基于混合智能的中医辨证系统研究
|
摘要
在长期与疾病的斗争中，中医演化并形成了一套独特且完整的理论体系,为中国及世界人民的健康做出了不可磨灭的贡献，在诸如慢性乙型肝炎的个体化治疗中显示出特有的优势，以至于越来越受到各国人民的欢迎，以及引起许多研究者的重视。但是传统中医诊断学的经验性、不确定性、模糊性等特点，严重制约了中医的发展和应用。中医证的研究一直是中医现代化研究的关键之一，也是中医用药和治疗的重要依据，其核心是证候分类和诊断标准的研究，然而目前的中医辨证过程缺少严格设计的统一框架，和规范化、定量化的诊断标准，如何将经验且模糊的中医辨证过程规范化、客观化和具有可计算性是本文研究的主要问题。
本文旨在运用智能技术从中医和西医两个角度对中医证候进行综合性研究，引入混合智能系统理论，为中医辨证过程设计一个具有规范化和客观化的整体框架，并以慢性乙型肝炎为例建立混合智能中医辨证系统，为中医临床实践提供现代化的技术手段。由于当前应用于中医证候分类研究的方法繁多，但仍没有一个普遍适用的方法，而且由于中医证候的复杂性、多模式性等特点，也使得证候辨证过程不能简单的使用某种单一技术来模拟，为此借鉴复杂性科学研究的理论和方法进行证候研究成为可能。本文将在中医辨证的研究现状和相关智能算法的基础上，提出适合于中医辨证的理论方法和系统实施方案。
1．基于多视图的混和属性选择
属性选择作为一项重要的数据预处理技术，主要目的是识别和消除样本的属性集中与预测结果不相关的或冗余的属性。中医数据集包含从主、客观手段获取的数据，其样本数量有限，但属性种类繁多且性质不同，正确有效的属性选择是构建中医辨证模型的重要基础。现有的属性选择方法很多，但都不能全面的获取与证候密切相关的关键属性。本论文提出了基于多视图的混合属性选择方法MVHFS(Multi-View Based Hybrid Feature Selection)。该方法利用领域知识，将原有的整体属性空间分割成中医症状、中医体征和西医指标视图，并在每个视图中分别运行由多个基于filter模式的属性选择方法构成的混合属性选择算法，提取和每个证候密切相关的中医症状、中医体征和西医指标。该方法从中西医两个侧面提取证候的关键属性，且得到的构成每个证候的关键属性集不同，体现了证候之间的差异，为后续证候辨证模型的构建奠定基础。
2．结合分布信息计算属性权重
属性权重是属性重要程度的一种主观评价和客观反映的综合度量。在中医辨证领域，不同的属性对证候诊断的重要程度和作用是不等的，一个属性的作用越重要，其相应的权重就越大。在中医领域常使用属性整体出现的频率来计算该属性的重要程度，并不考虑在证候间分布的信息。本文提出了一个改进的TF-IDF算法，用于计算属性权重，可显示的区分不同属性对证候的作用，也可量化的显示出即使同一属性对不同证候的作用程度也是不同的，符合中医理论，也为后续证候辨证模型的构建奠定了基础。
3．基于属性选择的混合智能中医辨证模型
中医辨证的本质是证候分类。现有的分类方法很多，但由于中西医属性和证候之间的关系比较复杂，用单一分类器或单一模型很难提高其辨证精度。除此之外，在中医诊断学领域，获取每位患者的类别概率估计是非常重要的，基于此才能准确的为每位患者设置其用药和治疗方案。为此，本文引入混合智能系统理论及其思想，选用BayesNet、改进的概率决策树（WPET）和改进的分类关联规则分析(WCBA)，进行加权融合，构建了一个基于属性选择的混合智能中医辨证方法。通过实验对比分析，该方法不论是对UCI标准数据集还是对慢性乙型肝炎数据集都有很好的性能，证明了该方法的有效性。而且通过对180例慢性乙型肝炎未标注新样本的预测，展现了该方法应用于临床实践的美好前景。
4．辨证系统的开发
在研究中医辨证过程和方法的基础上，论文研发了针对慢性乙型肝炎病例的中医辨证系统原型，该系统利用所提出的属性选择算法，可获得与每个证候密切相关的属性子集；使用改进的属性权重计算方法可获得与每个证候各自密切相关的属性的权重；使用系统的混合辨证模型可以判别新样本的主要证候和次要证候；并在新样本和新技术的增加过程中，系统的辨证模型将得到不断完善。
In a long course of struggling against diseases, traditional Chinese medicine(TCM) has been evolved into a unique and integrated theoretical system, and has beenremarkably contributing to the health of people in China and all over the world. TCMhas been clinically observed to have dramatic performance in treating many chronicand systematic diseases such as the treatment of chronic hepatitis B (CHB). So TCMis getting more and more popularity, and attracted the attention of many researcher-s. However, it also has been badly hindered from being popularized and further de-veloped due to the empirical, unquantifiable and obscure features of its diagnostics.Syndrome differentiation in TCM is an important part in the theory of TCM. It is alsoan important basis for making up a prescription and treatment in clinical. The core ofTCM syndrome differentiation is the study of syndrome classification and diagnosticcriteria. However, the current process of TCM syndrome differentiation is lack of astrict designed and unified framework, and a standardized and quantitative diagnosticcriterion. Therefore, it is the issue to study in this article on how to standardize, objec-tify and be computable with computability the syndrome differentiation of traditionalChinese medicine science, which is full of empirical and obscurity.
This paper aims to use intelligent techniques to conduct a comprehensive studyabout syndrome from the two perspectives of Chinese medicine and western medicine.In order to design a standardization and objective framework for TCM syndrome d-ifferentiation process, this paper introduces the theory of hybrid intelligent systemto establish a hybrid intelligent based syndrome differentiation for CHB. As current-ly much more research methods applied to TCM syndrome classification, but stillhave not a universally applicable method. On the other hand, due to the complexi-ty and multi-mode of syndromes, the process of syndrome differentiation can not be accurately simulated by one technology. Thereby, it is possible to use theories andmethods of the complexity of scientific research to study syndrome. On the basis ofunderstanding and analyzing the current syndrome differentiation research state andrelating intelligent algorithms, the main achievement of this paper is as follows:
1. Multi-view based hybrid feature selection
Feature selection is an important technique of data pre-processing, which is aimedto recognize so as to eliminate the features, in all features, which are redundant or irrel-evant to the issue studied. The dataset of TCM has objective and subjective features,the number is huge. At the same time, collecting data is never an easy job in CHBapplications because of time consuming and costly work. So feature selection is thekey step in the TCM syndrome differentiation. There are so many feature selectionmethods currently. But they can not obtain a comprehensive result of the key fea-tures of syndromes by itself respectively. So in this paper, we propose a Multi-Viewbased Hybrid Feature Selection (MVHFS) method. The proposed method firstly par-tition features of data into different disjoint views according to the nature of features,such as TCM symptoms, TCM signs, and western indicators. And then, the proposedmethod applies hybrid feature selection algorithm, which combines many filters basedfeature selection methods, such as Relief, LVF, mRMR and FCBF, to pick up the keyfeatures of each syndrome on each feature view. The obtained key features of eachsyndrome by proposed method are different each other, which reflects the differencebetween the syndromes, and to lay the foundation for subsequent models of syndromedifferentiation.
2. Calculate feature weights combined with distribution information
Feature weight is a subjective evaluation and objectively reflection of compre-hensive measure about the degree of importance of feature. In the field of TCM,the importance and role of the different features to syndrome diagnosis are differen-t. The more important the role of a feature is, the greater its weight should be. Theresearchers often calculate the feature weights according to the occurrence frequen-cy of the features in TCM. They do not consider the distribution information of thefeatures between classes. In this paper, we propose a modified TF-IDF method tocompute the feature weights. We consider the distribution information of the features between classes. Thereby, it can intuitively distinguish the role of different featuresto syndromes. It also quantified shows that the role of the same feature to differentsyndromes is different. This method is consistent with the theory of TCM, and alsolays the foundation for subsequent models of syndrome differentiation.
3. Hybrid intelligent syndrome differentiation model based on feature selection
The essence of TCM syndrome differentiation is syndrome classification. Thereare many classifying methods currently. However, we can not use single classifier orsingle model to improve the classification accuracy of syndrome differentiation due tothe complicated relationships between syndromes and features of TCM and westernmedicine. In additions, it is important to obtain the class probability estimation abouteach patient in the field of TCM diagnosis. accordingly, the doctors can accuratelymake up the prescription and treatment programs for each patient. In this paper, weintroduce the theory of hybrid intelligent system, weighted fuse BayesNet, WPET andWCBA methods, and construct a hybrid intelligent syndrome differentiation modelbased on feature selection. From the experimental results, we can see that this methodcan obtain optimal performance on UCI datasets and CHB dataset. It is shown that thevalidity of the method. We use the proposed method to predict the class probabilityof new180cases, and obtain consistent results with clinical. Further, the proposedmethod shows the potential applications in clinical practice.
4. Development of the syndrome differentiation system
We integrate some of the proposed algorithms to develop a hybrid intelligentbased syndrome differentiation system, which is applied to CHB dataset. By thissystem, we can obtain the optimal feature subsets and predict the syndrome and classprobability of an input case. In the future, this system can fuse new technology forfurther improvement.
本文旨在运用智能技术从中医和西医两个角度对中医证候进行综合性研究，引入混合智能系统理论，为中医辨证过程设计一个具有规范化和客观化的整体框架，并以慢性乙型肝炎为例建立混合智能中医辨证系统，为中医临床实践提供现代化的技术手段。由于当前应用于中医证候分类研究的方法繁多，但仍没有一个普遍适用的方法，而且由于中医证候的复杂性、多模式性等特点，也使得证候辨证过程不能简单的使用某种单一技术来模拟，为此借鉴复杂性科学研究的理论和方法进行证候研究成为可能。本文将在中医辨证的研究现状和相关智能算法的基础上，提出适合于中医辨证的理论方法和系统实施方案。
1．基于多视图的混和属性选择
属性选择作为一项重要的数据预处理技术，主要目的是识别和消除样本的属性集中与预测结果不相关的或冗余的属性。中医数据集包含从主、客观手段获取的数据，其样本数量有限，但属性种类繁多且性质不同，正确有效的属性选择是构建中医辨证模型的重要基础。现有的属性选择方法很多，但都不能全面的获取与证候密切相关的关键属性。本论文提出了基于多视图的混合属性选择方法MVHFS(Multi-View Based Hybrid Feature Selection)。该方法利用领域知识，将原有的整体属性空间分割成中医症状、中医体征和西医指标视图，并在每个视图中分别运行由多个基于filter模式的属性选择方法构成的混合属性选择算法，提取和每个证候密切相关的中医症状、中医体征和西医指标。该方法从中西医两个侧面提取证候的关键属性，且得到的构成每个证候的关键属性集不同，体现了证候之间的差异，为后续证候辨证模型的构建奠定基础。
2．结合分布信息计算属性权重
属性权重是属性重要程度的一种主观评价和客观反映的综合度量。在中医辨证领域，不同的属性对证候诊断的重要程度和作用是不等的，一个属性的作用越重要，其相应的权重就越大。在中医领域常使用属性整体出现的频率来计算该属性的重要程度，并不考虑在证候间分布的信息。本文提出了一个改进的TF-IDF算法，用于计算属性权重，可显示的区分不同属性对证候的作用，也可量化的显示出即使同一属性对不同证候的作用程度也是不同的，符合中医理论，也为后续证候辨证模型的构建奠定了基础。
3．基于属性选择的混合智能中医辨证模型
中医辨证的本质是证候分类。现有的分类方法很多，但由于中西医属性和证候之间的关系比较复杂，用单一分类器或单一模型很难提高其辨证精度。除此之外，在中医诊断学领域，获取每位患者的类别概率估计是非常重要的，基于此才能准确的为每位患者设置其用药和治疗方案。为此，本文引入混合智能系统理论及其思想，选用BayesNet、改进的概率决策树（WPET）和改进的分类关联规则分析(WCBA)，进行加权融合，构建了一个基于属性选择的混合智能中医辨证方法。通过实验对比分析，该方法不论是对UCI标准数据集还是对慢性乙型肝炎数据集都有很好的性能，证明了该方法的有效性。而且通过对180例慢性乙型肝炎未标注新样本的预测，展现了该方法应用于临床实践的美好前景。
4．辨证系统的开发
在研究中医辨证过程和方法的基础上，论文研发了针对慢性乙型肝炎病例的中医辨证系统原型，该系统利用所提出的属性选择算法，可获得与每个证候密切相关的属性子集；使用改进的属性权重计算方法可获得与每个证候各自密切相关的属性的权重；使用系统的混合辨证模型可以判别新样本的主要证候和次要证候；并在新样本和新技术的增加过程中，系统的辨证模型将得到不断完善。
In a long course of struggling against diseases, traditional Chinese medicine(TCM) has been evolved into a unique and integrated theoretical system, and has beenremarkably contributing to the health of people in China and all over the world. TCMhas been clinically observed to have dramatic performance in treating many chronicand systematic diseases such as the treatment of chronic hepatitis B (CHB). So TCMis getting more and more popularity, and attracted the attention of many researcher-s. However, it also has been badly hindered from being popularized and further de-veloped due to the empirical, unquantifiable and obscure features of its diagnostics.Syndrome differentiation in TCM is an important part in the theory of TCM. It is alsoan important basis for making up a prescription and treatment in clinical. The core ofTCM syndrome differentiation is the study of syndrome classification and diagnosticcriteria. However, the current process of TCM syndrome differentiation is lack of astrict designed and unified framework, and a standardized and quantitative diagnosticcriterion. Therefore, it is the issue to study in this article on how to standardize, objec-tify and be computable with computability the syndrome differentiation of traditionalChinese medicine science, which is full of empirical and obscurity.
This paper aims to use intelligent techniques to conduct a comprehensive studyabout syndrome from the two perspectives of Chinese medicine and western medicine.In order to design a standardization and objective framework for TCM syndrome d-ifferentiation process, this paper introduces the theory of hybrid intelligent systemto establish a hybrid intelligent based syndrome differentiation for CHB. As current-ly much more research methods applied to TCM syndrome classification, but stillhave not a universally applicable method. On the other hand, due to the complexi-ty and multi-mode of syndromes, the process of syndrome differentiation can not be accurately simulated by one technology. Thereby, it is possible to use theories andmethods of the complexity of scientific research to study syndrome. On the basis ofunderstanding and analyzing the current syndrome differentiation research state andrelating intelligent algorithms, the main achievement of this paper is as follows:
1. Multi-view based hybrid feature selection
Feature selection is an important technique of data pre-processing, which is aimedto recognize so as to eliminate the features, in all features, which are redundant or irrel-evant to the issue studied. The dataset of TCM has objective and subjective features,the number is huge. At the same time, collecting data is never an easy job in CHBapplications because of time consuming and costly work. So feature selection is thekey step in the TCM syndrome differentiation. There are so many feature selectionmethods currently. But they can not obtain a comprehensive result of the key fea-tures of syndromes by itself respectively. So in this paper, we propose a Multi-Viewbased Hybrid Feature Selection (MVHFS) method. The proposed method firstly par-tition features of data into different disjoint views according to the nature of features,such as TCM symptoms, TCM signs, and western indicators. And then, the proposedmethod applies hybrid feature selection algorithm, which combines many filters basedfeature selection methods, such as Relief, LVF, mRMR and FCBF, to pick up the keyfeatures of each syndrome on each feature view. The obtained key features of eachsyndrome by proposed method are different each other, which reflects the differencebetween the syndromes, and to lay the foundation for subsequent models of syndromedifferentiation.
2. Calculate feature weights combined with distribution information
Feature weight is a subjective evaluation and objectively reflection of compre-hensive measure about the degree of importance of feature. In the field of TCM,the importance and role of the different features to syndrome diagnosis are differen-t. The more important the role of a feature is, the greater its weight should be. Theresearchers often calculate the feature weights according to the occurrence frequen-cy of the features in TCM. They do not consider the distribution information of thefeatures between classes. In this paper, we propose a modified TF-IDF method tocompute the feature weights. We consider the distribution information of the features between classes. Thereby, it can intuitively distinguish the role of different featuresto syndromes. It also quantified shows that the role of the same feature to differentsyndromes is different. This method is consistent with the theory of TCM, and alsolays the foundation for subsequent models of syndrome differentiation.
3. Hybrid intelligent syndrome differentiation model based on feature selection
The essence of TCM syndrome differentiation is syndrome classification. Thereare many classifying methods currently. However, we can not use single classifier orsingle model to improve the classification accuracy of syndrome differentiation due tothe complicated relationships between syndromes and features of TCM and westernmedicine. In additions, it is important to obtain the class probability estimation abouteach patient in the field of TCM diagnosis. accordingly, the doctors can accuratelymake up the prescription and treatment programs for each patient. In this paper, weintroduce the theory of hybrid intelligent system, weighted fuse BayesNet, WPET andWCBA methods, and construct a hybrid intelligent syndrome differentiation modelbased on feature selection. From the experimental results, we can see that this methodcan obtain optimal performance on UCI datasets and CHB dataset. It is shown that thevalidity of the method. We use the proposed method to predict the class probabilityof new180cases, and obtain consistent results with clinical. Further, the proposedmethod shows the potential applications in clinical practice.
4. Development of the syndrome differentiation system
We integrate some of the proposed algorithms to develop a hybrid intelligentbased syndrome differentiation system, which is applied to CHB dataset. By thissystem, we can obtain the optimal feature subsets and predict the syndrome and classprobability of an input case. In the future, this system can fuse new technology forfurther improvement.
引文
[1]孙孙广仁.中医基础理论[M].北京:中国中医药出版社,2002.
[2]郭振球.中医辨证学研究的前景[J].大自然探索,1985,4(13):85–89.
[3]洪净.中医辨证的量化研究现状与展望[J].中国医药学报,2002,17(8):452–454.
[4]杨杰,牛欣.中医诊断信息数字化发展[J].中医药学刊,2006,24(5):810–812.
[5]郭振球.论中医诊断学的发展[J].安徽中医学院学报,1988,7(3):2–5.
[6]蒋依吾,陈建仲.电脑化中医舌诊系统[J].中国中西医结合杂志,2000,20(2):145–147.
[7]王忆勤.中医诊断学[M].北京:中国中医药出版社,2004.
[8]周昌乐.智能中医诊断信息处理技术研究进展与展望[J].中西医结合学报,2006,4(6):560–566.
[9]中国中医药学会内科肝胆病专业委员会.病毒性肝炎中医辨证标准(试行)[J].中医杂志,1992,33(5):39–40.
[10]中药新药临床研究指导原则(试行).病毒性肝炎中医辨证标准(试行)[J].北京:中国医药科技出版社,2002:147–149.
[11]孙占全,西广成.中医辨证的智能系统模型[J].系统仿真学报,2007,19(10):2318–2321.
[12]李宇航,靳琦.计算机模拟中医诊断的客观化研究[J].北京中医药大学学报,1999,22(4):10–12.
[13]邵红,崔文成.医疗诊断专家系统研究进展[J].小型微型计算机系统,2003,24(3):509–512.
[14]陈朝东.一个非处方性药物咨询专家系统的设计与实现[硕士学位论文][D].上海:华东师范大学计算机系,2000.
[15]莫传伟,武哲丽.中医舌诊客观化识别与图像技术的探析[J].中医药学刊,2005,23(6):1032–1034.
[16]岳小强，刘庆.中医舌象计算机识别研究的现状分析[J].中西医结合学报,2004,2(5):326–329.
[17]翁维良.中医舌诊客观化研究[J].中国工程科学,2001,3(1):78–82.
[18]许家佗,张志枫.舌象数字图像采集条件的实验观测[J].中国中医基础医学杂志,2007,13(1):23–27.
[19]王鸿谟.中医色诊学的定位定量研究[J].中国医药学报,1998,13(4):14–18.
[20]曾常春,王先菊.中医色诊研究及光子学技术在色诊中的应用[J].中国中医基础医学杂志,2004,10(9):74–76.
[21]朱咏华.中医症状的规范化研究[J].湖南中医学院学报,2002,22(3):35–37.
[22]由松.中医症状及证候的量化方法探讨[J].北京中医药大学学报,2002,25(2):13–15.
[23]魏守水,韩庚祥.基于金氏脉学的新型脉诊仪的研究[J].电子测量与仪器学报,2005,19(5):90–94.
[24]汤伟昌.三部脉象检测系统的研究[J].中国医疗器械杂志,2005,29(3):164–166.
[25]赵翠敏,杨学智.中医脉诊仪研制情况概述[J].2006国际传统医药创新与发展态势论坛论文集,2006增刊:260–262.
[26]黄碧群.基于信息融合理论的中医四诊合参研究[J].中国中医药杂志,2004,2(6):324–325.
[27] ZHENG N, WU Z. TCM-SIRD: an integrated aided system for traditional Chi-nese medicine Sizheng[C]//Proceedings of the IEEE International Conferenceon Systems, Man&Cybernetics. Netherlands: IEEE,2004:3864–3868.
[28]刘士敬.中医各系统病症脾气虚证诊断因素的多元逐步回归分析[J].甘肃中医学院学报,1996,9(3):4–7.
[29]潘毅.心系疾病心气虚证的心功能指标判别诊断[J].山东中医杂志,1997,16(4):151–152.
[30]李永健,李永健.154例原发性肝癌临床症状多元Logistic回归分析[J].中国中医基础医学杂志,2003,9(8):59–62.
[31]王磊,苏越.偏最小二乘法在肝炎后肝硬化中医证候分类建模中的应用[J].中西医结合学报,2008,6(11):1122–1128.
[32] WANG Y, MA L, LIU P. Feature selection and syndrome prediction for livercirrhosis in traditional Chinese medicine[J]. Comput. Methods Prog. Biomed.,2009,95(3):249–257.
[33] CHU N, MA L, ZHOU M. An Intelligent TCMEP Differentiation Sys-tem[C]//The8th World Congress on Intelligent Control and Automation. Jinan,Shandong: IEEE,2010:2686–2691.
[34] CHU N, LIZHUANG M, LI J, et al. Rough set based feature selection forimproved differentiation of traditional Chinese medical data[C]//Seventh Inter-national Conference on Fuzzy Systems and Knowledge Discovery, FSKD2010.Yantai, Shandong: IEEE,2010:2667–2672.
[35]王亚强,金晖.基于关联规则的中医症状组团分析[J].四川大学学报(自然科学版),2009,46(6):1650–1654.
[36]北京市科学技术志编辑委员会.1981年，中国科学院、北京第二医学院和北京中医院在中国首次研制成功“关幼波老中医诊断肝病的电子计算机中医专家系统”[J].2002.
[37] http://ziliao.hzu.edu.cn/n46198.html.
[38]吕汉兴,孙德保.中医专家系统辨证推理的决策模型[J].华中理工大学学报,1989,17(6):67–72.
[39]章浩伟,朱训生.中医证候分级推理诊断方法[J].计算机工程与应用,2005:207–209.
[40]吴芸.基于软计算方法的中医智能辨证处理系统[J].厦门理工学院学报,2008,16(2):50–55.
[41]孙佰清,潘启树.医疗诊断系统专家知识的表达与获取方法[J].哈尔滨工业大学学报,2001,33(1):134–136.
[42]李梢.从维度与阶度探讨中医证候的特征及标准化方法[J].北京中医药大学学报,2003,26(3):1–4.
[43]甘琴霞.模糊数学在中医学领域的应用进展[J].江苏中医药,2007,39(1):61–63.
[44]张琴,刘平.900例肝炎后肝硬化中医证候判别模式的研究[J].中国中西医结合杂志,2006,26(8):694–697.
[45]白云静,申洪波.基于人工神经网络的中医证候非线性建模研究[J].中国中医药信息杂志,2007,14(7):3–4,83.
[46]施明辉.人工神经网络在中医诊断中的应用现状与趋势[J].中国中医药信息杂志,2007,14(1):2–5.
[47]赵卫东,盛昭瀚.基于人工神经网络的案例推理医疗诊断[J].东南大学学报(自然科学版),2000,130(13):46－50.
[48]龚德平,高颖.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,2003,19(1):134–136.
[49]瞿海斌,王祥君.基于决策树的血瘀证诊断规则自动归纳方法[J].中国生物医学工程学报,2005,24(6):709–727.
[50] WANG H. A Novel Method for Quantitative Diagnosis Based on Decision Treein Traditional Chinese Medicine[C]//Proceedings of the Eighth InternationalConference on Machine Learning and Cybernetics. Baoding, Hebei: IEEE,2009:344–349.
[51]秦中广,毛宗源.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.
[52]张承江,闫朝升.中医肾病治疗信息中关联规则的挖掘算法[J].黑龙江大学自然科学学报,2005,22(6):842–845.
[53] BO W, MING-WEI Z, BIN Z, et al. Data Mining Application to SyndromeDifferentiation in Traditional Chinese Medicine[C]//Proceedings of the SeventhInternational Conference on Parallel and Distributed Computing, Applicationsand Technologies. Washington, DC, USA: IEEE Computer Society,2006:128–131.
[54] YAN J F, ZHAN Y, ZHU W F. Application of Support Vector Machine inTCM Diagnosis[C]//Proceedings of the2009WRI Global Congress on Intelli-gent Systems-Volume01. Washington, DC, USA: IEEE Computer Society,2009:338–342.
[55]罗丛波.基于模型诊断的应用[J].科技情报开发与经济,2007,17(3):152–153.
[56]李占山.基于模型诊断推理的回顾与展望[J].计算机科学,1998,25(6):54–58.
[57]操龙兵.开放复杂智能系统――基础、概念、分析、设计与实施[M].北京:人民邮电出版社,2008.
[58]贵忠华.智能混合系统研究综述[J].信息与控制,2000,29(1):59–64.
[59]王长琼.基于混合智能的故障诊断与维修决策模型研究与实践[博士论文][D].武汉,北京:武汉交通科技大学.
[60] LI S, DUAN Y, KINMAN R, et al. A framework for a hybrid intelligent systemin support of marketing strategy development[J]. Marketing Intelligence andPlanning,1999,17(4):209–216.
[61]程国建,张喜锋.混合智能系统在测井储层识别中的应用[J].电子技术应用,2007,10:128–130.
[62] FUNG R Y K, POPPLEWELL K, XIE J. An intelligent hybrid system for cus-tomer requirements analysis and product attribute targets determination[J]. In-ternational Journal of Production Research,1998,36(1):13–34.
[63] MORI H, TAKAHASHI A. Hybrid intelligent system for daily maximum tem-perature forecasting in smart grids[C]//International Symposium on Circuitsand Systems (ISCAS2011). Rio de Janeiro, Brazil: IEEE,2011:1852–1855.
[64] CORTES C, VAPNIK V. Support-Vector Networks[J]. Mach. Learn.,1995,20(3):273–297.
[65] BENNETT K P. Advances in kernel methods[M]//. Cambridge, MA, USA: MITPress,1999:307–326.
[66] BENNETT K P, CAMPBELL C. Support vector machines: hype or hallelu-jah?[J]. SIGKDD Explor. Newsl.,2000,2(2):1–13.
[67]赵恒平.混合智能系统及其在软测量建模中的应用[博士论文][D].上海:华东理工大学.
[68]王刚,黄丽华.混合智能系统研究综述[J].系统工程学报,2010,25(4):569–578.
[69] MEESAD P, YEN G G. A Hybrid Intelligent System for Medical Diag-nosis[C]//Proceedings of International Joint Conference on Neural Networks.Washington D.C., U.S.A.: IEEE,2001:2558–2563.
[70] SEHGAL M S B, GONDAL I, DOOLEY L. Support Vector Machine and Gen-eralized Regression Neural Network Based Classification Fusion Models forCancer Diagnosis[C]//Proceedings of the Fourth International Conference onHybrid Intelligent Systems. Washington, DC, USA: IEEE Computer Society,2004:49–54.
[71] REDDY N P, ROTHSCHILD B M. Hybrid fuzzy logic committee neural net-works for classification in medical decision support systems[C]//Proceedingsof the Second Joint EMBS/BMES Conference. Houston, Texas, USA: IEEEComputer Society,2002:30–31.
[72] ALAHAKONE A, SENANAYAKE S. Hybrid fuzzy logic committee neural net-works for classification in medical decision support systems[C]//IEEE Confer-ence on Multisensor Fusion and Integration for Intelligent Systems (MFI). SaltLake City, Utah, USA: IEEE Computer Society,2010:38–43.
[73] NEGOITA M G, NEAGU D, PALADE V. New Trends of Developing HybridIntelligent Systems–AIS Hybridization and DNA-Hybridization[J]. Compu-tational Intelligence Studies in Fuzziness and Soft Computing,2005,174:151–161.
[74] TSAKONAS A, TSILIGIANNI T, DOUNIAS G. Evolutionary Neural Logic Net-works in Splice-junction Gene Sequences Classification[J]. International Jour-nal on Artificial Intelligence Tools,2006,15:287–308.
[75] KALRA G, PENG Y, GUO M, et al. A hybrid intelligent system for formula-tion of BCS Class II drugs in hard gelatin capsules[C]//Proceedings of the9thInternational Conference on Neural Information Processing. Singapore: IEEEService Center,2002，4:1987–1991.
[76] WANG M, GENG Z, WANG M, et al. Combination of network con-struction and cluster analysis and its application to traditional chinesemedicine[C]//Proceedings of the Third international conference on Advancesin Neural Networks-Volume Part III. Berlin, Heidelberg: Springer-Verlag,2006:777–785.
[77]王彦.中医证候信息的数据挖掘[博士论文][D].上海:上海交通大学.
[78] COVER T, VANCAMPENHOUT J. On the possible orderings in the measurementselection problem[J]. IEEE Transactions on System,1977,7(9):657–661.
[79] BIESIADA J, DUCH W. Feature selection for high-dimensional data: aKolmogorov-Smirnov correlation-based filter[J]. Computer Recognition Sys-tems,2005,30:95–103.
[80] JAIN A K, DUIN R P W, MAO J. Statistical Pattern Recognition: A Review[J].IEEE Trans. Pattern Anal. Mach. Intell.,2000,22(1):4–37.
[81] AEBI D, PERROCHON L. Towards Improving Data Quality[C]//Proceedings ofthe International Conference on Information Systems and Management of Data.New Delhi: INSDOC Regional Centre,1993:273–281.
[82]李梢,张宁波.慢性乙型肝炎患者肝胆湿热和肝郁脾虚证的决策树诊断模型初探[J].中国中西医结合杂志,2009,29(11):993–996.
[83] Blake, C., Merz, C. UCI repository of machine learning databases.http://www.ics.uci.edu/mlearn/MLRepository.html.
[84] JOHN G H, KOHAVI R, PFLEGER K. Irrelevant Features and the Subset Selec-tion Problem[C]//Machine Learning, Proceedings of the Eleventh InternationalConference. New Brunswick, NJ, USA: Morgan Kaufmann,1994:121–129.
[85]朱晓峰.缺失值填充的若干问题研究[D].桂林市:广西师范大学,2007.
[86] WANG X, MA Y, LI X. Data mining in inconsistent data[C]//. San Jose, CA:IEEE,2010:1–5.
[87] COHAGAN C, GRZYMALA-BUSSE J W, HIPPE Z S. Mining InconsistentData with the Bagged MLEM2Rule Induction Algorithm[C]//Proceedings ofthe2010IEEE International Conference on Granular Computing. Washington,DC, USA: IEEE Computer Society,2010:115–120.
[88]汪庆,张巍.连续特征离散化方法综述[C]//第六届中国管理科学与工程论坛.中国,上海:中国管理科学与工程论坛学术委员会,2008:1091–1096.
[89] DOUGHERTY J, KOHAVI R, SAHAMI M. Supervised and UnsupervisedDiscretization of Continuous Features[C]//machine learning: Proceedings ofthe twelfth international conference. California, USA: Morgan Kaufmann,1995:194–202.
[90] FAYYAD, IRANI. Multi-Interval Discretization of Continuous-Valued At-tributes for Classification Learning[C]//Proceedings of the International Join-t Conference on Uncertainty in AI. Chambéry, France: Morgan Kaufmann,1993:1022–1027.
[91]白云静,申洪波.中医证候复杂性特征及证候研究思路探析[J].中国中医药信息杂志,2004,11(9):754–756.
[92] L M. Hybrid Intelligent Systems[M]. Boston: MA: Kluwer,1995.
[93] ABRAHAM A, NATH B. Hybrid intelligent systems Design: a review of adecade of research[R].[S.l.]: Monash University,2000.
[94] HIS, Hybrid Intelligent Systemhttp://en.wikipedia.org/wiki/Hybrid_intelligent_system.
[95]王众托.系统工程引论[M].北京:电子工业出版社,2006.
[96] http://en.wikipedia.org/wiki/System.
[97]王刚.混合智能系统及其在商务智能中的应用研究[博士论文][D].上海:复旦大学,2008.
[98] OVASKA S J, VANLANDINGHAM H F, KAMIYA A. Fusion of soft computingand hard computing in industrial applications: an overview[J]. IEEE Transac-tions on Systems, Man, and Cybernetics, Part C,2002,32:72–79.
[99] GAVRILOV A V. Hybrid Intelligent Systems in Ubiquitous Computing[J]. De-signing Solutions-Based Ubiquitous and Pervasive Computing: New Issues andTrends,2010:263–281.
[100] RAMOS E, N U′N EZ H, CASA N AS R. A Fuzzy Hybrid Intelligent System forHuman Semen Analysis[C]//Proceedings of the11th Ibero-American confer-ence on AI: Advances in Artificial Intelligence. Berlin, Heidelberg: Springer-Verlag,2008:422–431.
[101] WOLPERT D, MACREADY W G. No free lunch theorems for optimization[J].IEEE Trans. Evolutionary Computation,1997,1(1):67–82.
[102]蔡自兴V.人工智能及其应用[M].北京:清华大学出版社,2004.
[103]阮晓钢.神经计算科学――在细胞的水平上模拟脑功能[M].北京:国防工业出版社,2006.
[104]戴汝为王珏.智能系统的综合集成[M].杭州:浙江科学技术出版社,1995.
[105] L C, W L. Expert System Based on Neural Networks for TCM Diagnosis andTreatment of Hypertension[J]. Computer Engineering,1994,20(2):23–26.
[106] FEIGENBAUM E A. Expert Systems: Looking Back and Looking Ahead[C]//InProceedings of GI Jahrestagung. Reinhard Wilhelm: Springer,1980，33:1–14.
[107]袁曾任.人工神经元网络及其应用[M].北京:清华大学出版社,1999.
[108]陈兆乾,周志华.神经计算研究现状及发展趋势[R].南京:南京大学计算机软件新技术国家重点实验室,1999.
[109]钟义信,潘新安.智能理论与技术――人工智能与神经网络[J].人民邮电出版社,1992:311–316.
[110] WIDROW B, D.STEARNS S. Adaptive Signal Processing[M]. NJ: PrenticeHall: Englewood Cliffs,1985.
[111] http://baike.baidu.com/view/19743.htm.
[112]周志华.神经网络及其应用[M].北京:清华大学出版社,1999:343–365.
[113] HARRISON R. F. P L C, KENNEDY R L. Autonomously Learning Neural Net-works for Clinical Decision Support[C]//Proceedings of the International Con-ference on Neural Networks and Expert Systems in Medicine and Healthcare.United Kingdom: University of Plymouth,1994:15–22.
[114] M. J A J, A. G R J, G. R J, et al. A Combined Neural Network and DecisionTrees Model for Prognosis of Breast Cancer Replace[J]. Artificial Intelligencein Medicine,2003,27(1):45–63.
[115] HAYASHI Y, SETIONO R, YOSHIDA K. A comparison between two neural net-work rule extraction techniques for the diagnosis of hepatobiliary disorders[J].Artificial Intelligence in Medicine,2000,20(3):205–216.
[116] FURUNDZIC D, DJORDJEVIC M, BEKIC A J. Neural networks approach toearly breast cancer detection[J]. J. Syst. Archit.,1998,44(8):617–633.
[117]任艳玲,董平.多元统计分析在中医药研究中的应用与思考[J].中国中西医结合杂志,2002,22(11):860–862.
[118]丁维,蒋永光.数据挖掘及其在中医领域的应用研究[J].数理医药学杂志,2007,20(3):403–404.
[119]袁世宏,王天芳.中医证候的认知思路及其数据挖掘方法[J].中医杂志,2011,52(4):284–288.
[120] GREGORY U F, PIATETSKY-SHAPIRO, SMYTH P. Knowledge Discovery andData Mining: Towards a Unifying Framework[C]//Proceedings of the SecondInternational Conference on Knowledge Discovery and Data Mining. Portland,Oregon: AAAI Press,1996:82–88.
[121] ZHOU Z H. Three perspectives of data mining[J]. Artificial Intelligence,2003,143(1):139–146.
[122] MICHALSKI R S, BRATKO I, KUBAT M. Machine learning and data miningmethods and applications[M]. Bei Jing: Publishing House of Electronics In-dustry,2004.
[123] WANG Y, MA L, LIAO X, et al. Decision tree method to extract syn-drome differentiation rules of Posthepatitic Cirrhosis in traditional Chinesemedicine[C]//Proceedings of2008IEEE International Symposium on IT inMedicine and Education. Xiamen: Xiamen University,2008:744–748.
[124]邹蔚萌,高宏杰.决策树技术在中医证候学中应用研究思路[J].辽宁中医药大学学报,2011,13(2):126–128.
[125]周忞,褚娜.中医证候研究中的分类算法方法学研究[J].中西医结合学报,2010,8(10):911–916.
[126]王彦,马利庄.基于决策树的代偿期和失代偿期肝硬化自动诊断的方法[J].现代生物医学进展,2008,8(1):126–140.
[127]姚美村,艾路.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,2002,25(6):48–50.
[128]李慧琴.慢性乙型肝炎药物配伍及其关联性辨析[J].中医药学刊,2003,21(4):581–582.
[129] TAN Y, YIN G, LI G, et al. Mining compatitbility rules from irregular Chinesetraditional medicine database by Apriori algorithm[J]. Journal of SouthwestJiaotong University (English Edition),2007,15(4):288–293.
[130] XUEMEI Y, DUANYI L, CHANG’EN Z, et al. Classification association rulesmining for Zhongjing prescriptions[C]//Proceedings of2008IEEE InternationalSymposium on IT in Medicine and Education. Xiamen: Xiamen University,2008:768–772.
[131]张涛,徐飞.中医症状间的关联规则研究[J].杭州师范学院学报,2007,6(3):205–207.
[132]艾军,汪受传.关联规则在小儿病毒性肺炎中医病机理论研究中的应用[J].中国中医基础医学杂志,2011,17(8):857–859.
[133]李靖,王硕仁.基于关联规则的IgA肾病中医证候与病理相关性的探讨[J].北京中医药,2011,30(9):653–655.
[134]程丹丹,徐俊峰.中风病证候诊断与治法的相关性研究[J].中医中药,2007,4(5):81–83.
[135]李赛,聂莉芳.聂莉芳治疗慢性肾功能衰竭经验的关联规则分析[J].中华中医药杂志,2011,26(7):1602–1606.
[136]朱咏华.基于贝叶斯网络的中医辨证系统[J].湖南大学学报,2006,33(4):123–125.
[137] HUIYAN W. A Computerized Diagnostic Model Based on Naive BayesianClassifier in Traditional Chinese Medicine[C]//Proceedings of the2008Inter-national Conference on BioMedical Engineering and Informatics-Volume01.Washington, DC, USA: IEEE Computer Society,2008:474–477.
[138]吴荣,聂晓燕.基于贝叶斯网络的名老中医治疗冠心病辨证规律研究[J].中国中医药信息杂志,2010,17(5):98–99.
[139] LANGLEY P. Selection of Relevant Features in Machine Learning[C]//In Pro-ceedings of the AAAI Fall symposium on relevance. New Orleans: AAAI Press,1994:140–144.
[140] LANGLEY P, SAGE S. Computational learning theory and natural learning sys-tems: Volume IV[M]//. Cambridge, MA, USA: MIT Press,1997:51–63.
[141] LANGLEY P, SAGE S. Induction of Selective Bayesian Classifier-s[C]//Proceedings of the Tenth Annual Conference on Uncertainty in ArtificialIntelligence. Washington, USA: Morgan Kaufman,1994:399–406.
[142] BEYER K S, GOLDSTEIN J, RAMAKRISHNAN R, et al. When Is”NearestNeighbor” Meaningful?[C]//Proceedings of the7th International Conference onDatabase Theory. London, UK, UK: Springer-Verlag,1999:217–235.
[143] HUGHES G. On the mean accuracy of statistical pattern recognizers[C]//IEEEtransaction on information theory. New York, U.S.A: IEEE,1968:55–63.
[144] WEBER R, SCHEK H J, BLOTT S. A Quantitative Analysis andPerformance Study for Similarity-Search Methods in High-Dimensional S-paces[C]//Proceedings of the24rd International Conference on Very Large DataBases. San Francisco, CA, USA: Morgan Kaufmann Publishers Inc.,1998:194–205.
[145] QUINLAN J. C4.5: Programs for machine learning[M]. Los Altos: MorganKaufmann,1993.
[146] KEARNS M J, VAZIRANI U V. An introduction to computational learningtheory[M]. Cambridge, MA, USA: MIT Press,1994.
[147] T. HASTIE R T, FRIEDMAN J. The Elements of Statistical Learning: DataMining, Inference, and Prediction[M]. New York: Springer-Verlag,2001.
[148] NARENDRA P M, FUKUNAGA K. A Branch and Bound Algorithm for FeatureSubset Selection[J]. IEEE Trans. Comput.,1977,26(9):917–922.
[149] YU L, LIU H. Efficient Feature Selection via Analysis of Relevance and Re-dundancy[J]. J. Mach. Learn. Res.,2004,5:1205–1224.
[150] DASH M, LIU H. Feature Selection for Classification[J]. Intelligent Data Anal-ysis,1997,1:131–156.
[151] MARILL T, GREEN D. On the effectiveness of receptors in recognition system-s[J]. IEEE Transactions on Information Theory,1963,9(1):11–17.
[152] WHITNEY A W. A Direct Method of Nonparametric Measurement Selec-tion[J]. IEEE Trans. Comput.,1971,20(9):1100–1103.
[153] STEARNS S D. On selecting features for pattern classifiers.[C]//In Preceed-ings of3rd International Conference on Pattern Recognition. Coronado, CA:International Association for Pattern Recognition (IAPR),1976:71–75.
[154] PUDIL P, NOVOVI CˇOV A′J, KITTLER J. Floating search methods in featureselection[J]. Pattern Recogn. Lett.,1994,15(11):1119–1125.
[155] STRACUZZI D J. Randomized Feature Selection[M]. British: Chapman andHall/CRC,2008:41–62.
[156] BLUM A L, LANGLEY P. Selection of relevant features and examples in ma-chine learning[J]. Artif. Intell.,1997,97(1-2):245–271.
[157] GUYON I, ELISSEEFF A. An introduction to variable and feature selection[J].J. Mach. Learn. Res.,2003,3:1157–1182.
[158] M. L P. The characteristic selection problem in recognition system[J]. IRETransaction on Information Theory,1962,8:171–178.
[159] COVER T M. The best two independent measurements are not the two best[J].IEEE Trans. Syst. Man, Cybern.,1974,4(1):116–117.
[160] KOHAVI R, JOHN G H. Wrappers for feature subset selection[J]. Artif. Intell.,1997,97(1-2):273–324.
[161] LIU H, YU L. Toward Integrating Feature Selection Algorithms for Classifica-tion and Clustering[J]. IEEE Trans. on Knowl. and Data Eng.,2005,17(4):491–502.
[162]张丽新,王家钦.机器学习中的特征选择[J].计算机科学,2004,31(11):180–184.
[163]边肇祺.特征的选择与提取[M].北京:清华大学出版社,2004:176–210.
[164] KIRA K, RENDELL L A. A practical approach to feature selec-tion[C]//Proceedings of the ninth international workshop on Machine learning.San Francisco, CA, USA: Morgan Kaufmann Publishers Inc.,1992:249–256.
[165] KONONENKO I. Estimating attributes: analysis and extensions of RE-LIEF[C]//Proceedings of the European conference on machine learning onMachine Learning. Secaucus, NJ, USA: Springer-Verlag New York, Inc.,1994:171–182.
[166] FOUNTAIN T, ALMUALLIM H, DIETTERICH T G. Learning With Many Irrel-evant Features[R]. Corvallis, OR, USA: Oregon State University,1991.
[167] LIU H, SETIONO R. A Probabilistic Approach to Feature Selection-A Fil-ter Solution[C]//Proceedings of International Conference on Machine Learning(ICML-96). Bari, Italy: Morgan Kaufmann,1996:319–327.
[168] DASH M, LIU H. Consistency-based search in feature selection[J]. Artif. In-tell.,2003,151(1-2):155–176.
[169]刘华文.基于信息熵的特征选择算法研究[博士论文][D].长春:吉林大学,2010.
[170] YANG Y, PEDERSEN J O. A Comparative Study on Feature Selection in TextCategorization[C]//Proceedings of the Fourteenth International Conference onMachine Learning. San Francisco, CA, USA: Morgan Kaufmann PublishersInc.,1997:412–420.
[171] BATTITI R. Using mutual information for selecting features in supervised neu-ral net learning[J]. IEEE Transactions on Neural Networks,1994,5:537–550.
[172] HALL M. Correlation-based Feature Selection for Machine Learning[D].Hamilton, NewZealand: University of Waikato,1999.
[173]刘桥.基于最短描述长度的高维特征选择方法研究[博士论文][D].成都:信息安全系,电子科技大学.
[174]梁循.决策树算法[M].北京:北京大学出版社,2006:44–73.
[175]张小峰,张志旺.基于通信系统的决策树构造算法[J].山东大学学报(工学版),2011,41(4):79–84.
[176] KWAK N, CHOI C H. Input Feature Selection for Classification Problems[J].IEEE Trans. Neural Networks,2002,13(1):143–159.
[177] DING C, PENG H. Minimum Redundancy Feature Selection from Microar-ray Gene Expression Data[C]//Proceedings of the Second IEEE Computation-al Systems Bioinformatics. Washington, DC, USA: IEEE Computer Society,2003:523–528.
[178] ESTéVEZ P A, TESMER M, PEREZ C A, et al. Normalized mutual informationfeature selection[J]. Trans. Neur. Netw.,2009,20(2):189–201.
[179] FLEURET F. Fast Binary Feature Selection with Conditional Mutual Informa-tion[J]. J. Mach. Learn. Res.,2004,5:1531–1555.
[180] HALL M A. Correlation-based Feature Selection for Discrete and NumericClass Machine Learning[C]//Proceedings of the Seventeenth International Con-ference on Machine Learning. San Francisco, CA, USA: Morgan KaufmannPublishers Inc.,2000:359–366.
[181] YU L, LIU H. Feature selection for high-dimensional data: A fast correlation-based filter solution[C]//In Proceedings of the Twentieth International Con-ference on Machine Leaning (ICML-03). Washington, D.C.: AAAI Press,2003:856–863.
[182]姚旭,王晓丹.控制与决策,修回日期2011-07-26.
[183]曹静.基于最大相关最小冗余的特征选择算法研究[硕士论文][D].河北:生物医学工程系,电气工程学院,燕山大学.
[184] KIRA K, RENDELL L A. The feature selection problem: traditional meth-ods and a new algorithm[C]//Proceedings of the tenth national conference onArtificial intelligence. San Jose, California: AAAI Press,1992:129–134.
[185] ROBNIK-SˇIKONJA M, KONONENKO I. Theoretical and Empirical Analysis ofReliefF and RReliefF[J]. Mach. Learn.,2003,53(1-2):23–69.
[186]杨艺,韩德强.基于排序融合的特征选择[J].控制与决策,2011,26(3):397–401.
[187]吴艳文,胡学钢.基于Relief算法的特征学习聚类[J].合肥学院学报（自然科学版）,2008,18(2):45–48.
[188] THRUN S B, BALA J, BLOEDORN E, et al. The MONK’s Problems A Per-formance Comparison of Different Learning Algorithms[R]. USA: CarnegieMellon University, Tech. Rep.,1991.
[189]廖晓威.结合属性筛选的决策树分析及其在中医诊断中的应用[硕士论文][D].上海:上海交通大学.
[190]王丹芬,朱文锋.主症在中医诊断中的作用[J].甘肃中医,2003,16(7):8–10.
[191]刘雁云.中医主症证治学简述[J].中医临床研究,2010,2(19):50.
[192]李乾构.改革辨证模式――按主症与次症辨证施治[C]//中华中医药学会脾胃病分会第十八次学术交流会论文汇编.北京:中华中医药学会,2006:13–14.
[193]陈建新,赵慧辉.中医证候生物学基础研究思路初探-基于特征选择的数据挖掘方法[J].中西医结合学报,2010,8(8):747–749.
[194] ZHAO Z, LIU H. Searching for Interacting Features[C]//IJCAI2007, Pro-ceedings of the20th International Joint Conference on Artificial Intelligence.Hyderabad, India: Springer,2007:1156–1161.
[195] ZHAO Z, LIU H. Searching for interacting features in subset selection[J]. Intell.Data Anal.,2009,13(2):207–228.
[196] JAKULIN A, BRATKO I. Analyzing Attribute Dependencies[C]//KnowledgeDiscovery in Databases: PKDD2003,7th European Conference on Principlesand Practice of Knowledge Discovery in Databases. Cavtat-Dubrovnik, Croatia:Springer,2003，2838:229–240.
[197] JAKULIN A, BRATKO I. Testing the significance of attribute interaction-s[C]//Machine Learning, Proceedings of the Twenty-first International Confer-ence (ICML2004). Banff, Alberta, Canada: ACM,2004，69:52–59.
[198] BREFELD U, SCHEFFER T. Co-EM support vector learning[C]//MachineLearning, Proceedings of the Twenty-first International Conference (ICML2004). Banff, Alberta, Canada: ACM,2004，69:121–128.
[199]张晓东,凌琪华.慢性乙型肝炎肝郁脾虚证的logistic回归及判别分析[J].中国中医药信息杂志,2009,16(9):23–25.
[200]薛飞飞.基于数据挖掘的肝郁脾虚证研究[博士论文][D].北京:北京中医药大学.
[201]金实.慢乙型肝炎中医辨证分型与生化免疫指标关系的探讨[J].中医杂志,1989,30(2):13–15.
[202]高风琴,徐慧媛.慢性乙型肝炎病理诊断与中医证型关系初探[J].北京中医药,2010,29(7):525–526.
[203] SEBASTIANI F. Machine learning in automated text categorization[J]. ACMComput. Surv.,2002,34(1):1–47.
[204]唐启盛,曲淼.抑郁症中医证候的贝叶斯网络研究[J].中医杂志,2008,49(11):1013–1015.
[205] YANG X, LIANG Z, ZHANG G, et al. A classification algorithm for TCMsyndromes based on P-SVM[C]//Proceedings of International Conference onMachine Learning and cybernetics. Bonn, Germany: ACM,2005:3692–3697.
[206]徐琎,王忆勤.基于SVM的中医心系证候分类研究[J].世界科学技术-中医药现代化,2010,12(5):713–717.
[207]周正荣,宋晓峰.使用组合分类器预测蛋白质相互作用[J].电子学报,2010,38(6):1464–1467.
[208]曹美玲,张新峰.分类器融合技术在中医舌象老嫩识别中的应用研究[J].北京生物医学工程,2006,25(6):644–648.
[209]李霞,何丽云. Boosting算法及其在中医亚健康数据分类中的应用[J].中国卫生统计,2008,25(2):158–161.
[210]刘昆宏.多分类集成系统在基因微阵列数据分析中的应用[博士论文][D].安徽:中国科学技术大学.
[211]邢欣来,何中市.组合分类器辅助诊断肺栓塞的研究[J].计算机工程与应用,2009,45(12):214–217,245.
[212]孔志周.多分类器系统中信息融合方法研究[博士论文][D].长沙:中南大学.
[213]沈学华,周志华. Boosting和Bagging综述[J].计算机工程与应用,2000:31–32,40.
[214]汪云云.基于AUC的分类器评价和设计综述[J].模式识别与人工智能,2011,24(1):64–71.
[215] HANSEN L K, SALAMON P. Neural Network Ensembles[J]. IEEE Trans.Pattern Anal. Mach. Intell.,1990,12(10):993–1001.
[216] ZHOU Z H, WU J, TANG W. Ensembling neural networks: many could bebetter than all[J]. Artif. Intell.,2002,137(1-2):239–263.
[217] COOPER G F, HERSKOVITS E. A Bayesian Method for the Induction of Prob-abilistic Networks from Data[J]. Mach. Learn.,1992,9(4):309–347.
[218] BOUCKAERT R R. A stratified simulation scheme for inference in Bayesianbelief networks[C]//Proceedings of the Tenth international conference on Un-certainty in artificial intelligence. San Francisco, CA, USA: Morgan KaufmannPublishers Inc.,1994:110–117.
[219] HERSKOVITS E, COOPER G F. an entropy-driven system for construction ofprobabilistic expert systems from databases[C]//Proceedings of the Sixth Annu-al Conference on Uncertainty in Artificial Intelligence. New York, NY, USA:Elsevier Science Inc.,1991:117–128.
[220] CHENG J, BELL D A, LIU W. An Algorithm for Bayesian Belief NetworkConstruction from Data[C]//IN PROCEEDINGS OF AI&STAT’97. Laud-erdale, Florida: Society for Artificial Intelligence and Statistics,1997:83–90.
[221] PROVOST F J, DOMINGOS P. Tree Induction for Probability-Based Ranking[J].Machine Learning,2003,52(3):199–215.
[222] KOHAVI R. Scaling Up the Accuracy of Naive-Bayes Classifiers: ADecision-Tree Hybrid[C]//Proceedings of the Second International Conferenceon Knowledge Discovery and Data Mining. Portland, Oregon: AAAI Press,1996:202–207.
[223] ZHANG H, SU J. Conditional Independence Trees[C]//15th European Confer-ence on Machine Learning. Pisa, Italy: Springer,2004:513–524.
[224] SU J, ZHANG H. Learning Conditional Independence Tree for Rank-ing[C]//Proceedings of the4th IEEE International Conference on Data Mining(ICDM2004). Brighton, UK: IEEE Computer Society,2004:531–534.
[225] SU J, ZHANG H. Representing Conditional Independence Using DecisionTrees[C]//AAAI. Pennsylvania, USA: AAAI Press/The MIT Press,2005:874–879.
[226] SU J, ZHANG H. Probabilistic Inference Trees for Classification and Rank-ing[C]//Canadian Conference on AI. Canada: Springer,2006:526–537.
[227] LIANG H, YAN Y. Learning naive bayes tree for conditional probability es-timation[C]//Proceedings of the19th international conference on Advances inArtificial Intelligence: Canadian Society for Computational Studies of Intelli-gence. Berlin, Heidelberg: Springer-Verlag,2006:455–466.
[228] LIANG H, ZHANG H, YAN Y. Decision Trees for Probability Estimation: AnEmpirical Study[C]//ICTAI. Washington,DC, USA: IEEE Computer Society,2006:756–764.
[229] LIANG H, YAN Y, ZHANG H. Learning Decision Trees with log ConditionalLikelihood[J]. IJPRAI,2010,24(1):117–151.
[230] CHU N, MA L, LIU P, et al. A comparative analysis of methods for probabilityestimation tree[J]. W. Trans. on Comp.,2011,10(3):71–80.
[231] LIU B, HSU W, MA Y. Integrating Classification and Association Rule Min-ing[C]//Proceedings of the4th international conference on Knowledge Discov-ery and Data mining (KDD’98). New York, NY: AAAI Press,1998:80–86.
[232] LI W, HAN J, PEI J. CMAR: Accurate and Efficient Classification Based onMultiple Class-Association Rules[C]//ICDM. San Jose, California,USA: IEEEComputer Society,2001:369–376.
[233] YIN X, HAN J. CPAR: Classification based on Predictive AssociationRules[C]//SDM. San Francisco, CA, USA: SIAM,2003:331–335.
[234] XU X, HAN G, MIN H. Construct concise and accurate classifier by atom-ic association rules[C]//Proceedings of the Third International Conference onMachine Learning and Cybernetics. Shanghai: IEEE in Piscataway, NJ.,2004.
[235] THABTAH F A, COWLING P I. A greedy classification algorithm based onassociation rule[J]. Applied Soft Computing,2007,7(3):1102–1111.
[236]贺志.关联规则优化方法的研究[博士论文][D].北京:北京交通大学.
[237]李成军.一种改进的加权关联规则挖掘方法[J].计算机工程,2010,36(7):55–57.
[2]郭振球.中医辨证学研究的前景[J].大自然探索,1985,4(13):85–89.
[3]洪净.中医辨证的量化研究现状与展望[J].中国医药学报,2002,17(8):452–454.
[4]杨杰,牛欣.中医诊断信息数字化发展[J].中医药学刊,2006,24(5):810–812.
[5]郭振球.论中医诊断学的发展[J].安徽中医学院学报,1988,7(3):2–5.
[6]蒋依吾,陈建仲.电脑化中医舌诊系统[J].中国中西医结合杂志,2000,20(2):145–147.
[7]王忆勤.中医诊断学[M].北京:中国中医药出版社,2004.
[8]周昌乐.智能中医诊断信息处理技术研究进展与展望[J].中西医结合学报,2006,4(6):560–566.
[9]中国中医药学会内科肝胆病专业委员会.病毒性肝炎中医辨证标准(试行)[J].中医杂志,1992,33(5):39–40.
[10]中药新药临床研究指导原则(试行).病毒性肝炎中医辨证标准(试行)[J].北京:中国医药科技出版社,2002:147–149.
[11]孙占全,西广成.中医辨证的智能系统模型[J].系统仿真学报,2007,19(10):2318–2321.
[12]李宇航,靳琦.计算机模拟中医诊断的客观化研究[J].北京中医药大学学报,1999,22(4):10–12.
[13]邵红,崔文成.医疗诊断专家系统研究进展[J].小型微型计算机系统,2003,24(3):509–512.
[14]陈朝东.一个非处方性药物咨询专家系统的设计与实现[硕士学位论文][D].上海:华东师范大学计算机系,2000.
[15]莫传伟,武哲丽.中医舌诊客观化识别与图像技术的探析[J].中医药学刊,2005,23(6):1032–1034.
[16]岳小强，刘庆.中医舌象计算机识别研究的现状分析[J].中西医结合学报,2004,2(5):326–329.
[17]翁维良.中医舌诊客观化研究[J].中国工程科学,2001,3(1):78–82.
[18]许家佗,张志枫.舌象数字图像采集条件的实验观测[J].中国中医基础医学杂志,2007,13(1):23–27.
[19]王鸿谟.中医色诊学的定位定量研究[J].中国医药学报,1998,13(4):14–18.
[20]曾常春,王先菊.中医色诊研究及光子学技术在色诊中的应用[J].中国中医基础医学杂志,2004,10(9):74–76.
[21]朱咏华.中医症状的规范化研究[J].湖南中医学院学报,2002,22(3):35–37.
[22]由松.中医症状及证候的量化方法探讨[J].北京中医药大学学报,2002,25(2):13–15.
[23]魏守水,韩庚祥.基于金氏脉学的新型脉诊仪的研究[J].电子测量与仪器学报,2005,19(5):90–94.
[24]汤伟昌.三部脉象检测系统的研究[J].中国医疗器械杂志,2005,29(3):164–166.
[25]赵翠敏,杨学智.中医脉诊仪研制情况概述[J].2006国际传统医药创新与发展态势论坛论文集,2006增刊:260–262.
[26]黄碧群.基于信息融合理论的中医四诊合参研究[J].中国中医药杂志,2004,2(6):324–325.
[27] ZHENG N, WU Z. TCM-SIRD: an integrated aided system for traditional Chi-nese medicine Sizheng[C]//Proceedings of the IEEE International Conferenceon Systems, Man&Cybernetics. Netherlands: IEEE,2004:3864–3868.
[28]刘士敬.中医各系统病症脾气虚证诊断因素的多元逐步回归分析[J].甘肃中医学院学报,1996,9(3):4–7.
[29]潘毅.心系疾病心气虚证的心功能指标判别诊断[J].山东中医杂志,1997,16(4):151–152.
[30]李永健,李永健.154例原发性肝癌临床症状多元Logistic回归分析[J].中国中医基础医学杂志,2003,9(8):59–62.
[31]王磊,苏越.偏最小二乘法在肝炎后肝硬化中医证候分类建模中的应用[J].中西医结合学报,2008,6(11):1122–1128.
[32] WANG Y, MA L, LIU P. Feature selection and syndrome prediction for livercirrhosis in traditional Chinese medicine[J]. Comput. Methods Prog. Biomed.,2009,95(3):249–257.
[33] CHU N, MA L, ZHOU M. An Intelligent TCMEP Differentiation Sys-tem[C]//The8th World Congress on Intelligent Control and Automation. Jinan,Shandong: IEEE,2010:2686–2691.
[34] CHU N, LIZHUANG M, LI J, et al. Rough set based feature selection forimproved differentiation of traditional Chinese medical data[C]//Seventh Inter-national Conference on Fuzzy Systems and Knowledge Discovery, FSKD2010.Yantai, Shandong: IEEE,2010:2667–2672.
[35]王亚强,金晖.基于关联规则的中医症状组团分析[J].四川大学学报(自然科学版),2009,46(6):1650–1654.
[36]北京市科学技术志编辑委员会.1981年，中国科学院、北京第二医学院和北京中医院在中国首次研制成功“关幼波老中医诊断肝病的电子计算机中医专家系统”[J].2002.
[37] http://ziliao.hzu.edu.cn/n46198.html.
[38]吕汉兴,孙德保.中医专家系统辨证推理的决策模型[J].华中理工大学学报,1989,17(6):67–72.
[39]章浩伟,朱训生.中医证候分级推理诊断方法[J].计算机工程与应用,2005:207–209.
[40]吴芸.基于软计算方法的中医智能辨证处理系统[J].厦门理工学院学报,2008,16(2):50–55.
[41]孙佰清,潘启树.医疗诊断系统专家知识的表达与获取方法[J].哈尔滨工业大学学报,2001,33(1):134–136.
[42]李梢.从维度与阶度探讨中医证候的特征及标准化方法[J].北京中医药大学学报,2003,26(3):1–4.
[43]甘琴霞.模糊数学在中医学领域的应用进展[J].江苏中医药,2007,39(1):61–63.
[44]张琴,刘平.900例肝炎后肝硬化中医证候判别模式的研究[J].中国中西医结合杂志,2006,26(8):694–697.
[45]白云静,申洪波.基于人工神经网络的中医证候非线性建模研究[J].中国中医药信息杂志,2007,14(7):3–4,83.
[46]施明辉.人工神经网络在中医诊断中的应用现状与趋势[J].中国中医药信息杂志,2007,14(1):2–5.
[47]赵卫东,盛昭瀚.基于人工神经网络的案例推理医疗诊断[J].东南大学学报(自然科学版),2000,130(13):46－50.
[48]龚德平,高颖.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,2003,19(1):134–136.
[49]瞿海斌,王祥君.基于决策树的血瘀证诊断规则自动归纳方法[J].中国生物医学工程学报,2005,24(6):709–727.
[50] WANG H. A Novel Method for Quantitative Diagnosis Based on Decision Treein Traditional Chinese Medicine[C]//Proceedings of the Eighth InternationalConference on Machine Learning and Cybernetics. Baoding, Hebei: IEEE,2009:344–349.
[51]秦中广,毛宗源.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.
[52]张承江,闫朝升.中医肾病治疗信息中关联规则的挖掘算法[J].黑龙江大学自然科学学报,2005,22(6):842–845.
[53] BO W, MING-WEI Z, BIN Z, et al. Data Mining Application to SyndromeDifferentiation in Traditional Chinese Medicine[C]//Proceedings of the SeventhInternational Conference on Parallel and Distributed Computing, Applicationsand Technologies. Washington, DC, USA: IEEE Computer Society,2006:128–131.
[54] YAN J F, ZHAN Y, ZHU W F. Application of Support Vector Machine inTCM Diagnosis[C]//Proceedings of the2009WRI Global Congress on Intelli-gent Systems-Volume01. Washington, DC, USA: IEEE Computer Society,2009:338–342.
[55]罗丛波.基于模型诊断的应用[J].科技情报开发与经济,2007,17(3):152–153.
[56]李占山.基于模型诊断推理的回顾与展望[J].计算机科学,1998,25(6):54–58.
[57]操龙兵.开放复杂智能系统――基础、概念、分析、设计与实施[M].北京:人民邮电出版社,2008.
[58]贵忠华.智能混合系统研究综述[J].信息与控制,2000,29(1):59–64.
[59]王长琼.基于混合智能的故障诊断与维修决策模型研究与实践[博士论文][D].武汉,北京:武汉交通科技大学.
[60] LI S, DUAN Y, KINMAN R, et al. A framework for a hybrid intelligent systemin support of marketing strategy development[J]. Marketing Intelligence andPlanning,1999,17(4):209–216.
[61]程国建,张喜锋.混合智能系统在测井储层识别中的应用[J].电子技术应用,2007,10:128–130.
[62] FUNG R Y K, POPPLEWELL K, XIE J. An intelligent hybrid system for cus-tomer requirements analysis and product attribute targets determination[J]. In-ternational Journal of Production Research,1998,36(1):13–34.
[63] MORI H, TAKAHASHI A. Hybrid intelligent system for daily maximum tem-perature forecasting in smart grids[C]//International Symposium on Circuitsand Systems (ISCAS2011). Rio de Janeiro, Brazil: IEEE,2011:1852–1855.
[64] CORTES C, VAPNIK V. Support-Vector Networks[J]. Mach. Learn.,1995,20(3):273–297.
[65] BENNETT K P. Advances in kernel methods[M]//. Cambridge, MA, USA: MITPress,1999:307–326.
[66] BENNETT K P, CAMPBELL C. Support vector machines: hype or hallelu-jah?[J]. SIGKDD Explor. Newsl.,2000,2(2):1–13.
[67]赵恒平.混合智能系统及其在软测量建模中的应用[博士论文][D].上海:华东理工大学.
[68]王刚,黄丽华.混合智能系统研究综述[J].系统工程学报,2010,25(4):569–578.
[69] MEESAD P, YEN G G. A Hybrid Intelligent System for Medical Diag-nosis[C]//Proceedings of International Joint Conference on Neural Networks.Washington D.C., U.S.A.: IEEE,2001:2558–2563.
[70] SEHGAL M S B, GONDAL I, DOOLEY L. Support Vector Machine and Gen-eralized Regression Neural Network Based Classification Fusion Models forCancer Diagnosis[C]//Proceedings of the Fourth International Conference onHybrid Intelligent Systems. Washington, DC, USA: IEEE Computer Society,2004:49–54.
[71] REDDY N P, ROTHSCHILD B M. Hybrid fuzzy logic committee neural net-works for classification in medical decision support systems[C]//Proceedingsof the Second Joint EMBS/BMES Conference. Houston, Texas, USA: IEEEComputer Society,2002:30–31.
[72] ALAHAKONE A, SENANAYAKE S. Hybrid fuzzy logic committee neural net-works for classification in medical decision support systems[C]//IEEE Confer-ence on Multisensor Fusion and Integration for Intelligent Systems (MFI). SaltLake City, Utah, USA: IEEE Computer Society,2010:38–43.
[73] NEGOITA M G, NEAGU D, PALADE V. New Trends of Developing HybridIntelligent Systems–AIS Hybridization and DNA-Hybridization[J]. Compu-tational Intelligence Studies in Fuzziness and Soft Computing,2005,174:151–161.
[74] TSAKONAS A, TSILIGIANNI T, DOUNIAS G. Evolutionary Neural Logic Net-works in Splice-junction Gene Sequences Classification[J]. International Jour-nal on Artificial Intelligence Tools,2006,15:287–308.
[75] KALRA G, PENG Y, GUO M, et al. A hybrid intelligent system for formula-tion of BCS Class II drugs in hard gelatin capsules[C]//Proceedings of the9thInternational Conference on Neural Information Processing. Singapore: IEEEService Center,2002，4:1987–1991.
[76] WANG M, GENG Z, WANG M, et al. Combination of network con-struction and cluster analysis and its application to traditional chinesemedicine[C]//Proceedings of the Third international conference on Advancesin Neural Networks-Volume Part III. Berlin, Heidelberg: Springer-Verlag,2006:777–785.
[77]王彦.中医证候信息的数据挖掘[博士论文][D].上海:上海交通大学.
[78] COVER T, VANCAMPENHOUT J. On the possible orderings in the measurementselection problem[J]. IEEE Transactions on System,1977,7(9):657–661.
[79] BIESIADA J, DUCH W. Feature selection for high-dimensional data: aKolmogorov-Smirnov correlation-based filter[J]. Computer Recognition Sys-tems,2005,30:95–103.
[80] JAIN A K, DUIN R P W, MAO J. Statistical Pattern Recognition: A Review[J].IEEE Trans. Pattern Anal. Mach. Intell.,2000,22(1):4–37.
[81] AEBI D, PERROCHON L. Towards Improving Data Quality[C]//Proceedings ofthe International Conference on Information Systems and Management of Data.New Delhi: INSDOC Regional Centre,1993:273–281.
[82]李梢,张宁波.慢性乙型肝炎患者肝胆湿热和肝郁脾虚证的决策树诊断模型初探[J].中国中西医结合杂志,2009,29(11):993–996.
[83] Blake, C., Merz, C. UCI repository of machine learning databases.http://www.ics.uci.edu/mlearn/MLRepository.html.
[84] JOHN G H, KOHAVI R, PFLEGER K. Irrelevant Features and the Subset Selec-tion Problem[C]//Machine Learning, Proceedings of the Eleventh InternationalConference. New Brunswick, NJ, USA: Morgan Kaufmann,1994:121–129.
[85]朱晓峰.缺失值填充的若干问题研究[D].桂林市:广西师范大学,2007.
[86] WANG X, MA Y, LI X. Data mining in inconsistent data[C]//. San Jose, CA:IEEE,2010:1–5.
[87] COHAGAN C, GRZYMALA-BUSSE J W, HIPPE Z S. Mining InconsistentData with the Bagged MLEM2Rule Induction Algorithm[C]//Proceedings ofthe2010IEEE International Conference on Granular Computing. Washington,DC, USA: IEEE Computer Society,2010:115–120.
[88]汪庆,张巍.连续特征离散化方法综述[C]//第六届中国管理科学与工程论坛.中国,上海:中国管理科学与工程论坛学术委员会,2008:1091–1096.
[89] DOUGHERTY J, KOHAVI R, SAHAMI M. Supervised and UnsupervisedDiscretization of Continuous Features[C]//machine learning: Proceedings ofthe twelfth international conference. California, USA: Morgan Kaufmann,1995:194–202.
[90] FAYYAD, IRANI. Multi-Interval Discretization of Continuous-Valued At-tributes for Classification Learning[C]//Proceedings of the International Join-t Conference on Uncertainty in AI. Chambéry, France: Morgan Kaufmann,1993:1022–1027.
[91]白云静,申洪波.中医证候复杂性特征及证候研究思路探析[J].中国中医药信息杂志,2004,11(9):754–756.
[92] L M. Hybrid Intelligent Systems[M]. Boston: MA: Kluwer,1995.
[93] ABRAHAM A, NATH B. Hybrid intelligent systems Design: a review of adecade of research[R].[S.l.]: Monash University,2000.
[94] HIS, Hybrid Intelligent Systemhttp://en.wikipedia.org/wiki/Hybrid_intelligent_system.
[95]王众托.系统工程引论[M].北京:电子工业出版社,2006.
[96] http://en.wikipedia.org/wiki/System.
[97]王刚.混合智能系统及其在商务智能中的应用研究[博士论文][D].上海:复旦大学,2008.
[98] OVASKA S J, VANLANDINGHAM H F, KAMIYA A. Fusion of soft computingand hard computing in industrial applications: an overview[J]. IEEE Transac-tions on Systems, Man, and Cybernetics, Part C,2002,32:72–79.
[99] GAVRILOV A V. Hybrid Intelligent Systems in Ubiquitous Computing[J]. De-signing Solutions-Based Ubiquitous and Pervasive Computing: New Issues andTrends,2010:263–281.
[100] RAMOS E, N U′N EZ H, CASA N AS R. A Fuzzy Hybrid Intelligent System forHuman Semen Analysis[C]//Proceedings of the11th Ibero-American confer-ence on AI: Advances in Artificial Intelligence. Berlin, Heidelberg: Springer-Verlag,2008:422–431.
[101] WOLPERT D, MACREADY W G. No free lunch theorems for optimization[J].IEEE Trans. Evolutionary Computation,1997,1(1):67–82.
[102]蔡自兴V.人工智能及其应用[M].北京:清华大学出版社,2004.
[103]阮晓钢.神经计算科学――在细胞的水平上模拟脑功能[M].北京:国防工业出版社,2006.
[104]戴汝为王珏.智能系统的综合集成[M].杭州:浙江科学技术出版社,1995.
[105] L C, W L. Expert System Based on Neural Networks for TCM Diagnosis andTreatment of Hypertension[J]. Computer Engineering,1994,20(2):23–26.
[106] FEIGENBAUM E A. Expert Systems: Looking Back and Looking Ahead[C]//InProceedings of GI Jahrestagung. Reinhard Wilhelm: Springer,1980，33:1–14.
[107]袁曾任.人工神经元网络及其应用[M].北京:清华大学出版社,1999.
[108]陈兆乾,周志华.神经计算研究现状及发展趋势[R].南京:南京大学计算机软件新技术国家重点实验室,1999.
[109]钟义信,潘新安.智能理论与技术――人工智能与神经网络[J].人民邮电出版社,1992:311–316.
[110] WIDROW B, D.STEARNS S. Adaptive Signal Processing[M]. NJ: PrenticeHall: Englewood Cliffs,1985.
[111] http://baike.baidu.com/view/19743.htm.
[112]周志华.神经网络及其应用[M].北京:清华大学出版社,1999:343–365.
[113] HARRISON R. F. P L C, KENNEDY R L. Autonomously Learning Neural Net-works for Clinical Decision Support[C]//Proceedings of the International Con-ference on Neural Networks and Expert Systems in Medicine and Healthcare.United Kingdom: University of Plymouth,1994:15–22.
[114] M. J A J, A. G R J, G. R J, et al. A Combined Neural Network and DecisionTrees Model for Prognosis of Breast Cancer Replace[J]. Artificial Intelligencein Medicine,2003,27(1):45–63.
[115] HAYASHI Y, SETIONO R, YOSHIDA K. A comparison between two neural net-work rule extraction techniques for the diagnosis of hepatobiliary disorders[J].Artificial Intelligence in Medicine,2000,20(3):205–216.
[116] FURUNDZIC D, DJORDJEVIC M, BEKIC A J. Neural networks approach toearly breast cancer detection[J]. J. Syst. Archit.,1998,44(8):617–633.
[117]任艳玲,董平.多元统计分析在中医药研究中的应用与思考[J].中国中西医结合杂志,2002,22(11):860–862.
[118]丁维,蒋永光.数据挖掘及其在中医领域的应用研究[J].数理医药学杂志,2007,20(3):403–404.
[119]袁世宏,王天芳.中医证候的认知思路及其数据挖掘方法[J].中医杂志,2011,52(4):284–288.
[120] GREGORY U F, PIATETSKY-SHAPIRO, SMYTH P. Knowledge Discovery andData Mining: Towards a Unifying Framework[C]//Proceedings of the SecondInternational Conference on Knowledge Discovery and Data Mining. Portland,Oregon: AAAI Press,1996:82–88.
[121] ZHOU Z H. Three perspectives of data mining[J]. Artificial Intelligence,2003,143(1):139–146.
[122] MICHALSKI R S, BRATKO I, KUBAT M. Machine learning and data miningmethods and applications[M]. Bei Jing: Publishing House of Electronics In-dustry,2004.
[123] WANG Y, MA L, LIAO X, et al. Decision tree method to extract syn-drome differentiation rules of Posthepatitic Cirrhosis in traditional Chinesemedicine[C]//Proceedings of2008IEEE International Symposium on IT inMedicine and Education. Xiamen: Xiamen University,2008:744–748.
[124]邹蔚萌,高宏杰.决策树技术在中医证候学中应用研究思路[J].辽宁中医药大学学报,2011,13(2):126–128.
[125]周忞,褚娜.中医证候研究中的分类算法方法学研究[J].中西医结合学报,2010,8(10):911–916.
[126]王彦,马利庄.基于决策树的代偿期和失代偿期肝硬化自动诊断的方法[J].现代生物医学进展,2008,8(1):126–140.
[127]姚美村,艾路.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,2002,25(6):48–50.
[128]李慧琴.慢性乙型肝炎药物配伍及其关联性辨析[J].中医药学刊,2003,21(4):581–582.
[129] TAN Y, YIN G, LI G, et al. Mining compatitbility rules from irregular Chinesetraditional medicine database by Apriori algorithm[J]. Journal of SouthwestJiaotong University (English Edition),2007,15(4):288–293.
[130] XUEMEI Y, DUANYI L, CHANG’EN Z, et al. Classification association rulesmining for Zhongjing prescriptions[C]//Proceedings of2008IEEE InternationalSymposium on IT in Medicine and Education. Xiamen: Xiamen University,2008:768–772.
[131]张涛,徐飞.中医症状间的关联规则研究[J].杭州师范学院学报,2007,6(3):205–207.
[132]艾军,汪受传.关联规则在小儿病毒性肺炎中医病机理论研究中的应用[J].中国中医基础医学杂志,2011,17(8):857–859.
[133]李靖,王硕仁.基于关联规则的IgA肾病中医证候与病理相关性的探讨[J].北京中医药,2011,30(9):653–655.
[134]程丹丹,徐俊峰.中风病证候诊断与治法的相关性研究[J].中医中药,2007,4(5):81–83.
[135]李赛,聂莉芳.聂莉芳治疗慢性肾功能衰竭经验的关联规则分析[J].中华中医药杂志,2011,26(7):1602–1606.
[136]朱咏华.基于贝叶斯网络的中医辨证系统[J].湖南大学学报,2006,33(4):123–125.
[137] HUIYAN W. A Computerized Diagnostic Model Based on Naive BayesianClassifier in Traditional Chinese Medicine[C]//Proceedings of the2008Inter-national Conference on BioMedical Engineering and Informatics-Volume01.Washington, DC, USA: IEEE Computer Society,2008:474–477.
[138]吴荣,聂晓燕.基于贝叶斯网络的名老中医治疗冠心病辨证规律研究[J].中国中医药信息杂志,2010,17(5):98–99.
[139] LANGLEY P. Selection of Relevant Features in Machine Learning[C]//In Pro-ceedings of the AAAI Fall symposium on relevance. New Orleans: AAAI Press,1994:140–144.
[140] LANGLEY P, SAGE S. Computational learning theory and natural learning sys-tems: Volume IV[M]//. Cambridge, MA, USA: MIT Press,1997:51–63.
[141] LANGLEY P, SAGE S. Induction of Selective Bayesian Classifier-s[C]//Proceedings of the Tenth Annual Conference on Uncertainty in ArtificialIntelligence. Washington, USA: Morgan Kaufman,1994:399–406.
[142] BEYER K S, GOLDSTEIN J, RAMAKRISHNAN R, et al. When Is”NearestNeighbor” Meaningful?[C]//Proceedings of the7th International Conference onDatabase Theory. London, UK, UK: Springer-Verlag,1999:217–235.
[143] HUGHES G. On the mean accuracy of statistical pattern recognizers[C]//IEEEtransaction on information theory. New York, U.S.A: IEEE,1968:55–63.
[144] WEBER R, SCHEK H J, BLOTT S. A Quantitative Analysis andPerformance Study for Similarity-Search Methods in High-Dimensional S-paces[C]//Proceedings of the24rd International Conference on Very Large DataBases. San Francisco, CA, USA: Morgan Kaufmann Publishers Inc.,1998:194–205.
[145] QUINLAN J. C4.5: Programs for machine learning[M]. Los Altos: MorganKaufmann,1993.
[146] KEARNS M J, VAZIRANI U V. An introduction to computational learningtheory[M]. Cambridge, MA, USA: MIT Press,1994.
[147] T. HASTIE R T, FRIEDMAN J. The Elements of Statistical Learning: DataMining, Inference, and Prediction[M]. New York: Springer-Verlag,2001.
[148] NARENDRA P M, FUKUNAGA K. A Branch and Bound Algorithm for FeatureSubset Selection[J]. IEEE Trans. Comput.,1977,26(9):917–922.
[149] YU L, LIU H. Efficient Feature Selection via Analysis of Relevance and Re-dundancy[J]. J. Mach. Learn. Res.,2004,5:1205–1224.
[150] DASH M, LIU H. Feature Selection for Classification[J]. Intelligent Data Anal-ysis,1997,1:131–156.
[151] MARILL T, GREEN D. On the effectiveness of receptors in recognition system-s[J]. IEEE Transactions on Information Theory,1963,9(1):11–17.
[152] WHITNEY A W. A Direct Method of Nonparametric Measurement Selec-tion[J]. IEEE Trans. Comput.,1971,20(9):1100–1103.
[153] STEARNS S D. On selecting features for pattern classifiers.[C]//In Preceed-ings of3rd International Conference on Pattern Recognition. Coronado, CA:International Association for Pattern Recognition (IAPR),1976:71–75.
[154] PUDIL P, NOVOVI CˇOV A′J, KITTLER J. Floating search methods in featureselection[J]. Pattern Recogn. Lett.,1994,15(11):1119–1125.
[155] STRACUZZI D J. Randomized Feature Selection[M]. British: Chapman andHall/CRC,2008:41–62.
[156] BLUM A L, LANGLEY P. Selection of relevant features and examples in ma-chine learning[J]. Artif. Intell.,1997,97(1-2):245–271.
[157] GUYON I, ELISSEEFF A. An introduction to variable and feature selection[J].J. Mach. Learn. Res.,2003,3:1157–1182.
[158] M. L P. The characteristic selection problem in recognition system[J]. IRETransaction on Information Theory,1962,8:171–178.
[159] COVER T M. The best two independent measurements are not the two best[J].IEEE Trans. Syst. Man, Cybern.,1974,4(1):116–117.
[160] KOHAVI R, JOHN G H. Wrappers for feature subset selection[J]. Artif. Intell.,1997,97(1-2):273–324.
[161] LIU H, YU L. Toward Integrating Feature Selection Algorithms for Classifica-tion and Clustering[J]. IEEE Trans. on Knowl. and Data Eng.,2005,17(4):491–502.
[162]张丽新,王家钦.机器学习中的特征选择[J].计算机科学,2004,31(11):180–184.
[163]边肇祺.特征的选择与提取[M].北京:清华大学出版社,2004:176–210.
[164] KIRA K, RENDELL L A. A practical approach to feature selec-tion[C]//Proceedings of the ninth international workshop on Machine learning.San Francisco, CA, USA: Morgan Kaufmann Publishers Inc.,1992:249–256.
[165] KONONENKO I. Estimating attributes: analysis and extensions of RE-LIEF[C]//Proceedings of the European conference on machine learning onMachine Learning. Secaucus, NJ, USA: Springer-Verlag New York, Inc.,1994:171–182.
[166] FOUNTAIN T, ALMUALLIM H, DIETTERICH T G. Learning With Many Irrel-evant Features[R]. Corvallis, OR, USA: Oregon State University,1991.
[167] LIU H, SETIONO R. A Probabilistic Approach to Feature Selection-A Fil-ter Solution[C]//Proceedings of International Conference on Machine Learning(ICML-96). Bari, Italy: Morgan Kaufmann,1996:319–327.
[168] DASH M, LIU H. Consistency-based search in feature selection[J]. Artif. In-tell.,2003,151(1-2):155–176.
[169]刘华文.基于信息熵的特征选择算法研究[博士论文][D].长春:吉林大学,2010.
[170] YANG Y, PEDERSEN J O. A Comparative Study on Feature Selection in TextCategorization[C]//Proceedings of the Fourteenth International Conference onMachine Learning. San Francisco, CA, USA: Morgan Kaufmann PublishersInc.,1997:412–420.
[171] BATTITI R. Using mutual information for selecting features in supervised neu-ral net learning[J]. IEEE Transactions on Neural Networks,1994,5:537–550.
[172] HALL M. Correlation-based Feature Selection for Machine Learning[D].Hamilton, NewZealand: University of Waikato,1999.
[173]刘桥.基于最短描述长度的高维特征选择方法研究[博士论文][D].成都:信息安全系,电子科技大学.
[174]梁循.决策树算法[M].北京:北京大学出版社,2006:44–73.
[175]张小峰,张志旺.基于通信系统的决策树构造算法[J].山东大学学报(工学版),2011,41(4):79–84.
[176] KWAK N, CHOI C H. Input Feature Selection for Classification Problems[J].IEEE Trans. Neural Networks,2002,13(1):143–159.
[177] DING C, PENG H. Minimum Redundancy Feature Selection from Microar-ray Gene Expression Data[C]//Proceedings of the Second IEEE Computation-al Systems Bioinformatics. Washington, DC, USA: IEEE Computer Society,2003:523–528.
[178] ESTéVEZ P A, TESMER M, PEREZ C A, et al. Normalized mutual informationfeature selection[J]. Trans. Neur. Netw.,2009,20(2):189–201.
[179] FLEURET F. Fast Binary Feature Selection with Conditional Mutual Informa-tion[J]. J. Mach. Learn. Res.,2004,5:1531–1555.
[180] HALL M A. Correlation-based Feature Selection for Discrete and NumericClass Machine Learning[C]//Proceedings of the Seventeenth International Con-ference on Machine Learning. San Francisco, CA, USA: Morgan KaufmannPublishers Inc.,2000:359–366.
[181] YU L, LIU H. Feature selection for high-dimensional data: A fast correlation-based filter solution[C]//In Proceedings of the Twentieth International Con-ference on Machine Leaning (ICML-03). Washington, D.C.: AAAI Press,2003:856–863.
[182]姚旭,王晓丹.控制与决策,修回日期2011-07-26.
[183]曹静.基于最大相关最小冗余的特征选择算法研究[硕士论文][D].河北:生物医学工程系,电气工程学院,燕山大学.
[184] KIRA K, RENDELL L A. The feature selection problem: traditional meth-ods and a new algorithm[C]//Proceedings of the tenth national conference onArtificial intelligence. San Jose, California: AAAI Press,1992:129–134.
[185] ROBNIK-SˇIKONJA M, KONONENKO I. Theoretical and Empirical Analysis ofReliefF and RReliefF[J]. Mach. Learn.,2003,53(1-2):23–69.
[186]杨艺,韩德强.基于排序融合的特征选择[J].控制与决策,2011,26(3):397–401.
[187]吴艳文,胡学钢.基于Relief算法的特征学习聚类[J].合肥学院学报（自然科学版）,2008,18(2):45–48.
[188] THRUN S B, BALA J, BLOEDORN E, et al. The MONK’s Problems A Per-formance Comparison of Different Learning Algorithms[R]. USA: CarnegieMellon University, Tech. Rep.,1991.
[189]廖晓威.结合属性筛选的决策树分析及其在中医诊断中的应用[硕士论文][D].上海:上海交通大学.
[190]王丹芬,朱文锋.主症在中医诊断中的作用[J].甘肃中医,2003,16(7):8–10.
[191]刘雁云.中医主症证治学简述[J].中医临床研究,2010,2(19):50.
[192]李乾构.改革辨证模式――按主症与次症辨证施治[C]//中华中医药学会脾胃病分会第十八次学术交流会论文汇编.北京:中华中医药学会,2006:13–14.
[193]陈建新,赵慧辉.中医证候生物学基础研究思路初探-基于特征选择的数据挖掘方法[J].中西医结合学报,2010,8(8):747–749.
[194] ZHAO Z, LIU H. Searching for Interacting Features[C]//IJCAI2007, Pro-ceedings of the20th International Joint Conference on Artificial Intelligence.Hyderabad, India: Springer,2007:1156–1161.
[195] ZHAO Z, LIU H. Searching for interacting features in subset selection[J]. Intell.Data Anal.,2009,13(2):207–228.
[196] JAKULIN A, BRATKO I. Analyzing Attribute Dependencies[C]//KnowledgeDiscovery in Databases: PKDD2003,7th European Conference on Principlesand Practice of Knowledge Discovery in Databases. Cavtat-Dubrovnik, Croatia:Springer,2003，2838:229–240.
[197] JAKULIN A, BRATKO I. Testing the significance of attribute interaction-s[C]//Machine Learning, Proceedings of the Twenty-first International Confer-ence (ICML2004). Banff, Alberta, Canada: ACM,2004，69:52–59.
[198] BREFELD U, SCHEFFER T. Co-EM support vector learning[C]//MachineLearning, Proceedings of the Twenty-first International Conference (ICML2004). Banff, Alberta, Canada: ACM,2004，69:121–128.
[199]张晓东,凌琪华.慢性乙型肝炎肝郁脾虚证的logistic回归及判别分析[J].中国中医药信息杂志,2009,16(9):23–25.
[200]薛飞飞.基于数据挖掘的肝郁脾虚证研究[博士论文][D].北京:北京中医药大学.
[201]金实.慢乙型肝炎中医辨证分型与生化免疫指标关系的探讨[J].中医杂志,1989,30(2):13–15.
[202]高风琴,徐慧媛.慢性乙型肝炎病理诊断与中医证型关系初探[J].北京中医药,2010,29(7):525–526.
[203] SEBASTIANI F. Machine learning in automated text categorization[J]. ACMComput. Surv.,2002,34(1):1–47.
[204]唐启盛,曲淼.抑郁症中医证候的贝叶斯网络研究[J].中医杂志,2008,49(11):1013–1015.
[205] YANG X, LIANG Z, ZHANG G, et al. A classification algorithm for TCMsyndromes based on P-SVM[C]//Proceedings of International Conference onMachine Learning and cybernetics. Bonn, Germany: ACM,2005:3692–3697.
[206]徐琎,王忆勤.基于SVM的中医心系证候分类研究[J].世界科学技术-中医药现代化,2010,12(5):713–717.
[207]周正荣,宋晓峰.使用组合分类器预测蛋白质相互作用[J].电子学报,2010,38(6):1464–1467.
[208]曹美玲,张新峰.分类器融合技术在中医舌象老嫩识别中的应用研究[J].北京生物医学工程,2006,25(6):644–648.
[209]李霞,何丽云. Boosting算法及其在中医亚健康数据分类中的应用[J].中国卫生统计,2008,25(2):158–161.
[210]刘昆宏.多分类集成系统在基因微阵列数据分析中的应用[博士论文][D].安徽:中国科学技术大学.
[211]邢欣来,何中市.组合分类器辅助诊断肺栓塞的研究[J].计算机工程与应用,2009,45(12):214–217,245.
[212]孔志周.多分类器系统中信息融合方法研究[博士论文][D].长沙:中南大学.
[213]沈学华,周志华. Boosting和Bagging综述[J].计算机工程与应用,2000:31–32,40.
[214]汪云云.基于AUC的分类器评价和设计综述[J].模式识别与人工智能,2011,24(1):64–71.
[215] HANSEN L K, SALAMON P. Neural Network Ensembles[J]. IEEE Trans.Pattern Anal. Mach. Intell.,1990,12(10):993–1001.
[216] ZHOU Z H, WU J, TANG W. Ensembling neural networks: many could bebetter than all[J]. Artif. Intell.,2002,137(1-2):239–263.
[217] COOPER G F, HERSKOVITS E. A Bayesian Method for the Induction of Prob-abilistic Networks from Data[J]. Mach. Learn.,1992,9(4):309–347.
[218] BOUCKAERT R R. A stratified simulation scheme for inference in Bayesianbelief networks[C]//Proceedings of the Tenth international conference on Un-certainty in artificial intelligence. San Francisco, CA, USA: Morgan KaufmannPublishers Inc.,1994:110–117.
[219] HERSKOVITS E, COOPER G F. an entropy-driven system for construction ofprobabilistic expert systems from databases[C]//Proceedings of the Sixth Annu-al Conference on Uncertainty in Artificial Intelligence. New York, NY, USA:Elsevier Science Inc.,1991:117–128.
[220] CHENG J, BELL D A, LIU W. An Algorithm for Bayesian Belief NetworkConstruction from Data[C]//IN PROCEEDINGS OF AI&STAT’97. Laud-erdale, Florida: Society for Artificial Intelligence and Statistics,1997:83–90.
[221] PROVOST F J, DOMINGOS P. Tree Induction for Probability-Based Ranking[J].Machine Learning,2003,52(3):199–215.
[222] KOHAVI R. Scaling Up the Accuracy of Naive-Bayes Classifiers: ADecision-Tree Hybrid[C]//Proceedings of the Second International Conferenceon Knowledge Discovery and Data Mining. Portland, Oregon: AAAI Press,1996:202–207.
[223] ZHANG H, SU J. Conditional Independence Trees[C]//15th European Confer-ence on Machine Learning. Pisa, Italy: Springer,2004:513–524.
[224] SU J, ZHANG H. Learning Conditional Independence Tree for Rank-ing[C]//Proceedings of the4th IEEE International Conference on Data Mining(ICDM2004). Brighton, UK: IEEE Computer Society,2004:531–534.
[225] SU J, ZHANG H. Representing Conditional Independence Using DecisionTrees[C]//AAAI. Pennsylvania, USA: AAAI Press/The MIT Press,2005:874–879.
[226] SU J, ZHANG H. Probabilistic Inference Trees for Classification and Rank-ing[C]//Canadian Conference on AI. Canada: Springer,2006:526–537.
[227] LIANG H, YAN Y. Learning naive bayes tree for conditional probability es-timation[C]//Proceedings of the19th international conference on Advances inArtificial Intelligence: Canadian Society for Computational Studies of Intelli-gence. Berlin, Heidelberg: Springer-Verlag,2006:455–466.
[228] LIANG H, ZHANG H, YAN Y. Decision Trees for Probability Estimation: AnEmpirical Study[C]//ICTAI. Washington,DC, USA: IEEE Computer Society,2006:756–764.
[229] LIANG H, YAN Y, ZHANG H. Learning Decision Trees with log ConditionalLikelihood[J]. IJPRAI,2010,24(1):117–151.
[230] CHU N, MA L, LIU P, et al. A comparative analysis of methods for probabilityestimation tree[J]. W. Trans. on Comp.,2011,10(3):71–80.
[231] LIU B, HSU W, MA Y. Integrating Classification and Association Rule Min-ing[C]//Proceedings of the4th international conference on Knowledge Discov-ery and Data mining (KDD’98). New York, NY: AAAI Press,1998:80–86.
[232] LI W, HAN J, PEI J. CMAR: Accurate and Efficient Classification Based onMultiple Class-Association Rules[C]//ICDM. San Jose, California,USA: IEEEComputer Society,2001:369–376.
[233] YIN X, HAN J. CPAR: Classification based on Predictive AssociationRules[C]//SDM. San Francisco, CA, USA: SIAM,2003:331–335.
[234] XU X, HAN G, MIN H. Construct concise and accurate classifier by atom-ic association rules[C]//Proceedings of the Third International Conference onMachine Learning and Cybernetics. Shanghai: IEEE in Piscataway, NJ.,2004.
[235] THABTAH F A, COWLING P I. A greedy classification algorithm based onassociation rule[J]. Applied Soft Computing,2007,7(3):1102–1111.
[236]贺志.关联规则优化方法的研究[博士论文][D].北京:北京交通大学.
[237]李成军.一种改进的加权关联规则挖掘方法[J].计算机工程,2010,36(7):55–57.