信息瓶颈方法的特征权重研究
|
摘要
信息瓶颈(Information Bottleneck, IB)方法是起源于信息论的数据分析方法。IB方法采用联合概率模型表示数据,以互信息为度量手段,拥有着很好的样本和样本属性相关性的表达能力。该方法在文本聚类、图像聚类、图像语义标注、语音识别、软件聚类和协同聚类等各种数据分析领域取得了丰硕的成果。但是与向量空间模型相比,联合概率模型缺乏样本属性重要度的表达能力,这使得现有的IB方法研究中,大都忽略了属性重要度(属性权重)这个因素,从而影响了IB方法的数据分析效果。因此,IB方法的特征权重研究的日的就是在IB方法上引入属性权重计算方法及赋权机制,从而达到突出重要属性、抑制冗余属性,提高IB方法的数据分析性能的目的。
本义首先提出了从向量空间模型到加权联合概率模型的构造过程,而后系统性分析并提出了三种可行的加权方法：综合赋权IB方法、自学习权重机制和非共现数据加权二元化转化方法。实验表明,这三种方法是可行的和有效的,能够提高IB算法性能。同时,提出了互信息增益权重评价方式,在不影响聚类质量的前提下,有效降低了IB算法的运行时间。本文成果对进一步研究IB方法,提高IB方法的性能有一定意义,同时也为构造特征赋权的IB数据分析工具奠定了一定的基础。
本文的主要工作包括：
1、深入分析了联合概率模型与向量空间模型表达能力的相同性和差异性,提出了IB方法中从向量空间模型到加权联合概率模型的构造过程。加权联合概率模型结合了向量空间模型和联合概率模型的优点,既能较好的表达出样本属性和样本的相关性,也能较好的表达出样本属性的重要度。
2、为了将多属性决策中的综合赋权应用到IB方法中,提出了相对熵综合赋权IB方法。指出在综合赋权中无需区分主观赋权和客观赋权,并选择了相对熵方法以降低组合权重计算时间。同时,给出了一种基于三种代表性的客观权重方案(熵值法、均方差法和互信息法)的组合权重集选取方法,构建了相对熵综合赋权CWRE-sIB算法。实验表明,CWRE-sIB算法优于sIB算法和一系列单一权重赋权sIB算法。
3、为了消除主观因素的影响,提出了IB方法上的自学习权重机制。在IB聚类过程中调整各个属性的权重,以得到最优赋权数据表示。聚类迭代中,根据权重对最终聚类结果的影响确定权重调整的方向及量值。实验表明,自学习权重是一种客观有效的权重计算方法,FWA_CDsIB算法优于CD-sIB算法。
4、为了降低权重评价的时间消耗,提出了互信息增益权重评价方法。传统的权重评价方法依赖于聚类的评价结果,是一个有效、可行、但却十分耗时的任务。互信息增益评价方式可以在不影响聚类质量的前提下,有效降低算法运行时间。本文中给出了两种典型案例：1)线性组合综合权重案例。对互信息增益评价出的最佳25%个加权数据聚类后,得到最优/次优结果的概率为100%。与此同时,节约了76.04%的运行时间；2)单一权重方案案例。对互信息增益评价出的最优25%个加权数据聚类后,得到最优/次优结果的概率超过75%,而运行时间节约了76.82%。
5、在指出IB方法中非共现数据的共现转化拥有两阶段三视角特性的基础上,提出了加权二元化转换方法。两阶段三视角加权可以在非共现数据向共现数据的转化过程中,突出代表性属性来得到更准确反映数据特征的数据表示,以提高IB方法对非共现数据的分析效果。实验表明,TPAW-sIB算法优于CD-sIB、 ROCK、COOLCAT和LIMBO算法。
Information Bottleneck (IB) method is one of data analysis methods, which is originated from Information Theory. IB method uses a special way of data representation-the joint probability model (JPM)-so that it has good expression ability on the relativity between data features and data. However. JPM lacks the ability to express the important level of data features in comparison with the vector space model (VSM). It causes that most of the researches on the IB method ignore the important level of data features and weakens the effectiveness of the IB method. To address this issue, the thesis studies on the feature weighting on the IB method. The goal is to highlight important features by the aid of feature weighting. It can achieve better data representation and improve the effectiveness of the IB method.
First of all, we propose the construction procedure from VSM to weighting JPM. Then, we propose a series of weighing IB method,such as combination weighting, self-learning weighting and two-stage-three-angles weighting for non co-occurrence data. Experimental results show that these methods are feasible and effective. Meanwhile, we suggest to applying mutual information gain on feature weighting evaluation. The mutual information gain evaluation reduces the running time without sacrificing the quality of clustering. Results from this study are useful for improving the effectiveness of the IB method and lay the foundation for constructing a set of the feature weighting IB analysis tools.
The main researches in the study are stated as:
1) Propose the construction procedure from VSM to weighting JPM on the basis of analyzing deeply the similarity and diversity between JPM and VSM. Weighting JPM combines the advantages of JPM and VSM. It has good expression ability on the relativity between data features and data. It also has good ability to express the important level of data features.
2) Propose the relative entropy combination weighting IB method. How to choose a proper weighting scheme is a generally acknowledged devilish problem. The combination weighting derived from the idea of combination evaluation for multiple attribute decision making (MADM) can overcome the limitations of using single weighting scheme. It will help to reflect better the essential characteristics of the data. Firstly, we suggest considering only the combinations among objective weighting schemes. Secondly, we choose relative entropy as the combination method which can be computed in a short time. The experiments on real data have shown that the proposed C WRE-sIB algorithm is superior to the sIB algorithm.
3) Propose a feature weight self-learning mechanism for the IB method. A weight adjusting procedure is applied in the iteration stage. In the procedure, the weights of features are adjusted iteratively. The purpose of the feature self-learning mechanism is to simultaneously minimize the separations within clusters and maximize the separations between clusters so that it can improve the quality of the clustering result. Experimental results show that the proposed feature weight self-learning mechanism is objective and effective. The proposed FWA_CDsIB algorithm is superior to the CD-sIB algorithm.
4) Propose mutual information gain for the weighting evaluation on the IB method. Among majority of weighting schemes and combination weighting methods, the traditional way evaluates the performance of feature weighting by measuring the quality of clustering. However, it is a time-consuming task because clustering algorithms should be run many times, and the number of times depends on the number of weighting schemes or the number of combination weighting iteration. We propose to judge the quality of feature weighting by the resulting gain in mutual information. Therefore, the top s weighted data representations can be selected from the weighting data representation set. Then, the best/second best cluster result can be obtained from the top s representations. Experimental results show that the mutual information gain evaluation reduces the running time without sacrificing the quality of clustering.
5) Propose two stage three angles weighting method for non co-occurrence data. In order to analyze non co-occurrence data using the IB method, non co-occurrence data should be transformed into co-occurrence data with the binary transformation. At two stages of the co-occurrence transformation, we highlight representative features and dim irrelevant features from three viewpoints:non co-occurrence, co-occurrence and both. Experiment results show that the weighting binary transformation method generates better co-occurrence data. The TPAW-sIB algorithm is superior to the CD-sIB, LIMBO, ROCK and COOLCAT algorithms.
本义首先提出了从向量空间模型到加权联合概率模型的构造过程,而后系统性分析并提出了三种可行的加权方法：综合赋权IB方法、自学习权重机制和非共现数据加权二元化转化方法。实验表明,这三种方法是可行的和有效的,能够提高IB算法性能。同时,提出了互信息增益权重评价方式,在不影响聚类质量的前提下,有效降低了IB算法的运行时间。本文成果对进一步研究IB方法,提高IB方法的性能有一定意义,同时也为构造特征赋权的IB数据分析工具奠定了一定的基础。
本文的主要工作包括：
1、深入分析了联合概率模型与向量空间模型表达能力的相同性和差异性,提出了IB方法中从向量空间模型到加权联合概率模型的构造过程。加权联合概率模型结合了向量空间模型和联合概率模型的优点,既能较好的表达出样本属性和样本的相关性,也能较好的表达出样本属性的重要度。
2、为了将多属性决策中的综合赋权应用到IB方法中,提出了相对熵综合赋权IB方法。指出在综合赋权中无需区分主观赋权和客观赋权,并选择了相对熵方法以降低组合权重计算时间。同时,给出了一种基于三种代表性的客观权重方案(熵值法、均方差法和互信息法)的组合权重集选取方法,构建了相对熵综合赋权CWRE-sIB算法。实验表明,CWRE-sIB算法优于sIB算法和一系列单一权重赋权sIB算法。
3、为了消除主观因素的影响,提出了IB方法上的自学习权重机制。在IB聚类过程中调整各个属性的权重,以得到最优赋权数据表示。聚类迭代中,根据权重对最终聚类结果的影响确定权重调整的方向及量值。实验表明,自学习权重是一种客观有效的权重计算方法,FWA_CDsIB算法优于CD-sIB算法。
4、为了降低权重评价的时间消耗,提出了互信息增益权重评价方法。传统的权重评价方法依赖于聚类的评价结果,是一个有效、可行、但却十分耗时的任务。互信息增益评价方式可以在不影响聚类质量的前提下,有效降低算法运行时间。本文中给出了两种典型案例：1)线性组合综合权重案例。对互信息增益评价出的最佳25%个加权数据聚类后,得到最优/次优结果的概率为100%。与此同时,节约了76.04%的运行时间；2)单一权重方案案例。对互信息增益评价出的最优25%个加权数据聚类后,得到最优/次优结果的概率超过75%,而运行时间节约了76.82%。
5、在指出IB方法中非共现数据的共现转化拥有两阶段三视角特性的基础上,提出了加权二元化转换方法。两阶段三视角加权可以在非共现数据向共现数据的转化过程中,突出代表性属性来得到更准确反映数据特征的数据表示,以提高IB方法对非共现数据的分析效果。实验表明,TPAW-sIB算法优于CD-sIB、 ROCK、COOLCAT和LIMBO算法。
Information Bottleneck (IB) method is one of data analysis methods, which is originated from Information Theory. IB method uses a special way of data representation-the joint probability model (JPM)-so that it has good expression ability on the relativity between data features and data. However. JPM lacks the ability to express the important level of data features in comparison with the vector space model (VSM). It causes that most of the researches on the IB method ignore the important level of data features and weakens the effectiveness of the IB method. To address this issue, the thesis studies on the feature weighting on the IB method. The goal is to highlight important features by the aid of feature weighting. It can achieve better data representation and improve the effectiveness of the IB method.
First of all, we propose the construction procedure from VSM to weighting JPM. Then, we propose a series of weighing IB method,such as combination weighting, self-learning weighting and two-stage-three-angles weighting for non co-occurrence data. Experimental results show that these methods are feasible and effective. Meanwhile, we suggest to applying mutual information gain on feature weighting evaluation. The mutual information gain evaluation reduces the running time without sacrificing the quality of clustering. Results from this study are useful for improving the effectiveness of the IB method and lay the foundation for constructing a set of the feature weighting IB analysis tools.
The main researches in the study are stated as:
1) Propose the construction procedure from VSM to weighting JPM on the basis of analyzing deeply the similarity and diversity between JPM and VSM. Weighting JPM combines the advantages of JPM and VSM. It has good expression ability on the relativity between data features and data. It also has good ability to express the important level of data features.
2) Propose the relative entropy combination weighting IB method. How to choose a proper weighting scheme is a generally acknowledged devilish problem. The combination weighting derived from the idea of combination evaluation for multiple attribute decision making (MADM) can overcome the limitations of using single weighting scheme. It will help to reflect better the essential characteristics of the data. Firstly, we suggest considering only the combinations among objective weighting schemes. Secondly, we choose relative entropy as the combination method which can be computed in a short time. The experiments on real data have shown that the proposed C WRE-sIB algorithm is superior to the sIB algorithm.
3) Propose a feature weight self-learning mechanism for the IB method. A weight adjusting procedure is applied in the iteration stage. In the procedure, the weights of features are adjusted iteratively. The purpose of the feature self-learning mechanism is to simultaneously minimize the separations within clusters and maximize the separations between clusters so that it can improve the quality of the clustering result. Experimental results show that the proposed feature weight self-learning mechanism is objective and effective. The proposed FWA_CDsIB algorithm is superior to the CD-sIB algorithm.
4) Propose mutual information gain for the weighting evaluation on the IB method. Among majority of weighting schemes and combination weighting methods, the traditional way evaluates the performance of feature weighting by measuring the quality of clustering. However, it is a time-consuming task because clustering algorithms should be run many times, and the number of times depends on the number of weighting schemes or the number of combination weighting iteration. We propose to judge the quality of feature weighting by the resulting gain in mutual information. Therefore, the top s weighted data representations can be selected from the weighting data representation set. Then, the best/second best cluster result can be obtained from the top s representations. Experimental results show that the mutual information gain evaluation reduces the running time without sacrificing the quality of clustering.
5) Propose two stage three angles weighting method for non co-occurrence data. In order to analyze non co-occurrence data using the IB method, non co-occurrence data should be transformed into co-occurrence data with the binary transformation. At two stages of the co-occurrence transformation, we highlight representative features and dim irrelevant features from three viewpoints:non co-occurrence, co-occurrence and both. Experiment results show that the weighting binary transformation method generates better co-occurrence data. The TPAW-sIB algorithm is superior to the CD-sIB, LIMBO, ROCK and COOLCAT algorithms.
引文
[1]. Tishby N, Pereira F C, Bialek W. The Information Bottleneck Method [C]. In:Proc. of the 37th Allerton Conference on Communication, Control and Computing.1999, 368-377.
[2]. Slonim N. The information bottleneck:Theory and Application. Ph.D. Thesis [D]. Jerusalem, Israel:The Hebrew University of Jerusalem.2002.
[3]. Fabrizio R, Nicola D M. Applying the information bottleneck to statistical relational learning [J]. Machine Learning,2012,86(1):89-114.
[4]. Gedeon T, Parker A E, Dimitrov A G. The Mathematical Structure of Information Bottleneck Methods [J]. Entropy,2012,14,456-479.
[5]. Z Lou, Y Ye, Z Zhu. Information Bottleneck with Local Consistency [C]. In:PRICAI 2012:Trends in Artificial Intelligence,2012-Springer.
[6]. Slonim N, Friedman N, Tishby N. Unsupervised Document Classification Using Sequential Information Maximization [C]. In:Proc. of the 25th Annual International ACM SIGIR Conference on Research and Development in Information Retrieval, 2002:129-136.
[7]. Yuan H Q, Ye Y D. Iterative sIB algorithm [J]. Pattern Recognition Letters,2011, 32(4):606-614.
[8]. Dhanalakshmi S, Ravichandran T. A Modified Approach for Image Segmentation in Information Bottleneck Method [J]. International Journal of Advanced Research in Computer Engineering & Technology,2012,1(7):59-63.
[9].夏利民,谭立球,钟洪.基于信息瓶颈算法的图像语义标注[J].模式识别与人工智能,2008,21(6)：812-818.
[10]. Bardera A, Rigau J, Baoda I, et al. Image Segmentation using Information Bottleneck Method [J]. IEEE Transactions on Image Processing,2009,18(7):1601-1612.
[11]. Hecht R, Noor E, Tishby N. Speaker Recognition via Gaussian Information Bottleneck [C]. In:Proc. of InterSpeech,2009:1567-1570.
[12]. Winston H H, Kennedy L S, Chang S. Video Search Reranking via Information Bottleneck Principle [C]. In:Proc. of ACM International Conference on Multimedia, 2006:35-44.
[13]. Andritsos P, Tzerpos V. Information-Theoretic Software Clustering [J].IEEE Transactions on Software Engineering,2005,31(2):150-165.
[14]. Wang P, Domeniconi C, Laskey K B. Information Bottleneck Co-clustering [C]. In: Proc. of SIAM International Conference on Data Mining,2010.
[15]. Seldin Y, Tishby N. A PAC-Bayesian Analysis of Co-clustering and Beyond [J]. Journal of Machine Learning Research,2010
[16].沈华伟,程学琪,陈海强等.基于信息瓶颈的社区发现[J].计算机学报,2008,31(4)：677-686.
[17]. Bai L, Liang J Y, Dang C Y. A novel attribute weighting algorithm for clustering high-dimensional categorical data [J]. Pattern Recognition,2011,44(12):2843-2861.
[18]. Wen Z. A comparative study of TF-IDF, LSI and multi-words for text classification [J]. Expert Systems with Applications,2011,38(3):2758-2765.
[19].张爱华,靖红芳,王斌,徐燕.文本分类中特征权重因子的作用研究[J].中文信息学报,2010,24(3)：97-104.
[20]. Cost S, Salzberg S. A weighted nearest neighbor algorithm for learning with symbolic features [J]. Machine Learning,1973,10(1):57-78.
[21]. Han EH, Karypis G and Kumar V. Text categorization using weight-adjusted k-nearest neighbor classification [C]. In Proc. of PAKDD-01,5th Pacific-Asia Conference on Knowledge Discovery and Data Mining (ed. D. Cheung, Q. Li and G. Williams). Lecture Notes in Computer Science Series, Springer,2001,53-65.
[22]. Joachims T. A probabilistic analysis of the Rocchio algorithm with TFIDF for text categorization [C]. In:Proc. of ICML-97, Nashville, US,1997,143-151.
[23]. He Z Y, Xu X F, Deng S C. Attribute Value Weighting in k-Modes Clustering [J]. Expert Systems with Applications.2011,38(12):15365-15369.
[24]. Jing L, Ng M K, Huang Z X. An Entropy Weighting k-Means Algorithm for Subspace Clustering of High-Dimensional Sparse Data [J]. IEEE Transactions on knowledge and data engineering,2007,19(8):1026-1041.
[25]. Andritsos P, Tzerpos V. Evaluating value weighting schemes in the clustering of categorical data [C]. In:Proc. Of 1st Workshop on Machine Learning and Intelligent Optimization (LION),2007.
[26].钟洪,夏利民.基于互信息约束聚类的图像语义标注[J].中国图像图形学报,2009,14(6)：1199-1205.
[27].朱真峰,叶阳东,Gang Li.基于变异的迭代sIB算法[J].计算机研究与发展,2007,44(11)：1832-1838.
[28]. Li SS, Zhang B, Li A, et al. Hyperspectral Imagery Clustering With Neighborhood Constraints [J]. IEEE Geoscience and Remote Sensing Letters,2013,10(3):588-592.
[29]. Chang H, Yang S X, Cao J N. Dynamic genetic algorithms for the dynamic load balanced clustering problem in mobile ad hoc networks [J]. Expert Systems with Applications,2013,40(4):1381-1392.
[30]. Baskir M B, Turksen I B. Enhanced fuzzy clustering algorithm and cluster validity index for human perception [J]. Expert Systems with Applications,2013,40(3): 929-937.
[31]. Gou S P, Zhuang X, Li Y Y, et al. Multi-elitist immune clonal quantum clustering algorithm [J]. Neurocomputing,2013,101(4):275-289.
[32]. Gong M G, Liang Y, Shi J, et al. Fuzzy C-means clustering with local information and kernel metric for image segmentation [J]. IEEE transactions on image processing, 2013,22(2):573-584.
[33]. Lv SG, Feng Y L. Consistency of coefficient-based spectral clustering with 11-regularizer [J]. Mathematical and Computer Modelling,2013,57(3-4):469-482.
[34]. Jain A K, Murty M N, Flynn P J. Data clustering:a review [J]. ACM Computing Surveys,1999,32(3):264-323
[35]. Halkidi M, Batistakis Y, Vazirgiannis M. Cluster validity methods:part I[J]. SIGMOD Record,2002,31(2):40-45
[36]. Halkidi M, Batistakis Y, Vazirgiannis M. Clustering validity checking methods:part Ⅱ[J]. SIGMOD Record,2002,31(3):19-27
[37].孙吉贵,刘杰,赵连宇.聚类算法研究[J].软件学报,2008,19(1)：48-61.
[38]. Mehmed Kantardzic.数据挖掘—概念、模型、方法和算法[M].清华大学出版社,2003.
[39].郭建生,赵奕,施鹏飞.一种有效的用于数据挖掘的动态概念聚类算法[J].软件学报,2001,12(4)：582-591.
[40]. Bekkerman R, El-Yaniv R, Tishby N. Distributional Word Clusters vs. Words for Text Categorization. Journal of Machine Learning Research,2003:1183-1208.
[41]. Jain A K. Data clustering:50 years beyond K-means [J]. Pattern Recognition Letters, 2010,31:651-666.
[42].郑丹,王潜平.K-means初始聚类中心的选择算法[J].计算机应用.2012,32(8)：2186-2188,2192.
[43]. Fung B C M, Wang K, Ester M. Hierarchical document clustering [C]. In:John Wang (Ed.), The Encyclopedia of Data Warehousing and Mining, Idea Group,2005.
[44]. Dang X, Bailey J. A Hierarchical Information Theoretic Technique for the Discovery of Non Linear Alternative Clusterings [C]. In:Proc. of the 16th ACM SIGKDD International Conference on Knowledge Discovery and Data Mining,2010:573-582.
[45]. Tramacere A, Vecchio C. gamma-ray DBSCAN:a clustering algorithm applied to Fermi-LAT gamma-ray data [C].2012,1505:705-708. Heidelberg, GERMANY.
[46].岳士弘,王正友.二分网格聚类方法及有效性[J].计算机研究与发展,2005,42(9)：1505-1510.
[47].管涛.统计聚类模型研究综述[J].计算机科学,2012,39(7)：18-24.
[48].魏海坤,徐嗣鑫,宋文忠.神经网络的泛化理论和泛化方法[J].自动化学报,2001,27(6)：806-815.
[49].欧阳成,姬红兵,田野.一种基于模糊聚类的PHD航迹维持算法[J].电子学报,2012,40(6)：1284-1288.
[50]. Peters G, Weber R, Nowatzke R. Dynamic rough clustering and its applications [J]. Applied Soft Computing,2012,12(10):3193-3207.
[51]. Voges K E, Pope N K L. Rough Clustering Using an Evolutionary Algorithm[C]. In: 45th Hawaii International Conference on System Sciences (HICSS), Maui, HI, USA, 2012:4-7.
[52]. Qing S, Xulei Y, Yeng C S. An information-theoretic fuzzy C-spherical shells clustering algorithm [J]. Fuzzy Sets and Systems,2010,161(13):1755-1773.
[53]. Yang X, Xie W X, Huang J J. Spherical shell clustering based on quantum measurement[J].Journal of Xidian University,2008,35(1):43-48.
[54]. Ye Z W. The Research of Intrusion Detection Algorithms Based on the Clustering of Information Entropy[C]. In:International Conference on Environment Science and Engineering (ICESE), Bali Island, INDONESIA,2012,12:1329-1334.
[55]. da C, Anderson F B F, Pimentel B A, de S, Renata M C R. Clustering interval data through kernel-induced feature space[J]. Journal of Intelligent Information Systems, 2013,40(1):109-140.
[56]. Bronselaer A, De T G. Concept-relational text clustering [J]. International Journal of Intelligent Systems,2012,27(11):970-993.
[57].肖宇,于剑.基于近邻传播算法的半监督聚类[J].软件学报,2008,19(11)：2803-2813.
[58]. Feng X L,Yu H T. Research on density-insensitive affinity propagation clustering algorithm [J]. Computer Engineering,2012,38(2):159-162.
[59]. Swamakar, S. Ontology-based context dependent document clustering method [J]. International Journal of Knowledge Engineering and Data Mining,2012,2(1):35-59.
[60].Liao Z F, Luo H, Fan X P. New hybrid data orientation cluster algorithm [J]. Control and Decision,2009,24(5):697-700,705.
[61]. Jiao L M, Liu Y L, Zou B. Self-organizing dual clustering considering spatial analysis and hybrid distance measures[J].Science China-Earth Sciences,2011,54(8): 1268-1278.
[62]. Pan X Y, Chen H. Multi-agent Evolutionary Clustering Algorithm Based on Manifold Distance[C]. In:2012 Eighth International Conference on Computational Intelligence and Security (CIS),2012:123-127.
[63]. Shannon CE. A mathematical theory of communication [J]. The Bell System Technical Journal,1948,27:379-423.
[64].钟义信.信息科学与信息论[J].通信学报,1990,11(1)：45-51.
[65].韩镇,胡瑞敏,陈皓,李明.一种基于分层率失真优化的容错性视频转码算法[J].计算机学报,2009,32(6)：1152-1161.
[66]. Slonim N, Friedman N, Tishby N. Multivariate Information Bottleneck [J]. Neural Computation,2006,18 (8):1739-1789.
[67]. Seldin Y, Slonim N, and Tishby N. Information bottleneck for non co-occurrence data [J]. Advances in Neural Information Processing Systems. Cambridge, MA:MIT Press,2007,1241-1248.
[68]. Shamir O, Sabato S, and Tishby N. Learning and generalization with the information bottleneck [J]. Theoretical Computer Science,2010,411:2696-2711.
[69]. Andritsos P, Tsaparas P, Miller RJ, Sevcik KC. LIMBO:Scalable Clustering of Categorical Data [C]. In:Proc. of 9th International Conference on Extending Database Technology,2004.
[70].叶阳东,何锡点,贾利民CD-sIB:面向范畴类型数据的sIB算法[J].电子学报,2009,37(10)：2165-2172.
[71]. Van Rijsbergen CJ. A theoretical basis for the use of co-occurrence data in information retrieval [J]. Journal of Documentation,1997,33(2):106-119.
[72]. Peat H J, Willett P. The limitations of term co-occurrence data for query expansion in document retrieval systems [J]. Journal of the American Society for Information Science,1991,42(5):378-383.
[73].丁锋,陈通文,萧德云.一般双率随机系统状态空间模型及其辨识[J].自动化学报,2004,30(5)：652-663.
[74].陆玉昌,鲁明羽,李凡,周立柱.向量空间法中单词权重函数的分析和构造[J].计算机研究与发展,2002,39(10)：1205-1210.
[75].黄萱菁,夏迎炬,吴立德.基于向量空间模型的文本过滤系统[J].软件学报,2003,14(3)：435-442.
[76]. Shankar S, Karypis G. A feature weight adjustment algorithm for Document Categorizaiton [C]. In:Proc. Of the 6th ACM SIGKDD International Conference on Knowledge Discovery and DataMining. New York, ACM Press,2000.
[77]. Sebastiani, F. Machine learning in automated text categorization [J], ACM Computing Surveys 34,2002,1-47.
[78]. Debole F, Sebastiani F. Supervised term weighting for automated text categorization [C]. In Proc. of the ACM Symposium on Applied Computing.2003.
[79]. Sparck Jones K. A statistical interpretation of term specificity and its application in retrieval [J]. Journal of Documentation,1972,28:11-21.
[80].王骏,王士同,邓赵红.特征加权距离与软子空间学习相结合的文本聚类新方法[J].计算机学报,2012,35(8)：1655-1665.
[81]. Bai X, Chen G, Lin Z, et al. Improving image clustering:An unsupervised feature weight learning framework [C]. In:ICIP'2008,2008:977-980.
[82]. Tahayna B, Ayyasamy R K, Alhashmi S, Eu-Gene S. A Novel Weighting Scheme for Efficient Document Indexing and Classification [C]. In:Information Technology (ITSim),2010 International Symposium.2010:783-788.
[83]. Jiao Q Z, Wei C J. A Term Weighting Approach with Subjective Logic reasoning for Text Categorization [C]. In:Computational Intelligence and Software Engineering, 2009,1-5.
[84]. Tsai C Y, Chiu C C. Developing a feature weight self-adjustment mechanism for a K-means [J] Computational Statistics and Data Analysis.2008,52(10):4658-4672.
[85].唐焕玲,孙建涛,陆玉昌.文本分类中结合评估函数的TEF-WA权值调整技术[J].计算机研究与发展,2005,42(1)：47-53.
[86].张猛,王大玲,于戈.一种基于自动阈值发现的文本聚类方法[J].计算机研究与发展,2004,41(10)：1748-1753.
[87]. Liu H, Yu L. Toward integrating feature selection algorithms for classification and clustering [J]. IEEE T KNOWL DATA EN,2005,17(4):491-502.
[88]. Li X, Xiao X P. Study on the combination weighting method of hybrid multiple attribute decision-making [C]. In:Proc. of 2011 International Conference on Grey Systems and Intelligent Services.
[89]. Tang W, Chen A Z, Li D M, Yang, Y. The application of combination weighting approach in multiple attribute decision making [C]. In:Proc. of the 8th International Conference on Machine Learning and Cybernetics,2009,2724-2728.
[90]. Yang C, Bo L. Fuzzy Comprehensive Evaluation of Software Dependability with Rough Set Theory based Combinational Weight [C]. In:Proc. of International Conference on Networks Security, Wireless Communications and Trusted Computing, 2009,400-^03.
[91].胡文斌,孟波,王少梅.基于贝叶斯网络的权重自学习方法研究[J].计算机集成制造系统,2005,11(12)：1781-1784.
[92].张晓,樊治平.基于前景理论的风险型混合多属性决策方法[J].系统工程学报,2012,27(6)：772-781.
[93].刘秀梅,赵克勤.属性等级和属性值均为区间数的多属性决策集对分析[J].模糊系统与数学,2012,26(6)：124-131.
[94]. Hwang C L, Yoon K. Multiple Attribute Decision Making:Methods and Applications [M]. Springer, Berlin,1981.
[95]. Sparck Jones K. IDF term weighting and IR research lessons [J]. Journal of Documentation,2004,60(6):521-523.
[96]. Soucy P, Mineau G W. Beyond TFIDF Weighting for Text Categorization in the Vector Space Model [C]. In:Proc. of Int'l Joint Conf. Artificial Intelligence,2005: 1130-1135.
[97].杨芙清,梅宏,李克勤.软件复用与软件构件技术[J].电子学报,1999,27(2)：68-75.
[98]. Zhou Y F, Wu F J. Combination Weighting Approach in Multiple Attribute Decision Making Based on Relative Entropy [J] Operations research and management science, 2006,15:48-53. (In Chinese with English Abstract).
[99]. Chen X J, Ye Y M, Xu X F. A feature group weighting method for subspace clustering of high-dimensional data [J]. Pattern Recognition,2012,45:434-446.
[100].霍良安,王中兴.模糊多属性决策中的离差最大化方法[J].运筹与管理,2012,21(3)：39-43.
[101]. Man L. Supervised and Traditional Term Weighting Methods for Automatic Text Categorization [J]. IEEE Transactions on Pattern Analysis and Machine Intelligence, 2009,31(4):721-735.
[102]. Li D F. TOPSIS-Based Nonlinear-Programming Methodology for Multiattribute Decision Making [J]. IEEE Transactions on Fuzzy Systems.2010,18(2):299-311.
[103].王中兴.多属性决策的组合赋权法[J].应用数学与计算机数学学报.2003,17(2)：55-62.
[104]. Wang Y M, Parkand C. Multiple attribute decision making based on fuzzy preference information on alternatives:Ranking and weighting [J]. Fuzzy Sets and Systems, 2005,153:331-346.
[105].樊治平,赵萱.多属性决策中权重确定的主客观赋权法[J].决策与决策支持系统,1997,7(4)：87-91.
[106].王青,祝世虎,董朝阳,陈宗基.自学习智能决策支持系统[J].系统仿真学报,2006,18(4)：924-926.
[107].鲍培明.基于BP网络的模糊Petri网的学习能力[J].计算机学报,2004,27(5)：695-702.
[108].王宏刚,曾建潮,徐玉斌.优良模式自学习遗传算法[J].自动化学报,1999,25(3)：375-379.
[109]. Blum A L. Rivest R L. Training a 3-node Neural Networks is NP-complete [J]. Neural Netw,1992,5:117-127.
[110]. Akay M F, Zayid E I M, Akturk E, et al. Artificial neural network-based model for predicting VO2 max from a submaximal exercise test [J]. Expert Systems with Applications,2011,38(3):2007-2010.
[111]. Khan J, Wei J S, Ringner M, et al. Classification and diagnostic prediction of cancers using gene expression profiling and artificial neural networks [J]. Nature Medicine, 2001,7(6):673-679.
[112]. Garcia-Moral A I, Solera-Urena R, Pelaez-Moreno C, et al. Data Balancing for Efficient Training of Hybrid ANN/HMM Automatic Speech Recognition Systems [J]. IEEE Transactions on Audio, Speech and Language Processing,2011,3:468-81.
[113].何耀华,夏志忠.BP网络的快速自适应学习算法[J].系统工程理论与实践.2000,1：93-98.
[114].王君,潘星,李静,刘鲁.基于案例推理的知识管理咨询系统[J].清华大学学报(自然科学版),2006,46(S 1)：990-995.
[115]. Yates R B, Neto B R. Modern Information Retrieval [M]. Addison-Wesley-Longman, 1999.
[116].苏金树,张博锋,徐昕.基于机器学习的文本分类技术研究进展[J].软件学报,2006,17(9)：1848-1859.
[117].张净,孙志挥,宋余庆,倪巍伟,晏燕华.基于信息论的高维海量数据离群点挖掘[J].计算机科学,2011,38(7)：148-161.
[118].王利民,徐沛娟,李雄飞.基于广义信息论的决策森林多重子模型集成方法[J].模式识别与人工智能,2009,22(2)：325-329.
[119]. Wu X H, Wu B, Sun J. Mixed fuzzy inter-cluster separation clustering algorithm [J]. Applied Mathematical Modelling,2011,35(10):4790-4795.
[120]. Zhang J Y, Peng L Q, Zhao X X. Robust data clustering by learning multi-metric Lq-norm distances [J]. Expert Systems with Applications,2012,39:335-349.
[121]. Nguyen X V, Epps J. minCEntropy:A Novel Information Theoretic Approach for the Generation of Alternative Clusterings [C]. In:Proc. of IEEE International Conference on Data Mining,2010:521-530.
[122]. Hu B G, Wang Y. Evaluation criteria based on mutual information for classifications including rejected class [J]. ActaAutomatica Sinica,2008,34:1396-1403.
[123]. OkanSakar C, Kursun O. A method for combining mutual information and canonical correlation analysis-Predictive Mutual Information and its use in feature selection [J]. Expert Systems with Applications,2012,39:3333-3344.
[124]. Dhillon IS. Information Theoretic Coclustering [C]. In:Proc. of KDD2003,2003.
[125]. Torkkola K. Feature extraction by non-parametric mutual information maximization [J]. Journal of Machine Learning Research,2003,3:1415-1438.
[126]. Senst M, Ascheid G, Luumlders H. Performance Evaluation of the Markov Chain Monte Carlo MIMO Detector based on Mutual Information [C]. In:Proc. of ICC 2010,2010.
[127]. Andritsos P, Miller R J, Tsaparas P. Information-Theoretic Tools for Mining Database Structure from Large Data Sets [C]. In:Proc. of SIGMOD Conference,2004: 731-742.
[128]. Lazebnik S, Raginsky M. Supervised Learning of Quantizer Codebooks by Information Loss Minimization [J]. IEEE Transactions on Pattern Analysis and Machine Intelligence,2009,31:1294-1309.
[129]. Elidan G, Friedman N. Learning Hidden Variable Networks:The Information Bottleneck Approach [J]. Journal of Machine Learning Research,2005,6:81-127.
[130]. Buesing L, Maass W. Simplified Rules and Theoretical Analysis for Information Bottleneck Optimization and PCA with Spiking Neurons [C], In:Proc. of Advances in Neural Information Processing Systems,2007.
[131]. Buesing L, Maass W. A Spiking Neuron as Information Bottleneck [J]. Neural Computation,2010 22(8):1961-1992.
[132]. Deng S H, He Z Y, Xu X F. G-ANMI:A mutual information based genetic clustering algorithm for categorical data [J]. Knowledge-Based Systems,2010,23(21):144-149.
[133]. He Z Y, Xu X F, Deng S H. k-ANMI:A mutual information based clustering algorithm for categorical data. Information Fusion,2008,9(2):223-233.
[134]. Daniel B, Julia C, Yi L. COOLCAT. an entropy-based algorithm for categorical clustering [C]. In Proc. of the eleventh international conference on Information and knowledge management,2002:582-589.
[135]. Blake C L, Merz C J. UCI Repository of Machine Learning Databases [EB].1998. http://www.ics.uci.edu/～mlearn/MLRepository.html.
[2]. Slonim N. The information bottleneck:Theory and Application. Ph.D. Thesis [D]. Jerusalem, Israel:The Hebrew University of Jerusalem.2002.
[3]. Fabrizio R, Nicola D M. Applying the information bottleneck to statistical relational learning [J]. Machine Learning,2012,86(1):89-114.
[4]. Gedeon T, Parker A E, Dimitrov A G. The Mathematical Structure of Information Bottleneck Methods [J]. Entropy,2012,14,456-479.
[5]. Z Lou, Y Ye, Z Zhu. Information Bottleneck with Local Consistency [C]. In:PRICAI 2012:Trends in Artificial Intelligence,2012-Springer.
[6]. Slonim N, Friedman N, Tishby N. Unsupervised Document Classification Using Sequential Information Maximization [C]. In:Proc. of the 25th Annual International ACM SIGIR Conference on Research and Development in Information Retrieval, 2002:129-136.
[7]. Yuan H Q, Ye Y D. Iterative sIB algorithm [J]. Pattern Recognition Letters,2011, 32(4):606-614.
[8]. Dhanalakshmi S, Ravichandran T. A Modified Approach for Image Segmentation in Information Bottleneck Method [J]. International Journal of Advanced Research in Computer Engineering & Technology,2012,1(7):59-63.
[9].夏利民,谭立球,钟洪.基于信息瓶颈算法的图像语义标注[J].模式识别与人工智能,2008,21(6)：812-818.
[10]. Bardera A, Rigau J, Baoda I, et al. Image Segmentation using Information Bottleneck Method [J]. IEEE Transactions on Image Processing,2009,18(7):1601-1612.
[11]. Hecht R, Noor E, Tishby N. Speaker Recognition via Gaussian Information Bottleneck [C]. In:Proc. of InterSpeech,2009:1567-1570.
[12]. Winston H H, Kennedy L S, Chang S. Video Search Reranking via Information Bottleneck Principle [C]. In:Proc. of ACM International Conference on Multimedia, 2006:35-44.
[13]. Andritsos P, Tzerpos V. Information-Theoretic Software Clustering [J].IEEE Transactions on Software Engineering,2005,31(2):150-165.
[14]. Wang P, Domeniconi C, Laskey K B. Information Bottleneck Co-clustering [C]. In: Proc. of SIAM International Conference on Data Mining,2010.
[15]. Seldin Y, Tishby N. A PAC-Bayesian Analysis of Co-clustering and Beyond [J]. Journal of Machine Learning Research,2010
[16].沈华伟,程学琪,陈海强等.基于信息瓶颈的社区发现[J].计算机学报,2008,31(4)：677-686.
[17]. Bai L, Liang J Y, Dang C Y. A novel attribute weighting algorithm for clustering high-dimensional categorical data [J]. Pattern Recognition,2011,44(12):2843-2861.
[18]. Wen Z. A comparative study of TF-IDF, LSI and multi-words for text classification [J]. Expert Systems with Applications,2011,38(3):2758-2765.
[19].张爱华,靖红芳,王斌,徐燕.文本分类中特征权重因子的作用研究[J].中文信息学报,2010,24(3)：97-104.
[20]. Cost S, Salzberg S. A weighted nearest neighbor algorithm for learning with symbolic features [J]. Machine Learning,1973,10(1):57-78.
[21]. Han EH, Karypis G and Kumar V. Text categorization using weight-adjusted k-nearest neighbor classification [C]. In Proc. of PAKDD-01,5th Pacific-Asia Conference on Knowledge Discovery and Data Mining (ed. D. Cheung, Q. Li and G. Williams). Lecture Notes in Computer Science Series, Springer,2001,53-65.
[22]. Joachims T. A probabilistic analysis of the Rocchio algorithm with TFIDF for text categorization [C]. In:Proc. of ICML-97, Nashville, US,1997,143-151.
[23]. He Z Y, Xu X F, Deng S C. Attribute Value Weighting in k-Modes Clustering [J]. Expert Systems with Applications.2011,38(12):15365-15369.
[24]. Jing L, Ng M K, Huang Z X. An Entropy Weighting k-Means Algorithm for Subspace Clustering of High-Dimensional Sparse Data [J]. IEEE Transactions on knowledge and data engineering,2007,19(8):1026-1041.
[25]. Andritsos P, Tzerpos V. Evaluating value weighting schemes in the clustering of categorical data [C]. In:Proc. Of 1st Workshop on Machine Learning and Intelligent Optimization (LION),2007.
[26].钟洪,夏利民.基于互信息约束聚类的图像语义标注[J].中国图像图形学报,2009,14(6)：1199-1205.
[27].朱真峰,叶阳东,Gang Li.基于变异的迭代sIB算法[J].计算机研究与发展,2007,44(11)：1832-1838.
[28]. Li SS, Zhang B, Li A, et al. Hyperspectral Imagery Clustering With Neighborhood Constraints [J]. IEEE Geoscience and Remote Sensing Letters,2013,10(3):588-592.
[29]. Chang H, Yang S X, Cao J N. Dynamic genetic algorithms for the dynamic load balanced clustering problem in mobile ad hoc networks [J]. Expert Systems with Applications,2013,40(4):1381-1392.
[30]. Baskir M B, Turksen I B. Enhanced fuzzy clustering algorithm and cluster validity index for human perception [J]. Expert Systems with Applications,2013,40(3): 929-937.
[31]. Gou S P, Zhuang X, Li Y Y, et al. Multi-elitist immune clonal quantum clustering algorithm [J]. Neurocomputing,2013,101(4):275-289.
[32]. Gong M G, Liang Y, Shi J, et al. Fuzzy C-means clustering with local information and kernel metric for image segmentation [J]. IEEE transactions on image processing, 2013,22(2):573-584.
[33]. Lv SG, Feng Y L. Consistency of coefficient-based spectral clustering with 11-regularizer [J]. Mathematical and Computer Modelling,2013,57(3-4):469-482.
[34]. Jain A K, Murty M N, Flynn P J. Data clustering:a review [J]. ACM Computing Surveys,1999,32(3):264-323
[35]. Halkidi M, Batistakis Y, Vazirgiannis M. Cluster validity methods:part I[J]. SIGMOD Record,2002,31(2):40-45
[36]. Halkidi M, Batistakis Y, Vazirgiannis M. Clustering validity checking methods:part Ⅱ[J]. SIGMOD Record,2002,31(3):19-27
[37].孙吉贵,刘杰,赵连宇.聚类算法研究[J].软件学报,2008,19(1)：48-61.
[38]. Mehmed Kantardzic.数据挖掘—概念、模型、方法和算法[M].清华大学出版社,2003.
[39].郭建生,赵奕,施鹏飞.一种有效的用于数据挖掘的动态概念聚类算法[J].软件学报,2001,12(4)：582-591.
[40]. Bekkerman R, El-Yaniv R, Tishby N. Distributional Word Clusters vs. Words for Text Categorization. Journal of Machine Learning Research,2003:1183-1208.
[41]. Jain A K. Data clustering:50 years beyond K-means [J]. Pattern Recognition Letters, 2010,31:651-666.
[42].郑丹,王潜平.K-means初始聚类中心的选择算法[J].计算机应用.2012,32(8)：2186-2188,2192.
[43]. Fung B C M, Wang K, Ester M. Hierarchical document clustering [C]. In:John Wang (Ed.), The Encyclopedia of Data Warehousing and Mining, Idea Group,2005.
[44]. Dang X, Bailey J. A Hierarchical Information Theoretic Technique for the Discovery of Non Linear Alternative Clusterings [C]. In:Proc. of the 16th ACM SIGKDD International Conference on Knowledge Discovery and Data Mining,2010:573-582.
[45]. Tramacere A, Vecchio C. gamma-ray DBSCAN:a clustering algorithm applied to Fermi-LAT gamma-ray data [C].2012,1505:705-708. Heidelberg, GERMANY.
[46].岳士弘,王正友.二分网格聚类方法及有效性[J].计算机研究与发展,2005,42(9)：1505-1510.
[47].管涛.统计聚类模型研究综述[J].计算机科学,2012,39(7)：18-24.
[48].魏海坤,徐嗣鑫,宋文忠.神经网络的泛化理论和泛化方法[J].自动化学报,2001,27(6)：806-815.
[49].欧阳成,姬红兵,田野.一种基于模糊聚类的PHD航迹维持算法[J].电子学报,2012,40(6)：1284-1288.
[50]. Peters G, Weber R, Nowatzke R. Dynamic rough clustering and its applications [J]. Applied Soft Computing,2012,12(10):3193-3207.
[51]. Voges K E, Pope N K L. Rough Clustering Using an Evolutionary Algorithm[C]. In: 45th Hawaii International Conference on System Sciences (HICSS), Maui, HI, USA, 2012:4-7.
[52]. Qing S, Xulei Y, Yeng C S. An information-theoretic fuzzy C-spherical shells clustering algorithm [J]. Fuzzy Sets and Systems,2010,161(13):1755-1773.
[53]. Yang X, Xie W X, Huang J J. Spherical shell clustering based on quantum measurement[J].Journal of Xidian University,2008,35(1):43-48.
[54]. Ye Z W. The Research of Intrusion Detection Algorithms Based on the Clustering of Information Entropy[C]. In:International Conference on Environment Science and Engineering (ICESE), Bali Island, INDONESIA,2012,12:1329-1334.
[55]. da C, Anderson F B F, Pimentel B A, de S, Renata M C R. Clustering interval data through kernel-induced feature space[J]. Journal of Intelligent Information Systems, 2013,40(1):109-140.
[56]. Bronselaer A, De T G. Concept-relational text clustering [J]. International Journal of Intelligent Systems,2012,27(11):970-993.
[57].肖宇,于剑.基于近邻传播算法的半监督聚类[J].软件学报,2008,19(11)：2803-2813.
[58]. Feng X L,Yu H T. Research on density-insensitive affinity propagation clustering algorithm [J]. Computer Engineering,2012,38(2):159-162.
[59]. Swamakar, S. Ontology-based context dependent document clustering method [J]. International Journal of Knowledge Engineering and Data Mining,2012,2(1):35-59.
[60].Liao Z F, Luo H, Fan X P. New hybrid data orientation cluster algorithm [J]. Control and Decision,2009,24(5):697-700,705.
[61]. Jiao L M, Liu Y L, Zou B. Self-organizing dual clustering considering spatial analysis and hybrid distance measures[J].Science China-Earth Sciences,2011,54(8): 1268-1278.
[62]. Pan X Y, Chen H. Multi-agent Evolutionary Clustering Algorithm Based on Manifold Distance[C]. In:2012 Eighth International Conference on Computational Intelligence and Security (CIS),2012:123-127.
[63]. Shannon CE. A mathematical theory of communication [J]. The Bell System Technical Journal,1948,27:379-423.
[64].钟义信.信息科学与信息论[J].通信学报,1990,11(1)：45-51.
[65].韩镇,胡瑞敏,陈皓,李明.一种基于分层率失真优化的容错性视频转码算法[J].计算机学报,2009,32(6)：1152-1161.
[66]. Slonim N, Friedman N, Tishby N. Multivariate Information Bottleneck [J]. Neural Computation,2006,18 (8):1739-1789.
[67]. Seldin Y, Slonim N, and Tishby N. Information bottleneck for non co-occurrence data [J]. Advances in Neural Information Processing Systems. Cambridge, MA:MIT Press,2007,1241-1248.
[68]. Shamir O, Sabato S, and Tishby N. Learning and generalization with the information bottleneck [J]. Theoretical Computer Science,2010,411:2696-2711.
[69]. Andritsos P, Tsaparas P, Miller RJ, Sevcik KC. LIMBO:Scalable Clustering of Categorical Data [C]. In:Proc. of 9th International Conference on Extending Database Technology,2004.
[70].叶阳东,何锡点,贾利民CD-sIB:面向范畴类型数据的sIB算法[J].电子学报,2009,37(10)：2165-2172.
[71]. Van Rijsbergen CJ. A theoretical basis for the use of co-occurrence data in information retrieval [J]. Journal of Documentation,1997,33(2):106-119.
[72]. Peat H J, Willett P. The limitations of term co-occurrence data for query expansion in document retrieval systems [J]. Journal of the American Society for Information Science,1991,42(5):378-383.
[73].丁锋,陈通文,萧德云.一般双率随机系统状态空间模型及其辨识[J].自动化学报,2004,30(5)：652-663.
[74].陆玉昌,鲁明羽,李凡,周立柱.向量空间法中单词权重函数的分析和构造[J].计算机研究与发展,2002,39(10)：1205-1210.
[75].黄萱菁,夏迎炬,吴立德.基于向量空间模型的文本过滤系统[J].软件学报,2003,14(3)：435-442.
[76]. Shankar S, Karypis G. A feature weight adjustment algorithm for Document Categorizaiton [C]. In:Proc. Of the 6th ACM SIGKDD International Conference on Knowledge Discovery and DataMining. New York, ACM Press,2000.
[77]. Sebastiani, F. Machine learning in automated text categorization [J], ACM Computing Surveys 34,2002,1-47.
[78]. Debole F, Sebastiani F. Supervised term weighting for automated text categorization [C]. In Proc. of the ACM Symposium on Applied Computing.2003.
[79]. Sparck Jones K. A statistical interpretation of term specificity and its application in retrieval [J]. Journal of Documentation,1972,28:11-21.
[80].王骏,王士同,邓赵红.特征加权距离与软子空间学习相结合的文本聚类新方法[J].计算机学报,2012,35(8)：1655-1665.
[81]. Bai X, Chen G, Lin Z, et al. Improving image clustering:An unsupervised feature weight learning framework [C]. In:ICIP'2008,2008:977-980.
[82]. Tahayna B, Ayyasamy R K, Alhashmi S, Eu-Gene S. A Novel Weighting Scheme for Efficient Document Indexing and Classification [C]. In:Information Technology (ITSim),2010 International Symposium.2010:783-788.
[83]. Jiao Q Z, Wei C J. A Term Weighting Approach with Subjective Logic reasoning for Text Categorization [C]. In:Computational Intelligence and Software Engineering, 2009,1-5.
[84]. Tsai C Y, Chiu C C. Developing a feature weight self-adjustment mechanism for a K-means [J] Computational Statistics and Data Analysis.2008,52(10):4658-4672.
[85].唐焕玲,孙建涛,陆玉昌.文本分类中结合评估函数的TEF-WA权值调整技术[J].计算机研究与发展,2005,42(1)：47-53.
[86].张猛,王大玲,于戈.一种基于自动阈值发现的文本聚类方法[J].计算机研究与发展,2004,41(10)：1748-1753.
[87]. Liu H, Yu L. Toward integrating feature selection algorithms for classification and clustering [J]. IEEE T KNOWL DATA EN,2005,17(4):491-502.
[88]. Li X, Xiao X P. Study on the combination weighting method of hybrid multiple attribute decision-making [C]. In:Proc. of 2011 International Conference on Grey Systems and Intelligent Services.
[89]. Tang W, Chen A Z, Li D M, Yang, Y. The application of combination weighting approach in multiple attribute decision making [C]. In:Proc. of the 8th International Conference on Machine Learning and Cybernetics,2009,2724-2728.
[90]. Yang C, Bo L. Fuzzy Comprehensive Evaluation of Software Dependability with Rough Set Theory based Combinational Weight [C]. In:Proc. of International Conference on Networks Security, Wireless Communications and Trusted Computing, 2009,400-^03.
[91].胡文斌,孟波,王少梅.基于贝叶斯网络的权重自学习方法研究[J].计算机集成制造系统,2005,11(12)：1781-1784.
[92].张晓,樊治平.基于前景理论的风险型混合多属性决策方法[J].系统工程学报,2012,27(6)：772-781.
[93].刘秀梅,赵克勤.属性等级和属性值均为区间数的多属性决策集对分析[J].模糊系统与数学,2012,26(6)：124-131.
[94]. Hwang C L, Yoon K. Multiple Attribute Decision Making:Methods and Applications [M]. Springer, Berlin,1981.
[95]. Sparck Jones K. IDF term weighting and IR research lessons [J]. Journal of Documentation,2004,60(6):521-523.
[96]. Soucy P, Mineau G W. Beyond TFIDF Weighting for Text Categorization in the Vector Space Model [C]. In:Proc. of Int'l Joint Conf. Artificial Intelligence,2005: 1130-1135.
[97].杨芙清,梅宏,李克勤.软件复用与软件构件技术[J].电子学报,1999,27(2)：68-75.
[98]. Zhou Y F, Wu F J. Combination Weighting Approach in Multiple Attribute Decision Making Based on Relative Entropy [J] Operations research and management science, 2006,15:48-53. (In Chinese with English Abstract).
[99]. Chen X J, Ye Y M, Xu X F. A feature group weighting method for subspace clustering of high-dimensional data [J]. Pattern Recognition,2012,45:434-446.
[100].霍良安,王中兴.模糊多属性决策中的离差最大化方法[J].运筹与管理,2012,21(3)：39-43.
[101]. Man L. Supervised and Traditional Term Weighting Methods for Automatic Text Categorization [J]. IEEE Transactions on Pattern Analysis and Machine Intelligence, 2009,31(4):721-735.
[102]. Li D F. TOPSIS-Based Nonlinear-Programming Methodology for Multiattribute Decision Making [J]. IEEE Transactions on Fuzzy Systems.2010,18(2):299-311.
[103].王中兴.多属性决策的组合赋权法[J].应用数学与计算机数学学报.2003,17(2)：55-62.
[104]. Wang Y M, Parkand C. Multiple attribute decision making based on fuzzy preference information on alternatives:Ranking and weighting [J]. Fuzzy Sets and Systems, 2005,153:331-346.
[105].樊治平,赵萱.多属性决策中权重确定的主客观赋权法[J].决策与决策支持系统,1997,7(4)：87-91.
[106].王青,祝世虎,董朝阳,陈宗基.自学习智能决策支持系统[J].系统仿真学报,2006,18(4)：924-926.
[107].鲍培明.基于BP网络的模糊Petri网的学习能力[J].计算机学报,2004,27(5)：695-702.
[108].王宏刚,曾建潮,徐玉斌.优良模式自学习遗传算法[J].自动化学报,1999,25(3)：375-379.
[109]. Blum A L. Rivest R L. Training a 3-node Neural Networks is NP-complete [J]. Neural Netw,1992,5:117-127.
[110]. Akay M F, Zayid E I M, Akturk E, et al. Artificial neural network-based model for predicting VO2 max from a submaximal exercise test [J]. Expert Systems with Applications,2011,38(3):2007-2010.
[111]. Khan J, Wei J S, Ringner M, et al. Classification and diagnostic prediction of cancers using gene expression profiling and artificial neural networks [J]. Nature Medicine, 2001,7(6):673-679.
[112]. Garcia-Moral A I, Solera-Urena R, Pelaez-Moreno C, et al. Data Balancing for Efficient Training of Hybrid ANN/HMM Automatic Speech Recognition Systems [J]. IEEE Transactions on Audio, Speech and Language Processing,2011,3:468-81.
[113].何耀华,夏志忠.BP网络的快速自适应学习算法[J].系统工程理论与实践.2000,1：93-98.
[114].王君,潘星,李静,刘鲁.基于案例推理的知识管理咨询系统[J].清华大学学报(自然科学版),2006,46(S 1)：990-995.
[115]. Yates R B, Neto B R. Modern Information Retrieval [M]. Addison-Wesley-Longman, 1999.
[116].苏金树,张博锋,徐昕.基于机器学习的文本分类技术研究进展[J].软件学报,2006,17(9)：1848-1859.
[117].张净,孙志挥,宋余庆,倪巍伟,晏燕华.基于信息论的高维海量数据离群点挖掘[J].计算机科学,2011,38(7)：148-161.
[118].王利民,徐沛娟,李雄飞.基于广义信息论的决策森林多重子模型集成方法[J].模式识别与人工智能,2009,22(2)：325-329.
[119]. Wu X H, Wu B, Sun J. Mixed fuzzy inter-cluster separation clustering algorithm [J]. Applied Mathematical Modelling,2011,35(10):4790-4795.
[120]. Zhang J Y, Peng L Q, Zhao X X. Robust data clustering by learning multi-metric Lq-norm distances [J]. Expert Systems with Applications,2012,39:335-349.
[121]. Nguyen X V, Epps J. minCEntropy:A Novel Information Theoretic Approach for the Generation of Alternative Clusterings [C]. In:Proc. of IEEE International Conference on Data Mining,2010:521-530.
[122]. Hu B G, Wang Y. Evaluation criteria based on mutual information for classifications including rejected class [J]. ActaAutomatica Sinica,2008,34:1396-1403.
[123]. OkanSakar C, Kursun O. A method for combining mutual information and canonical correlation analysis-Predictive Mutual Information and its use in feature selection [J]. Expert Systems with Applications,2012,39:3333-3344.
[124]. Dhillon IS. Information Theoretic Coclustering [C]. In:Proc. of KDD2003,2003.
[125]. Torkkola K. Feature extraction by non-parametric mutual information maximization [J]. Journal of Machine Learning Research,2003,3:1415-1438.
[126]. Senst M, Ascheid G, Luumlders H. Performance Evaluation of the Markov Chain Monte Carlo MIMO Detector based on Mutual Information [C]. In:Proc. of ICC 2010,2010.
[127]. Andritsos P, Miller R J, Tsaparas P. Information-Theoretic Tools for Mining Database Structure from Large Data Sets [C]. In:Proc. of SIGMOD Conference,2004: 731-742.
[128]. Lazebnik S, Raginsky M. Supervised Learning of Quantizer Codebooks by Information Loss Minimization [J]. IEEE Transactions on Pattern Analysis and Machine Intelligence,2009,31:1294-1309.
[129]. Elidan G, Friedman N. Learning Hidden Variable Networks:The Information Bottleneck Approach [J]. Journal of Machine Learning Research,2005,6:81-127.
[130]. Buesing L, Maass W. Simplified Rules and Theoretical Analysis for Information Bottleneck Optimization and PCA with Spiking Neurons [C], In:Proc. of Advances in Neural Information Processing Systems,2007.
[131]. Buesing L, Maass W. A Spiking Neuron as Information Bottleneck [J]. Neural Computation,2010 22(8):1961-1992.
[132]. Deng S H, He Z Y, Xu X F. G-ANMI:A mutual information based genetic clustering algorithm for categorical data [J]. Knowledge-Based Systems,2010,23(21):144-149.
[133]. He Z Y, Xu X F, Deng S H. k-ANMI:A mutual information based clustering algorithm for categorical data. Information Fusion,2008,9(2):223-233.
[134]. Daniel B, Julia C, Yi L. COOLCAT. an entropy-based algorithm for categorical clustering [C]. In Proc. of the eleventh international conference on Information and knowledge management,2002:582-589.
[135]. Blake C L, Merz C J. UCI Repository of Machine Learning Databases [EB].1998. http://www.ics.uci.edu/～mlearn/MLRepository.html.
© 2004-2018 中国地质图书馆版权所有 京ICP备05064691号 京公网安备11010802017129号 地址：北京市海淀区学院路29号 邮编：100083 电话：办公室：(+86 10)66554848；文献借阅、咨询服务、科技查新：66554700 |