心气虚证的鉴别诊断研究福建中医药 2005年03期
[27]尚景盛.胡立胜.牛欣.司银楚.半夏泻心汤配伍应用的数据挖掘试验中日友好医院学报2005年04期
[2]朱文锋.构建“证素辨证”新体系的意义[J].浙江中医药大学学报,2006,30(2):135-
[3]朱文锋,黄碧群,陈新宇.病性证素辨别的意义与方法[J].中医药学刊,2006,24(2):204-
[4]晏峻峰,朱文锋.粗糙集理论在中医证素辨证研究中的应用[J].中国中医基础医学杂志,2006,12(2):90-
[5]朱文锋.论中医症状的规范研究[J].中医杂志,2005,46(9):649-
[6]朱文锋,李灿东,甘慧娟.病位证素的特征[J].福建中医药,2005,36(4)
[7]朱文锋.制定全病域中医辨证量表的设计思路[J].辽宁中医杂志,2005,32(6):521-
[8]朱文锋,晏峻峰.证素辨证新体系的内容及科学意义[J].医学与哲学,2005,26(1):69-
[9]朱文锋,黄碧群.证、证候的辨析与规范[J].山西中医,2005,21(3):1-
[10]朱文锋,甘慧娟.证素内容的辨析[J].湖南中医药导报,2005,11(1):11-
[11]朱文锋,张华敏.“证素”的基本特征[J].中国中医基础医学杂志,2005,11(1):17-
[12]朱文锋,晏峻峰,黄碧群.贝叶斯网络在中医证素辨证体系中的应用[J].中西医结合学报,2006年06期
[13]林鹏,杨波.粗糙集理论与方法[M].科学出版社,2001-7-1
[14]邓乃扬,田英杰.数据挖掘中的新方法-支持向量机[M].科学出版社,2004-06
[15]陈水利,李敬功,王向公.模糊集理论及其应用[M].科学出版社,2005-9-1
[16]李士勇.工程模糊数学及应用[M].哈尔滨工业大学出版社,2004-8-1
[17]张青贵.人工神经网络导论[M].中国水利水电出版社,2004-10-1
[18]蔡自兴,徐光祜.人工智能及其应用(第三版)[M].清华大学出版社,2004-08
[19]Simon Haykin神经网络原理[M].机械工业出版社,2004-01
[20]王国胤.Rough集理论与知识获取[M].西安:西安交通大学出版社,2001.5.
[21]李男,邱天爽.基于粗糙集的数据挖掘技术及其在临床医学诊断中的应用[J].上海生物医学工程,2002,2(23):3-7.
[22]方积乾.卫生统计学[M].人民卫生出版社,2003-8-1
[23]Coulter DM,Bate A,Meyboom RH,etal.Anti psychotic drugs and heart muscle disorder in international pharmacovigi21ance: data mining study. BMJ , 2001; 322 (7296) : 1207
[24]DokurZ0 , lmez T. ECG beat classification by a novel hy2brid neural network. Computer Methods and Program sin Biomedicine, 2001; 66 : 167
[25]V efgh i L , LinkensDA. Dynamic monitoring and control of patient an aesthetic and do se levels: time2delay, moving average neural networks, and principal components analysis. Computer Methods and Program s in Biomedicine, 1999; 59 : 91
[26]Ying H, Wu Shyu L Y. Detection of V PC using wavelet transform and fuzzy neural network. Proceeding of The First Joint BM ES^ EMBS Conference Serving Humanity, Advancing Technology, 1999 Oct, Atlanta, GA, USA
[27]Pavlopoulo s S, Kyriacou E, Koutsouris D, et al. Fuzzy neurale two rkbased texture analysis of ultrasonic images. IEEE EngM ed Bio 1M ag, 2000; 19 (1) : 39
[28]Podgo relecV, Brest J, Koko 1 P. Power of heterogeneous computing as a vehicle for implementing E (3) medical decision support system. Int J M ed Inf, 2000; 58 : 59179
[29]Bo jarczuk CC, Lopes HS, F reitas AA. Genetic programming for knowledge discovery in chest pain diagnosis. IEEE Eng M ed Bio 1M ag, 2000; 19 (4): 38
[30]Wang ML, Wai L, Leung KS. Discovery know ledge from medical database using evolutionary algorithm s. IEEE Eng Med Biol M ag, 2000; 19(4)45
[31]Kusiak A , Kern JA , Kernstine KH, et al. Autonomous decision making: a data mining app roach. IEEE Trans Inf Techno 1Biomed, 2000; 4 (4): 274
[32]Oh rn A , Row land T. Rough sets: a knowledge discovery technique for multifactorial medical outcomes. Am J Phys Med Rehabil , 2000; 79(1): 100
[33]M itra P, M itra S, Pal SK. Staging of cervical cancer with soft computing. IEEE Trans Bio med Eng, 2000; 47 (7) : 934
[34]Pavlidis P, Furey TS, L iberto M , et al. Promoter region based classification of genes. Pac Symp Bio comput, 2001; 151
[35]Hua S, Sun Z. A novel method of protein secondary structure prediction with high segment overlap measure: support vector machine app roach.J Mo l Bio l,2001;308(2):397
[36]Cai YD,L iu XJ,Xu XB,et al.Support vector machines for prediction of protein sub cellular location.Mo 1 Cell Bio l Res Commun,2000;4(4):230
[37]田文敬.中医特色研究应借助现代数据挖掘技术[J].中医研究,2005(8)
[38]胡镜清,刘保延,王永炎.中医临床个体化诊疗信息特征与数据挖掘技术应用分析[J].世界科学技术-中医药现代化,2004;6(1)
[39]王波,张斌,魏伟杰.面向中医辨证规范的交互式数据挖掘框架[J].世界科学技术中医药现代化,2006 Vol.8 No.1 P.24-30
[40]王映辉,姜在旸,闫英杰.基于信息和数据挖掘技术的名老中医临床诊疗经验研究思路[J].世界科学技术-中医药现代化,2005年01期
[41]赵晓山,罗云坚,罗仁,等.基于数据挖掘的中医证候规范化研究方法学的建立[J].中华实用中西医杂志,2005年VOL.(18) NO.
[42]龚德平,高颖,唐涛.基于数据挖掘的数字化中医诊断系统[J].中国医学影像技术,2003年第19卷204号(P132-134)
[43]陈明,张书河.关联规则在中医疾病证候诊断中的应用[J].中华医学丛刊,2004年第4卷第5期(p14-16)
[44]刘晋平,黄宇虹,陆小左.数据挖掘在中医脉诊中的应用[J].天津中医学院学报,2003,22(3):9
[45]姚美村,艾路,袁月梅,乔延江.消渴病复方配伍规律的关联规则分析[J].北京中医药大学学报,2002年11月第25卷第6期(p48-50)
[46]刘强,刘璨,朱文锋.数据挖掘:心气虚证的鉴别诊断研究[J].福建中医药,2005年03期
[47]尚景盛,胡立胜,牛欣,司银楚.半夏泻心汤配伍应用的数据挖掘试验[J].中日友好医院学报,2005年04期
[48]徐蕾,贺佳,孟虹,等.基于信息熵的决策树在慢性胃炎中医辨证中的应用[J].第二军医大学学报,2004sep;25(9)
[49]秦中广,毛宗源,邓兆智.粗糙集在中医类风湿证候诊断中的应用[J].中国生物医学工程学报,2001;20(4):357-363.
[50]马廷淮,赵亚伟,张海盛,曾振柄.基于粗糙集的决策规则约简[J].计算机工程.2003,Vol.29,No.12,pp:5-7
[51]方敏,陈雁翔.基于模糊神经的机械故障诊断方法的研究[J].控制理论与应用,1998,15(3):460-465
[52]Z.Pawlak.Rough sets and intelligent data analysis[J].Information Sciences,2002,147:1-12
[53]杨燮,杨炳儒.一种属性与值约简简化算法[J].小型微型计算机系统,2004,25(2):245-247.
[54]Z.Pawlak,ROUGH SETS:Theoretical Aspects of Reasoning about Data[M].Kluwer Academic Publishers,1991
[55]黄梯云,卢涛,程岩.数据挖掘中一种基于粗糙集理论的属性集离散映射方法[J].情报学报,2002,21(4):391-396.
(56]刘清.Rough集及Rough推理[M].北京:科学出版社,2001.
[57]Pawlak Z.Rough Sets[J].International Journal of Information and Computer Science.1982,11:341-356.
[58]Zdizislaw Pawlak,Jerzy Grzymala-Busse,Roman Slowinski,Wojciech Ziarko.Rough sets[J].Communication of the ACM,1995,38(11):89-95.
[59]曾黄麟.粗糙集理论及其应用[M].重庆:重庆大学出版社,1996.
[60]钟波,肖智,周家启.组合预测中基于粗糙集理论的权值确定方法[J].重庆大学学报,2002,25(7):127-130
[61]张文修,仇国芳.基于粗糙集的不确定决策[M].清华大学出版社,2005-08
[62]林鹏,杨波.粗糙集理论与方法[M].科学出版社,2001-07
[63]徐袭,姚琼荟,石敏.基于粗糙集与支持向量机的故障智能分类方法[J].计算技术与自动化,2006.25(1).-32-34
[64]邓乃扬,田英杰.数据挖掘中的新方法-支持向量机[M].科学出版社,2004-6-1
[65]张铃.支持向量机理论与基于规划的神经网络学习算法[J].计算机学报,2001,24(2):113-118.
[66]马永军,李孝忠,王希雷.基于模糊支持向量机和核方法的目标检测方法研究[J].天津科技大学学报,2005,20(3);29-32.
[67]张莉.支撑向量机与核方法研究[D].西安:西安电子科技大学,2002.
[68](美)瓦普尼克.统计学习理论的本质[M].张学工译北京;清华大学出版社,2000.
[69]范昕炜.支持向量机算法的研究及其应用[D].浙江大学,2003-05.
[70]李建民,张钹林,福宗.支持向量机的训练算法[J].清华大学学报(自然科学版),2003,43(1):120-124.
[71]威武,常俊林,邵惠鹤.一种贝叶斯证据框架下支持向量机建模方法的研究[J].控制与决策,2004。19(5):525-533.
[72]刘向东,陈兆乾.基于支持向量机方法的人脸识别研究[J].小型微型计算 机系统,2004,25(12):2 261 2 263.
[73]张爱丽,刘广利,刘长宇.基于SVM的多类文本分类研究[J].情报杂志,2001,23(9):6-10.
[74]魏新,冯兴杰,刘山.基于支持向量机的多元文本分类研究[J].海军工程大学学报.2004,16(5):30-32.
[75]Vapnik V.Statistical learning theory[M],New York:John Wiley&Sons.1998.
[76]Domeniconi C,Gunopulos D.Incremental support vector ma-chine construction[A].Proceedings of IEEE International Conference on Data Mining[C].San Jose,USA:IEEE,2001:589-592.
[77]VAV GESTEL T,SUYKENS JAK BAESTAENS D,et al.Finch.cial time series prediction using least squares support vector machines within the evidence framework[J].IEEE Trans on Neural Networks,2001,12(4):809-821.
[78]KRUIF BJ VRIES TJA.On using a support vector machinein learning feed forward control[A]Proceedings of IEEE/ASME International Conference on Advanced Intelligent Mechatronics[C].Coma.Italy,2001.1:272-277.
[79]V N Vapnik.The Nature of Statistical Learning Theory[M].NewYork:Springer,1999.
[80]V N Vapnik.Statistical Learning Theory[M].New York:Wiley,1998.
[81]B E Boser,et al.A Training Algorithm for Optimal Margin Classifiers[C].Pittsburgh,PA:ACM Press,1992.144-152.
[82]EOsuna,R Freund,F Girosi.An Improved Trmmng Algorithm for Support Vector Machines[C].New York,1997.276-285.
[83]E Osuna,R Freund,F Gimsi.Supppo Vector Machines:Training and Application JR].Cambridge,MA:Massachusetts Institute of Technology,AILab,1997.
[84]Platt J.Fast Training of Support Vector Machines Using Sequential Minimal Optimization[C].Cambridge,MA:MIT Press,1999.1S5208.
[85]J Platt.Using Analytic QP and Sparseness tO Speed Training of Support VectorMachines[C].Cambridge,MA:MIT Press,1999.557-563.
[86]Vapnik V.The nature of statistical learning theory[M].New York:Springer-Verlag,1995.
[87]Cortes C,Vapnik V.Support vector networks[J].Machine learning,1995,20(1):273 297.
[88]Smola A,Scholkopf B.On a kernel based method for pattern recognition,regression,approximation and operator inversion[J].Algorithmica,1998,22(1):211-231.
[89]Chang C C,1.in C J.Training nu support vector regression:theory and algorithms E J].Neural Computati.n,2002,11(1):1959-1977.
[90]Gill PE,Murray,W,Wright M H.Practical optimization[M].New York:Academic Press,1981.
[91]Platt J.Fast Training of Support Vector Machines Using Sequential Minimal Optimization[A].Scholkopf B,Burges C,Smola h.Advances in Kernel Methods-Support Vector Learning[C].Cambridge MA:MIT Press,1999.
[92]Fei S,Lawrence K,Daniel D.Multiplicative updates for nonnegative quadratic programming in support vector machines[h],suztlnna B,Sebastian T,Klaus O.Advances in Neural Information Processing Systems[(?).Cambridge MA:MIrr Press,2003.
[93]常玉清,邹伟,王福利,毛志忠.基于支持向量机的软测量方法研究[J].控制与决策,2005.20(11).-1307-1310
[94]陈淋艳,封筠.支持向量机分类器若干核心问题的研究[J].包头钢铁学院学报,2005.24(4).-318-320
[95]高智勇,龚健雅,秦前清,林家瑞.支持向量机在早期癌症检测中的应用[J].生物医学工程学杂志,2005.22(5).-1045-1048
[96]沈利,杨杰,周越.基于支持向量机的室性早搏捡测[J].生物医学工程学杂志,2005.22(1).-78-81
[97]丁彦蕊,蔡宇杰,须文波.基于氨基酸组成预测蛋白质热稳定性的v-支持向量机方法[J].计算机与应用化学,2005.22(6).-459-465
[98]陈永义.支持向量机方法与模糊系统[J].模糊系统与数学,2005.19(1)1-11
[99]齐志泉,田英杰,徐志洁.支持向量机中的核参数选择问题[J].控制工程2005.12(4).-379-381
[100]杜晓东李岐强.支持向量机及其算法研究[J].信息技术与信息化,2005(3).-37-40
[101]胡国胜.支持向量机算法及应用[J].现代电子技术,2005.28(3).-106-109
[102]贾银山,贾传荧.一种加权支持向量机分类算法[J].计算机工程, 2005.31(12).-23-25
[103]刘向东,骆斌,陈兆乾.支持向量机最优模型选择的研究[J].计算机研究与发展,2005.42(4).-576-581
[104]白亮,老松杨,胡艳丽.支持向量机训练算法比较研究[J].计算机工程与应用,2005.41(17).-79-81
[105]朱文锋.证候辨证量表制定的科学性要求[J].中国中医药信息杂志,2005,12(8):93-
[106]朱文锋,黄碧群,朱镇华.借鉴量表法研制中医症状辨证量表[J].中华现代临床医学杂志,2005,3(23):2474-
[107]朱文锋.症状辨证调查表设计的特色性要求[J].湖南中医学院学报,2005,25(3):27-
[108]李雄飞,李军.数据挖掘与知识发现[M].高等教育出版社,2003-11-1
[109]林杰斌,刘明德,陈湘.数据挖掘与OLAP理论与实务[M].清华大学出版社,2003-1-1
[110]邓纳姆.数据挖掘教程[M].清华大学出版社,2005-5-1
[111]陈文伟,黄金才.数据仓库与数据挖掘[M].人民邮电出版社,2004-1-1
[112]康晓东.基于数据仓库的数据挖掘技术[M].机械工业出版社,2004-1-1
[113]林丹红.信息资源数字化建设的设想与探索--谈中医药文献资源建设[J].情报探索,2001,(4):1-4.
[114]李文林,赵国平.数据挖掘技术及其在中医药领域的应用[J].中华医学图书情报杂志,2004,13(6):4-6.
[115]曹晋军.基于HIS的循证医学支持系统的设想[J].中华医院管理杂志,2004.20(8).-487-488
[116]高小葵,张琼汉.数据仓库及其在医学领域中的应用[J].医学与计算机应用,2003.16(2).-58-59
[117]屈景辉,廖琪梅,等.医学信息数据库的建立与数据挖掘[J].第四军医大学学报,2001.22(1).-88-89
[118]王宁,王延章,于淼.面向一般决策过程的数据仓库系统研究[J].计算机集成制造系统,2006.12(1).-139-143
[119]王波,张斌,等.面向中医辨证规范的交互式数据挖掘框架[J].世界科学技术:中医药现代化-2006.8(1).-24-30
[120]梁循.数据挖掘:建模、算法、应用和系统[J].计算机技术与发展,2006.16(1):1-4
[121]胡彦.基于数据仓库的决策支持工具的比较研究[J].计算机应用,2000, 20(6):20-24.
[122]Evgeniou T,Pontil M,Poggio T.Regularization networks and support vector machines[J].Advances in Computational Mathematics,2000,13(1):1-50.
[123]Burges C,Scholkopf B.Improving the accuracy and speed of support vectbr learning machines[A].Mozer M.Jordan M。 Petsche T.Advances in Neural Informat ion Process ing Systems[C].Cambridge MA:MIT Press,1997.
[124]Suykens J,Vandewalle J.Least squares support vector machine classifiers[J].Neural Processing Letters,1999,9(3):293-300.
[125]Drucker H,Burges C J,Kaufman L.Support vector regression machines[A].Mozer M,Jordan M,Petsche T.Advances in Neural Information Processing Systems[C].Cambridge MA:MIT Press,1997.
[126]Davide M,Francesco P.Simon H.Simple and Robust Methods for Support Vector Expansions[J].IEEE Transactions on Neural Networks.1999.10(5):1 038-1047
[127]胡侃,夏绍玮.基于大型数据仓库的数据采掘:研究综述[J].软件学报,1998,9(1):53-117.
[128]刘明杰,张晓京,刘洪杰,王秀峰,王治宝.数据仓库在证券交易中的研究与应用[J].计算机工程,2000,26(2):47-49、94
[129]李竹平,吴相林.基于数据仓库的企业管理型会计信息系统研究[J].华中理工大学学报,28(9):10-12
[130]朱凌云,吴宝明.医学数据挖掘的技术、方法及应用.生物医学工程学杂志[J],2003,3(20):559-562
[131]刘莉,徐玉田,马志新.数据挖掘中数据预处理技术综述[J].甘肃科学学报,2003,1(12):117-119
[132]瞿爱珍,庄天戈.计算机辅助医学诊断系统的数据挖掘和知识发现研究[J].国外医学·生物医学工程分册,2002,3(25):97-103
[133]余辉,吕扬生.数据挖掘技术在生物医学领域的应用[J].国外医学·生物医学工程分册,2003,2(26):54-59
[134]吉旭,朱立嘉,赵丰,唐建华.面向知识管理的过程企业知识模型体系研究[J].计算机集成制造系统,2006.12(3).-382-388
[135]施伯乐,汪卫.数据仓库与数据挖掘研究进展[J].计算机应用与软件,2003(11):10-12
[1]Coulter DM,Batch,Meyboom RH,et al.Anti psychotic drugs and heart muscle disorder in international pharmacovigi21ance:data mining study.BMJ,2001;322(7296):1207
[2]DokurZO,Imez T.ECG beat classification by a novel hy2brid neural network.Computer Methods and Program sin Biomedicine,2001;66:167
[3]V efgh i L,LinkensDh.Dynamic monitoring and control of patient an aesthetic and do se levels:time2delay,moving average neural networks,and principal components analysis.Computer Methods and Program s in Biomedicine,1999;59:91
[4]Ying H,Wu Shyu L Y.Detection of V PC using wavelet transform and fuzzy neural network.Proceeding of The First Joint BM ES^EMBS Conference Serving Humanity,Advancing Technology,1999 Oct,Atlanta,GA,USA
[5]Pavlopoulo s S,Kyriacou E,Koutsouris D,et al.Fuzzy neurale two rkbased texture analysis of ultrasonic images.IEEE EngM ed Bio 1M ag,2000;19(1):39
[6]Podgo relecV,Brest J,Koko I P.Power of heterogeneous computing as a vehicle for implementing E(3) medical decision support system.Int J M ed Inf,2000;58:59179
[7]Bo jarczuk CC,Lopes HS,F reitas AA.Genetic programming for knowledge discovery in chest pain diagnosis.IEEE Eng M ed Bio 1M ag,2000;19(4):38
[8]Wang ML,W ai L,Leung KS.Discovery know ledge from medical database using evolutionary algorithm s.IEEE Eng M ed Bio 1M ag,2000;19(4):45
[9]KusiakA,Kern JA,KernstineKH,et al.Autonomous decision making:a data mining app roach.IEEE Trans Inf Techno 1Biomed,2000;4(4)274
[10]Oh rn A,Row land T.Rough sets:a know ledge discovery technique for multi factorial medical outcomes.Am J Phys Med Rehabil,2000;79(1):i00
[11]M itra P,M itra S,Pal SK.Staging of cervical cancer with soft computing.IEEE Trans Bio med Eng,2000;47(7):934
[12]Pavlidis P,Furey TS,L iberto M,et al.Promoter region based classification of genes.Pac Symp Bio comput,2001;151
[13]Hua S,Sun Z.h novel method of protein secondary structure prediction with high segment overlap measure:support vector machineapp roach.J Mo 1Bio 1,2001;308(2):397
[14]Cai YD,L iu XJ,Xu XB,et al.Support vector machines for prediction of protein sub cellular location.Mo 1 Cell Bio IRes Commun,2000;4(4)230
[15]田文敬.中医特色研究应借助现代数据挖掘技术.中医研究,2005年8期
[16]胡镜清,刘保延,王永炎.中医临床个体化诊疗信息特征与数据挖掘技术应用分析.世界科学技术-中医药现代化·中医理论的科学特点.2004第6卷第6期
[17]王波,张斌,魏伟杰.面向中医辨证规范的交互式数据挖掘框架.世界科学技术中医药现代化·思路与方法.P26-30
[18]基于信息和数据挖掘技术的名老中医临床诊疗经验研究思路
[19]赵晓山,罗云坚,罗仁,等.基于数据挖掘的中医证候规范化研究方法学的建立CJCM.中华实用中西医杂志,2005年VOL.(18)NO.
[20]龚德平,高颖,唐涛.基于数据挖掘的数字化中医诊断系统.中国医学影像技术,2003年第19卷204号(P132-134)
[21]陈明,张书河.关联规则在中医疾病证候诊断中的应用.中华医学丛刊2004年第4卷第5期(p14-16)
[22]徐蕾,贺佳,孟虹,等.基于信息熵的决策树在慢性胃炎中医辨证中的应用.第二军医大学学报2004sep:25(9)
[23]秦中广,毛宗源,邓兆智.粗糙集在中医类风湿证候诊断中的应用[J].中 国生物医学工程学报2001;20(4):357-363.
[24]刘晋平,黄宇虹,陆小左.数据挖掘在中医脉诊中的应用,第22卷 2003年第3期:(P9-10)
[25]姚美村,艾路,袁月梅,乔延江.消渴病复方配伍规律的关联规则分析北京中医药大学学报2002年11月第25卷第6期(p48-50)
[26]刘强,刘璨,朱文锋.数据挖掘:心气虚证的鉴别诊断研究福建中医药 2005年03期
[27]尚景盛.胡立胜.牛欣.司银楚.半夏泻心汤配伍应用的数据挖掘试验中日友好医院学报2005年04期