模糊分类模型的研究
|
摘要
模糊分类是模糊集合理论的一个重要应用。模糊分类规则被广泛认为是分类知识较好的表示,与人类表达的知识类似,具有可读性和解释性。模糊分类在图像处理、文字识别、语音识别、文本分类、遥感、气象及工业自动化控制等许多领域得到广泛应用。
模糊划分和模糊分类规则的自动产生,分类规则的表达式,分类规则的调整及分类识别率的提高是模糊分类模型研究的关键问题。为了研究这些问题,这篇论文提出了三种模糊分类模型和一种多分类器集成方法,从不同的角度,利用不同的方法和技术,探索解决上述问题的思路和方法。
模型Ⅰ:基于模糊核超球感知器的模糊分类模型(简称FCMBFKP)。首先这种模型选择适当的核函数,将训练模式从输入空间映射到高维特征空间。在特征空间中,利用提出的模糊核超球感知器学习算法,对每一类训练模式找一个超球。这个超球将覆盖该类别的所有训练模式。将每个超球,看作为一个模糊划分,并为之建立一条IF-THEN分类规则。以超球中心和半径为参数,定义超圆锥体的隶属函数。考虑到各超球之间有交迭区域的可能,以超球半径作为规则的调整参数,提出了调整策略和算法。用权威的机器学习数据库中的数据集对模型的性能进行了实验评测,并与核超球感知器(KHP)和SVM方法进行比较,验证了模型的有效性。
模型Ⅱ:基于进化式核聚类的模糊分类模型(简称FCMBEKC)。首先,这种模型也是选用适当的核函数,将训练模式从输入空间映射到高维特征空间。在高维特征空间,利用提出的进化式核聚类算法,对每一类训练模式进行聚类,得到多个超球。然后,将每个超球看成一簇,每一簇就对应一个模糊划分。每个模糊划分产生一条模糊IF-THEN规则。以每簇的中心作为参数,定义超椭圆体的隶属函数。考虑到不同类别的簇之间可能存在交迭区域,提出了基于遗传算法的,并以簇的半径作为调整参数的规则调整方法。定义了适应度函数和介绍了规则调整算法。采用权威的机器学习数据库中的数据集,对模型的性能进行了实验评测,并与神经网络(ANN)和多层感知器(MLP)方法进行比较,验证了模型的有效性。
模型Ⅲ:基于支持向量机的模糊分类模型(简称FCMBSVM)。这种模型的基本思想是分类模型构建初期,以每个训练模式为中心,进行模糊划分,即,每个训练模式,对应一个模糊划分。每个模糊划分,建立一条模糊IF-THEN分类规则。选用适当的隶属函数,构造核函数。用支持向量机的学习方法,求出
Fuzzy classification is an important application of fuzzy set theory.Fuzzy classification rules are widely considered a well-suited representation of classification knowledge. Since they resemble the way which humans would possibly formulate their knowledge,they are readable and interpretable. Fuzzy classification has been widely applied in many fields, such as image processing, words recognition, voice recognition, text classification, remote sensing, weather and industry automation.The key problems of the model research on fuzzy classification are the automatic generation of fuzzy partitions and fuzzy classification rules, the expression of fuzzy rules, the optimization tuning of classification rules and the improvement of classification recognition rate.To study above problems, three fuzzy classification models and a method of classifier ensemble are proposed with different views, different methods and techniques in this paper.Model I: Fuzzy classification model basing fuzzy kernel hyperball perceptron (FCMBFKP). In this model, firstly the patterns in the initial input space are mapped to high dimensional feature space by selecting a suitable kernel function.In the feature space, the hyperball which covers all training patterns of a class is founded for every class by the algorithm of fuzzy kernel hyperball perceptron. a hyperball is regarded as a fuzzy partition and a IF-THEN rule is created for a fuzzy partition.A hyper-cone membership function is defined with regarding the center and radius of the hyperball as parameters.Considering the possibility of overlapping areas among hyperballs, the policy and algorithm of tuning the rules are proposed with regarding the radius of the hyperball as tuning parameter. Experiments with the data sets of standard machine leaning database evaluate the performances of this model with comprison of experiment results of the methods of kernel hyperball perceptron (KHP) and SVM.Model II: Fuzzy classification model basing evolving kernel clustering (FCMBEKC). Similar to the model I, firstly the patterns in the initial input space are mapped to high dimensional feature space by selecting a suitable kernel function. In feature space, Training patterns of every class are clustered by the proposed evolving kernel clustering algorithm.For each class, multiple hyperballs are got and a hyperball is regarded as a cluster which relates to a fuzzy partition. An IF-THEN
模糊划分和模糊分类规则的自动产生,分类规则的表达式,分类规则的调整及分类识别率的提高是模糊分类模型研究的关键问题。为了研究这些问题,这篇论文提出了三种模糊分类模型和一种多分类器集成方法,从不同的角度,利用不同的方法和技术,探索解决上述问题的思路和方法。
模型Ⅰ:基于模糊核超球感知器的模糊分类模型(简称FCMBFKP)。首先这种模型选择适当的核函数,将训练模式从输入空间映射到高维特征空间。在特征空间中,利用提出的模糊核超球感知器学习算法,对每一类训练模式找一个超球。这个超球将覆盖该类别的所有训练模式。将每个超球,看作为一个模糊划分,并为之建立一条IF-THEN分类规则。以超球中心和半径为参数,定义超圆锥体的隶属函数。考虑到各超球之间有交迭区域的可能,以超球半径作为规则的调整参数,提出了调整策略和算法。用权威的机器学习数据库中的数据集对模型的性能进行了实验评测,并与核超球感知器(KHP)和SVM方法进行比较,验证了模型的有效性。
模型Ⅱ:基于进化式核聚类的模糊分类模型(简称FCMBEKC)。首先,这种模型也是选用适当的核函数,将训练模式从输入空间映射到高维特征空间。在高维特征空间,利用提出的进化式核聚类算法,对每一类训练模式进行聚类,得到多个超球。然后,将每个超球看成一簇,每一簇就对应一个模糊划分。每个模糊划分产生一条模糊IF-THEN规则。以每簇的中心作为参数,定义超椭圆体的隶属函数。考虑到不同类别的簇之间可能存在交迭区域,提出了基于遗传算法的,并以簇的半径作为调整参数的规则调整方法。定义了适应度函数和介绍了规则调整算法。采用权威的机器学习数据库中的数据集,对模型的性能进行了实验评测,并与神经网络(ANN)和多层感知器(MLP)方法进行比较,验证了模型的有效性。
模型Ⅲ:基于支持向量机的模糊分类模型(简称FCMBSVM)。这种模型的基本思想是分类模型构建初期,以每个训练模式为中心,进行模糊划分,即,每个训练模式,对应一个模糊划分。每个模糊划分,建立一条模糊IF-THEN分类规则。选用适当的隶属函数,构造核函数。用支持向量机的学习方法,求出
Fuzzy classification is an important application of fuzzy set theory.Fuzzy classification rules are widely considered a well-suited representation of classification knowledge. Since they resemble the way which humans would possibly formulate their knowledge,they are readable and interpretable. Fuzzy classification has been widely applied in many fields, such as image processing, words recognition, voice recognition, text classification, remote sensing, weather and industry automation.The key problems of the model research on fuzzy classification are the automatic generation of fuzzy partitions and fuzzy classification rules, the expression of fuzzy rules, the optimization tuning of classification rules and the improvement of classification recognition rate.To study above problems, three fuzzy classification models and a method of classifier ensemble are proposed with different views, different methods and techniques in this paper.Model I: Fuzzy classification model basing fuzzy kernel hyperball perceptron (FCMBFKP). In this model, firstly the patterns in the initial input space are mapped to high dimensional feature space by selecting a suitable kernel function.In the feature space, the hyperball which covers all training patterns of a class is founded for every class by the algorithm of fuzzy kernel hyperball perceptron. a hyperball is regarded as a fuzzy partition and a IF-THEN rule is created for a fuzzy partition.A hyper-cone membership function is defined with regarding the center and radius of the hyperball as parameters.Considering the possibility of overlapping areas among hyperballs, the policy and algorithm of tuning the rules are proposed with regarding the radius of the hyperball as tuning parameter. Experiments with the data sets of standard machine leaning database evaluate the performances of this model with comprison of experiment results of the methods of kernel hyperball perceptron (KHP) and SVM.Model II: Fuzzy classification model basing evolving kernel clustering (FCMBEKC). Similar to the model I, firstly the patterns in the initial input space are mapped to high dimensional feature space by selecting a suitable kernel function. In feature space, Training patterns of every class are clustered by the proposed evolving kernel clustering algorithm.For each class, multiple hyperballs are got and a hyperball is regarded as a cluster which relates to a fuzzy partition. An IF-THEN
引文
[1] L.A. Zadeh.Fuzzy sets[J]. Information and Control, 1965,8:338-353.
[2] Zadeh L A.Fuzzy Logic[J].IEEE Computer, 1998, 21(4):83-91.
[3] Richard O.Duda, Peter E.Hart, David G.Stork.Pattern Classification,Second Edition [M].Beijing:China Machine Press,2004.2:192-195
[4] D.Nauck,R.Kruse.A neuro-fuzzy method to learn fuzzy classification rules from data[J].Fuzzy Sets and Systems, 1997,89:277-288.
[5] F.Uebele.A neural network-based fuzzy classifier[J].IEEE Trans.Syst, Man, Cybern, 1995,25:353-361.
[6 S.Horikawa, T.Furuhashi,Y. Uchikawa.On Fuzzy Modeling Using Fuzzy Neural Networks with the Back-Propagation Algorithm. IEEE TSnns[J]. Neural Networks, 1992,3(5):801-806.
[7] H.Ishibuchi,K.Nozaki,N.Yamamoto,H.Tanaka.Construction of fuzzy classification systems with rectangular fuzzy rules using genetic algorithms[J].Fuzzy Sets and Systems, 1994,65:237-253.
[8] H.Ishibuchi,K.Nozaki,N.Yamamoto, H.Tanaka.Seclecting fuzzy if-then rules for classification problems using genetic algorithms[J].IEEE Transactions on Fuzzy Systems, 1995,3(3):260-270.
[9] M.Russo.FuGeNeSys-a fuzzy genetic neural system for fuzzy modeling[J].IEEE Transactions on Fuzzy Systems, 1998,6(3):373-388.
[10] Shinn-Ying Ho,Chia-Cheng Liu,Soundy Liu.Design of an optimal nearest neighbor classifier using an intelligent genetic algorithm[J].Pattern Recognition Letters,2002,23 (13):1495-1503.
[11] T.Murata, H.Ishibuchi,M.Gen.Adjusting Fuzzy Partitions by Genetic Algorithms and Histograms for Pattern Classification Problems[C].The 5th IEEE International Conference on Evolutionary Computation.New York:IEEE Press, 1998:9-14.
[12] H.Ishibuchi, T.Murata,B.Turksen.Single-objective and two-objective genetic algorithm for selecting linguistic rules for pattern classification problems[J]. Fuzzy Sets and Systems,1997,89(2):135-150.
[13] B.Carse,T.C.Fogart,,A.Munro.Evolving fuzzy rule based controllers using genetic algorithms[J]. Fuzzy Sets and System, 1996,80:273-293.
[14] H.Ishibuchi,T.Murata.A genetic-algorithm-based fuzzy partition method for pattern classification problems[J].Genetic Algorithm and Soft Computing, 1996, 1(8):555-578.
[15] H.Ishibuchi, K.Nozaki,N.Yamamoto,H.Tanaka.Selecting fuzzy if-then rules for classification problems using genetic algorithms[J].IEEE Trans.On Fuzzy System, 1995,3:260-270
[16] C.L.Karr and E.J.Gentry.Fuzzy control of pH using genetic algorithms[J]. IEEE Trans on Fuzzy System, 1993,1:46-53.
[17] K.Kamei.An Application of Fuzzy Clustering to Controller Design[J]. J. Japan Society for Fuzzy Theory and Syst,1996,8(3):448-455.
[18] M.Ryoke, H.Tamara,Y.Nakamori.Fuzzy Rule Generation by Hyperellipsoidal Clustering[C].Methodologies for the Conception, Design and Application of intelligent.System.New Jersey:World Scientific, 1996: 86-89
[19] L.Junco,L.Sanchez.Using the adaboost algorithm to induce fuzzy rotes in classification problems[C].In Proc. Spanish Conference for Fuzzy Logic and Technologies, 2000:297-301.
[20] H.-M.Lee,C.-M. ChenJ.-M.Chen, Y.-L.Jou.An Efficient Fuzzy Classifier with Feature Selection Based on Fuzzy Entropy[J]. IEEE Trans. Syst., MAN,Cybern. B, 2001,31(3): 426-432.
[21] J.Yen.Fuzzy logic-a modern perspective[J]. IEEE Trans. Knowledge and Data Engineering, 1999,11:153-165.
[22] H. Ishibuchi,T.Nakashima,T.Murata.hree-objective genetics-based machine learning for linguistic rule extraction[J].Information Sciences, 2001, 136(1-4): 109-133.
[23] H. Ishibuchi and T.Yamamoto.Fuzzy rule selection by data mining criteria and genetic algorithms[C]. in Proc.Genetic and Evolutionary Computation Conference (GECCO-2002), 2002:399-406.
[24] J.Casillas,O.Cordon,M.J.Del Jesus, F.Herrera.Genetic feature selection in a fuzzy rule-based classification system learning process for high-dimensional problems [J]. Information Science, 2001,136:135-157.
[25] R.Thawonmas and S.Abe.A novel approach to feature selection based on analysis of class regions[J].IEEE Trans. Systems, Man, and Cybernetics, 1997, 27 (2):196 -207
[26] D.P.Mandal.Partitioning of feature space for pattern classification[J]. Pattern Recognition, 1997,30(12): 1971 -1990.
[27] H.Roubos,M.Setnes.Compact and transparent fuzzy models and classifiers through iterative complexity reduction[J]. IEEE Trans. Fuzzy Systems, 2001,9(4):516-524.
[28] S.Medasani, J. Kim, R.Krishnapuram.An overview of membership function generation techniques for pattern recognition[J]. Int. J. Approx.Reasoning, 1998, 19(3-4):391-417.
[29] S.-Y.Ho, H.-M.Chen, S.-J.Ho,T.-K.Chen.Design of accurate classifiers with a compact fuzzy-rule base using an evolutionary scatter partition of feature space[J]. IEEE TRANSACTIONS ON SYSTEMS, MAN, AND CYBERNETICS -PART B,2003,43(2):1031-1044.
[30] A. Homaifar and E. McCormick.Simultaneous design of membership functions and rule sets for fuzzy controllers using genetic algorithms[J].IEEE Trans. Fuzzy Syst., 1995,3:129-139.
[31] H. Ishibuchi and T.Nakashima.Effect of rule weights in fuzzy rule-based classification systems[J].IEEE Trans. Fuzzy Syst.,2001, 9:506-515.
[32] J.A.Dickerson and B.KoskoFuzzy Function Approximation with Ellipsoid Rules[J].IEEE Trans. Syst.,Man,Cybern.-B, 1996,26(4):542-560.
[33] P. K. Simpson.Fuzzy Min-Max Neural NetworksPart 1: Classification[T].IEEE Trans. Neural Networks,1992,3(5):776-786,.
[34] K.Shirnojima,T.FuKuda,Y.Hasegawa.RBF-Fuzzy System with GA Based Unsupervised/Supervised Learning Method[C].Proc. 4th IEEE Int. Conf. Fuzzy Systems.New York: IEEE ,1995:253-258.
[35] Hiroyuki INOUE.Automatic Generation of Fuzzy Rules Using Hyper Elliptic cone Membership Functions by Genetic Algorithms[J].J.Intelligent and Fuzzy systems, 1998, 6(1):65-81.
[36] S. Abe.Fast Training of a Fuzzy Classifier with Pyramidal Membership Functions [C].Proc. SCI '99/ISAS ',1999:487-492.
[37] S. Abe,M.-S.Lan.A Method for Fuzzy Rules Extraction Directly from Numerical Data and Its Application to Pattern Classification[J].IEEE Trans.Fuzzy Systems, 1995,3(1):18-28.
[38] F. Uebele, S. Abe, M. -S. Lan.A Neural Network-Based Fuzzy Classifier[J].IEEE Trans. Systems,Man, and Cybernetics, 1999,25(2):353-361.
[39] S. Abe.Dynamic Cluster Generation for a Fuzzy Classifier with Ellipsoidal Regions[J].IEEE Trans. Systems,Man, and Cybernetics-Part B,1998, 28(6): 869-876.
[40] S. Abe.Feature selection by analyzing class regions approximated by ellipsoids[J]. IEEE Trans. Syst, Man, Cybern.C, 1998,28:282-287.
[41] Ludmila I. Kuncheva: How good are fuzzy If-Then classifiers?[J] IEEE Transactions on Systems, Man, and Cybernetics,2000,30(4): 501-509.
[42] O. Cordon, M.J. del Jesus, and F. Herrera. A proposal on reasoning methods in fuzzy rule-based classification systems[J].Int. J. of Approximate Reasoning, 1999,20(l):21-45.
[43] F. Klawon and P.E. Klement. Mathematical analysis of fuzzy classifiers[J].Lecture Notes in Computer Science, 1997,1280:359-370.
[44] B. von Schmidt and F. Klawonn.Fuzzy max-min classifiers decide locally on the basis of two attributes[J]. Mathware & Soft Computing, 1999,6:91-108.
[45] H. Roubos and M. Setnes.Compact and transparent fuzzy models and classifiers through iterative complexity reduction[J]. IEEE Trans. Fuzzy Syst, 2001, 9: 516-524.
[46] L.Castillo, A.Gonzalez, R.Perez.Including a simplicity criterion in the selection of the best rule in a genetic fuzzy learning algorithm[J].Fuzzy Sets Syst., 2001, 120(2): 309-321.
[47] S. Abe and R. Thawonmas.A fuzzy classifier with ellipsoidal regions[J].IEEE Trans. Fuzzy Syst.,1997,5:358-368.
[48] V. Uebele, S.Abe,M.-S. Lan,Aneural-network-based fuzzy classifier[J].IEEE Trans. Syst., Man, Cybern., 1995,25:353-361.
[49] C. Z. Janikow.A genetic algorithm for optimizing fuzzy decision trees[J]. Information Sciences, 1996,89(3-4):275-296.
[50] H.Ishibuchi et al.Construction of fuzzy classification systems with rectangular fuzzy rules using genetic algorithms[J]. Fuzzy Sets Syst, 1994, 65(2):237-253.
[51] K.Nozaki et al.A simple but powerful heuristic method for generating fuzzy rules from numerical data[J].Fuzzy Sets Syst,1997,86(3):251-270.
[52] Ishibuchi.H,Nozaki.K,Tanaka.H.Distributed representation of fuzzy rules and its application to pattern classification[J].Fuzzy Sets and Syst. 1992,52:21-32.
[53] Ishibuchi.H,Nozaki.K,Tanaka.H. Efficient fuzzy partition of pattern space for classification problems[J].Fuzzy Sets and Syst. 1993,59:295-304.
[54] Hisao Ishibuchi,Ken Nozaki,Hideo Tanaka.Selecting Fuzzy If-Then Rules for Classification Problems Using Genetic Algorithms[J].IEEE Trans. On Fuzzy Systems, 1995,3(3):260-270.
[55] Chii-Maw Uang,Sheng-Li Lin,C.F.Jiang.Fuzzy-based IRA model[C].SPIE-The International Society for Optical Engineering, SPIE Press, 2001,4459: 203-209.
[56] Fu Guoyao.Optimization methods for fuzzy clustering[J].Fuzzy Sets and System s,1998,93:301-309.
[57] M. G. Genton.Classes of Kernels for Machine Learning: A Statistics Perspective [J]. Journal of Machine Learning Research, 2001,2:299-312
[58] V. Vapnik.The Nature of Statistical Learning Theory[M]. New York: Springer- Verlag, 1995.
[59] V. Vapnik.Statistical Learning Theory[M]. New York: John Wiley &Sons Inc., 1998.
[60] Burges,C.J.C.A tutorial on support vector machines for pattern recognition[J].Data Mining and Knowledge Discovery, 1998,2(2):1-47.
[61] Scholkopf, B.Mika, S.Burges, C.Knirsch, P.Miiller, K.-R.RltSCh, Smola.A.Input space vs. feature space in kernel-based methods[J]. IEEE Transactions on Neural Networks, 1999,10(5):1000-1017.
[62] N.Cristianini,J.Shawe-Taylor.An Introduction to Support Vector Machines and Other Kernel-Based Learning Methods[M].Cambridge: Cambridge University Press, 2000.
[63] MikaS,RatschG,Weston Jetal.Fisherdiscriminant analysis with kernels[C].Neural Networks for Signal Processing.NewYork:IEEE Press, 1999:41-48
[64] Jianhua XU, Xuegong ZHANG, Yanda LI. Kernel Neuron and its Training Algorithm[C]. Proc. of 8th Intl Conf on Neural Information Processing. 2001:861-866.
[65] F.L.Chung, Wang Shitong, Deng Zhaohong, Hu Dewen.Fuzzy kernel hyperball perceptron[J]. Applied Soft Computing,2004,5(l):67-74
[66] Jiun-Hung Chen,Chu-Song Chen. Fuzzy Kernel Perceptron[J]. IEEE TRANSACTIONS ON NEURAL NETWORKS, 2002,13(6):1364-1373
[67] J. M. Keller D.J.Hunt.Incorporating fuzzy membership functions into the perceptron algorithm[J]. IEEE Trans. Pattern Anal. Machine Intell.,1985,PAMI-7: 693-699.
[68] Blake, C.L.Merz, C.J. UCI Repository of machine learning databases[EB/OL] http://www.ics.uci.edu/~mlearn/MLRepository.html,1998.
[69] G. Ratsch,T.Onoda,K.-R.Muller.Soft margins for AdaBoost[J]. Machine Learning Machine Leaming,2001,42(3): 287-320.
[70] Kearns.M,Ron.C.Algorithmicstabilityandsanity-checkboundsforleave-one-outcros svalidation[C].In:ProclOthConfer-enceonComputationalLearningTheory.NewYor k:ACM Press, 1997:152-162
[71] D.Tax,R.Duin.Support vector domain description[J].Pattern Recognition Letters, 1999,20:1191-1199.
[72] A.Ben-Hur,D.Horn, H.T.Siegelmann.V.Vapnik.A kernel clustering method [C].15th International Conference on Pattern Recognition (ICPR), 2000:728-731,.
[73] A.Ben-Hur,D.Horn,H.T.Siegelmann,V.Vapnik.Support vector clustering[J]. Journal of Machine Learning Research,2001,2:125-137.
[74] A.Ben-Hur,D.Horn,H.T.Siegelmann,V.Vapnik.A support vector method for clustering [J].Advances in Neural Information Processing Systems,2001,13:367-373.
[75] D.GLuenberger.linear and nonlinear programming.Addison-Wesley Pub.,Massachusets, 1984
[76] Hng.L,Inoue.H.Automatic generation of fuzzy classification systems using hyper-cone membership function[C].Computational Intelligence in Robotics and Automation, 2003 IEEE International Symposium.New York:IEEE Press,2003: 658-663.
[77] Kaieda.K,Abe,S.A.kernel fuzzy classifier with ellipsoidal regions[C].Neural Networks,2003. Proceedings of the International Joint Conference on, New York:IEEEpress,2003,3:2043-2048,2003.
[78] Yang Ai-Min,Chen Yi,Hu Yun-Fa.A Method of Generating Fuzzy Classification Rules with Ellipsoidal Regions[C].Proceeding of 2004 International Conference on Machine Learning and Cybernetics.New York:IEEE Press,2004:1778-1783
[79] Takuya Inoue, Shigeo Abe. Fuzzy Support Vector Machines for Pattern Classification[C]. Neural Networks, 2001. Proceedings. IJCNN '01. International Joint Conference.New York: IEEE.2001,2:1449-1454.
[80] Shigeo Abe,Takuya Inoue.Fuzzy Support Vector Machines for Multiclass ProbIems[C].ESANN'2002 proceedings-European Symposium on Artificial Neural Networks. Bruges, 2002,2:113-118.
[81] Chun-Fu Lin,Sheng-De Wang.Fuzzy Support Vector Machines[J].IEEE TRANSACTIONS ON NEURAL NETWORK, 2002,13(2):464- 471.
[82] Han-Pang Huang,Yi-Hung Liu.Fuzzy Support Vector Machines for Pattern Recognition Data Mining[J].International Journal of Fuzzy Systems,2002,4: 826 -835.
[83] Qing He,Xi-Zhao Wang, Hong-Jie Xing.A Fuzzy Classification Method Based On Support Vector Machine[R].Proceedings of the Second International Conference on Machine Learning and Cybernetics.New York:IEEE Press,2003:1237-1240.
[83] Weston,C Watkins.Multi-class Support Vector machines[R]. London:Department of Computer Science,Royal Holloway University of, England, 1998.
[84] A. J. Smola, B. SchAolkopf, K.-R. MAuller.The Connection Between Regularization Operators and Support Vector Kernels[J]. Neural Networks, 1998,11(4): 637-649.
[85] Singh, S. Neural Learning of Spiral Structures[C]. Proc. International Conference on Advances in Pattern Recognition (ICAPR'98).New York:Springer, 1998:226 -231.
[86] Nadal.C, Legault.R,Suen.C.Y.Complementary algorithms for recognition of totally unconstrained handwritten numerals[C].Proc 10th Int.Conf. Pattern Recogrnition.New York:IEEE,1990 :434- 449
[87] Kittler J.Improving Recognition Rates by Classifier Combination: A Theortical Framework[C] .In: Downtown AC, Impedovos(eds), Progress in Handwriting Recognition. New York:World Scientific, 1997:231-248
[88] Ali.K.M,Pazzani.M.J.On the link between error correlation and error reduction in decision tree ensembles(Technical report 95-38, ICS-UCI)[R].California: Department of Information and Computer Science,University of California, 1995
[89] Ahmed Al-Ani,Mohamed Deriche.A New Technique for Combining Multiple Classifiers using The Dempster-Shafer Theory of Evidence[J].Journal of Artificial Intelligence Research,2002,17:333-361
[90] Rahman A.F.R, Fairhurst M.C.Serial combination of multiple experts:a unifed Valuation[J].Pattern Analysis&Application,1999,2:292-311
[91] Xu.Lei et al. Methods of Combining Multiple Classifiers and Their Application to Handwriting Recognition[J]. IEEE Trans on System, Man And Cybernetics 1992, 22:418-435
[92] L.Xu, A.Krzyzak ,C.Y. Suen.Methods for Combining Multiple Classifiers and their Applications to Handwriting Recognition[J].IEEE Trans.on Systems, Man, and Cybernetics, 1992,22:418-435
[93] J.Kittler,M. Hatef, R. P.W. Duin, Jiri Matas.On Combining Classifiers[J], IEEE Transactions on Pattern Analysis and Machine Intelligence, 1998, 20(3):226-239
[94] M. P. Perrone ,L. N. Cooper.When networks disagree: ensemble methods for hybrid neural networks, In R.J. Mammone (Ed.), Artificial Neural Networks for Speech and Vision. London: Chanman&Hall, 1993:126-142.
[95] T. Denoeux.A Neural Network Classifier Based on Dempster-Shafer Theory[J]. IEEE Transaction on System, Man, and Cybernetics, 2000,30(2):131-150
[96] E. Mandler,J.Schuerrmann.Combining the classification results of independent classifiers based on the Dempster/Shafer theory of evidences[C].Pattern Recognition and Artificial Intelligence, Gelsema and Kanal, Eds.New York:Elsevier Secience, 1988,381 -393
[97] Y.S.Huang, K.Liu,C.Y. Suen.The Combination of Multiple Classifiers by a Neural Network Approach[J].Journal of Pattern Recognition and Artificial Intelligence, 1995, 9:579-597.
[98] Wierzechon.S.T.On fuzzy measure and fuzzy integral[C]. Fuzzy information and decision processes, New York: North-Holland, 1982,78-86
[99] Schapire R E.The strength of weak learn ability[J].Machine Learning, 1990, 5(2): 197 -227.
[100] Breiman L.Bagging predictors[J].Machine Learning, 1996,24(2):123-140.
[101] Freund Y.Boosting a weak algorithm by majority[J].Information and Computation, 1995,121(2):256-285
[102] Freund Y,Schapire R E.A decision-theoretic generalization of on-linelearning and an application to boosting[J].Journal of Computer and System Sciences,1997,55(l): 119-139.
[103] Efron B,Tibshirani R.An Introduction to the Bootstrap/New York:Chapman&Hall, 1993.
[104] Hampshire J,Waibel A.A novel objective function for improved phoneme recognition using time-delay neural networks[J].IEEE Trans Neural Networks, 1990,1(2):216-228
[105] Maclin R,Shavlik J W.Combining the predictions of multiple classifiers:Using competitive learning to initialize neuralnet works[C].In:Proc the 14th
[2] Zadeh L A.Fuzzy Logic[J].IEEE Computer, 1998, 21(4):83-91.
[3] Richard O.Duda, Peter E.Hart, David G.Stork.Pattern Classification,Second Edition [M].Beijing:China Machine Press,2004.2:192-195
[4] D.Nauck,R.Kruse.A neuro-fuzzy method to learn fuzzy classification rules from data[J].Fuzzy Sets and Systems, 1997,89:277-288.
[5] F.Uebele.A neural network-based fuzzy classifier[J].IEEE Trans.Syst, Man, Cybern, 1995,25:353-361.
[6 S.Horikawa, T.Furuhashi,Y. Uchikawa.On Fuzzy Modeling Using Fuzzy Neural Networks with the Back-Propagation Algorithm. IEEE TSnns[J]. Neural Networks, 1992,3(5):801-806.
[7] H.Ishibuchi,K.Nozaki,N.Yamamoto,H.Tanaka.Construction of fuzzy classification systems with rectangular fuzzy rules using genetic algorithms[J].Fuzzy Sets and Systems, 1994,65:237-253.
[8] H.Ishibuchi,K.Nozaki,N.Yamamoto, H.Tanaka.Seclecting fuzzy if-then rules for classification problems using genetic algorithms[J].IEEE Transactions on Fuzzy Systems, 1995,3(3):260-270.
[9] M.Russo.FuGeNeSys-a fuzzy genetic neural system for fuzzy modeling[J].IEEE Transactions on Fuzzy Systems, 1998,6(3):373-388.
[10] Shinn-Ying Ho,Chia-Cheng Liu,Soundy Liu.Design of an optimal nearest neighbor classifier using an intelligent genetic algorithm[J].Pattern Recognition Letters,2002,23 (13):1495-1503.
[11] T.Murata, H.Ishibuchi,M.Gen.Adjusting Fuzzy Partitions by Genetic Algorithms and Histograms for Pattern Classification Problems[C].The 5th IEEE International Conference on Evolutionary Computation.New York:IEEE Press, 1998:9-14.
[12] H.Ishibuchi, T.Murata,B.Turksen.Single-objective and two-objective genetic algorithm for selecting linguistic rules for pattern classification problems[J]. Fuzzy Sets and Systems,1997,89(2):135-150.
[13] B.Carse,T.C.Fogart,,A.Munro.Evolving fuzzy rule based controllers using genetic algorithms[J]. Fuzzy Sets and System, 1996,80:273-293.
[14] H.Ishibuchi,T.Murata.A genetic-algorithm-based fuzzy partition method for pattern classification problems[J].Genetic Algorithm and Soft Computing, 1996, 1(8):555-578.
[15] H.Ishibuchi, K.Nozaki,N.Yamamoto,H.Tanaka.Selecting fuzzy if-then rules for classification problems using genetic algorithms[J].IEEE Trans.On Fuzzy System, 1995,3:260-270
[16] C.L.Karr and E.J.Gentry.Fuzzy control of pH using genetic algorithms[J]. IEEE Trans on Fuzzy System, 1993,1:46-53.
[17] K.Kamei.An Application of Fuzzy Clustering to Controller Design[J]. J. Japan Society for Fuzzy Theory and Syst,1996,8(3):448-455.
[18] M.Ryoke, H.Tamara,Y.Nakamori.Fuzzy Rule Generation by Hyperellipsoidal Clustering[C].Methodologies for the Conception, Design and Application of intelligent.System.New Jersey:World Scientific, 1996: 86-89
[19] L.Junco,L.Sanchez.Using the adaboost algorithm to induce fuzzy rotes in classification problems[C].In Proc. Spanish Conference for Fuzzy Logic and Technologies, 2000:297-301.
[20] H.-M.Lee,C.-M. ChenJ.-M.Chen, Y.-L.Jou.An Efficient Fuzzy Classifier with Feature Selection Based on Fuzzy Entropy[J]. IEEE Trans. Syst., MAN,Cybern. B, 2001,31(3): 426-432.
[21] J.Yen.Fuzzy logic-a modern perspective[J]. IEEE Trans. Knowledge and Data Engineering, 1999,11:153-165.
[22] H. Ishibuchi,T.Nakashima,T.Murata.hree-objective genetics-based machine learning for linguistic rule extraction[J].Information Sciences, 2001, 136(1-4): 109-133.
[23] H. Ishibuchi and T.Yamamoto.Fuzzy rule selection by data mining criteria and genetic algorithms[C]. in Proc.Genetic and Evolutionary Computation Conference (GECCO-2002), 2002:399-406.
[24] J.Casillas,O.Cordon,M.J.Del Jesus, F.Herrera.Genetic feature selection in a fuzzy rule-based classification system learning process for high-dimensional problems [J]. Information Science, 2001,136:135-157.
[25] R.Thawonmas and S.Abe.A novel approach to feature selection based on analysis of class regions[J].IEEE Trans. Systems, Man, and Cybernetics, 1997, 27 (2):196 -207
[26] D.P.Mandal.Partitioning of feature space for pattern classification[J]. Pattern Recognition, 1997,30(12): 1971 -1990.
[27] H.Roubos,M.Setnes.Compact and transparent fuzzy models and classifiers through iterative complexity reduction[J]. IEEE Trans. Fuzzy Systems, 2001,9(4):516-524.
[28] S.Medasani, J. Kim, R.Krishnapuram.An overview of membership function generation techniques for pattern recognition[J]. Int. J. Approx.Reasoning, 1998, 19(3-4):391-417.
[29] S.-Y.Ho, H.-M.Chen, S.-J.Ho,T.-K.Chen.Design of accurate classifiers with a compact fuzzy-rule base using an evolutionary scatter partition of feature space[J]. IEEE TRANSACTIONS ON SYSTEMS, MAN, AND CYBERNETICS -PART B,2003,43(2):1031-1044.
[30] A. Homaifar and E. McCormick.Simultaneous design of membership functions and rule sets for fuzzy controllers using genetic algorithms[J].IEEE Trans. Fuzzy Syst., 1995,3:129-139.
[31] H. Ishibuchi and T.Nakashima.Effect of rule weights in fuzzy rule-based classification systems[J].IEEE Trans. Fuzzy Syst.,2001, 9:506-515.
[32] J.A.Dickerson and B.KoskoFuzzy Function Approximation with Ellipsoid Rules[J].IEEE Trans. Syst.,Man,Cybern.-B, 1996,26(4):542-560.
[33] P. K. Simpson.Fuzzy Min-Max Neural NetworksPart 1: Classification[T].IEEE Trans. Neural Networks,1992,3(5):776-786,.
[34] K.Shirnojima,T.FuKuda,Y.Hasegawa.RBF-Fuzzy System with GA Based Unsupervised/Supervised Learning Method[C].Proc. 4th IEEE Int. Conf. Fuzzy Systems.New York: IEEE ,1995:253-258.
[35] Hiroyuki INOUE.Automatic Generation of Fuzzy Rules Using Hyper Elliptic cone Membership Functions by Genetic Algorithms[J].J.Intelligent and Fuzzy systems, 1998, 6(1):65-81.
[36] S. Abe.Fast Training of a Fuzzy Classifier with Pyramidal Membership Functions [C].Proc. SCI '99/ISAS ',1999:487-492.
[37] S. Abe,M.-S.Lan.A Method for Fuzzy Rules Extraction Directly from Numerical Data and Its Application to Pattern Classification[J].IEEE Trans.Fuzzy Systems, 1995,3(1):18-28.
[38] F. Uebele, S. Abe, M. -S. Lan.A Neural Network-Based Fuzzy Classifier[J].IEEE Trans. Systems,Man, and Cybernetics, 1999,25(2):353-361.
[39] S. Abe.Dynamic Cluster Generation for a Fuzzy Classifier with Ellipsoidal Regions[J].IEEE Trans. Systems,Man, and Cybernetics-Part B,1998, 28(6): 869-876.
[40] S. Abe.Feature selection by analyzing class regions approximated by ellipsoids[J]. IEEE Trans. Syst, Man, Cybern.C, 1998,28:282-287.
[41] Ludmila I. Kuncheva: How good are fuzzy If-Then classifiers?[J] IEEE Transactions on Systems, Man, and Cybernetics,2000,30(4): 501-509.
[42] O. Cordon, M.J. del Jesus, and F. Herrera. A proposal on reasoning methods in fuzzy rule-based classification systems[J].Int. J. of Approximate Reasoning, 1999,20(l):21-45.
[43] F. Klawon and P.E. Klement. Mathematical analysis of fuzzy classifiers[J].Lecture Notes in Computer Science, 1997,1280:359-370.
[44] B. von Schmidt and F. Klawonn.Fuzzy max-min classifiers decide locally on the basis of two attributes[J]. Mathware & Soft Computing, 1999,6:91-108.
[45] H. Roubos and M. Setnes.Compact and transparent fuzzy models and classifiers through iterative complexity reduction[J]. IEEE Trans. Fuzzy Syst, 2001, 9: 516-524.
[46] L.Castillo, A.Gonzalez, R.Perez.Including a simplicity criterion in the selection of the best rule in a genetic fuzzy learning algorithm[J].Fuzzy Sets Syst., 2001, 120(2): 309-321.
[47] S. Abe and R. Thawonmas.A fuzzy classifier with ellipsoidal regions[J].IEEE Trans. Fuzzy Syst.,1997,5:358-368.
[48] V. Uebele, S.Abe,M.-S. Lan,Aneural-network-based fuzzy classifier[J].IEEE Trans. Syst., Man, Cybern., 1995,25:353-361.
[49] C. Z. Janikow.A genetic algorithm for optimizing fuzzy decision trees[J]. Information Sciences, 1996,89(3-4):275-296.
[50] H.Ishibuchi et al.Construction of fuzzy classification systems with rectangular fuzzy rules using genetic algorithms[J]. Fuzzy Sets Syst, 1994, 65(2):237-253.
[51] K.Nozaki et al.A simple but powerful heuristic method for generating fuzzy rules from numerical data[J].Fuzzy Sets Syst,1997,86(3):251-270.
[52] Ishibuchi.H,Nozaki.K,Tanaka.H.Distributed representation of fuzzy rules and its application to pattern classification[J].Fuzzy Sets and Syst. 1992,52:21-32.
[53] Ishibuchi.H,Nozaki.K,Tanaka.H. Efficient fuzzy partition of pattern space for classification problems[J].Fuzzy Sets and Syst. 1993,59:295-304.
[54] Hisao Ishibuchi,Ken Nozaki,Hideo Tanaka.Selecting Fuzzy If-Then Rules for Classification Problems Using Genetic Algorithms[J].IEEE Trans. On Fuzzy Systems, 1995,3(3):260-270.
[55] Chii-Maw Uang,Sheng-Li Lin,C.F.Jiang.Fuzzy-based IRA model[C].SPIE-The International Society for Optical Engineering, SPIE Press, 2001,4459: 203-209.
[56] Fu Guoyao.Optimization methods for fuzzy clustering[J].Fuzzy Sets and System s,1998,93:301-309.
[57] M. G. Genton.Classes of Kernels for Machine Learning: A Statistics Perspective [J]. Journal of Machine Learning Research, 2001,2:299-312
[58] V. Vapnik.The Nature of Statistical Learning Theory[M]. New York: Springer- Verlag, 1995.
[59] V. Vapnik.Statistical Learning Theory[M]. New York: John Wiley &Sons Inc., 1998.
[60] Burges,C.J.C.A tutorial on support vector machines for pattern recognition[J].Data Mining and Knowledge Discovery, 1998,2(2):1-47.
[61] Scholkopf, B.Mika, S.Burges, C.Knirsch, P.Miiller, K.-R.RltSCh, Smola.A.Input space vs. feature space in kernel-based methods[J]. IEEE Transactions on Neural Networks, 1999,10(5):1000-1017.
[62] N.Cristianini,J.Shawe-Taylor.An Introduction to Support Vector Machines and Other Kernel-Based Learning Methods[M].Cambridge: Cambridge University Press, 2000.
[63] MikaS,RatschG,Weston Jetal.Fisherdiscriminant analysis with kernels[C].Neural Networks for Signal Processing.NewYork:IEEE Press, 1999:41-48
[64] Jianhua XU, Xuegong ZHANG, Yanda LI. Kernel Neuron and its Training Algorithm[C]. Proc. of 8th Intl Conf on Neural Information Processing. 2001:861-866.
[65] F.L.Chung, Wang Shitong, Deng Zhaohong, Hu Dewen.Fuzzy kernel hyperball perceptron[J]. Applied Soft Computing,2004,5(l):67-74
[66] Jiun-Hung Chen,Chu-Song Chen. Fuzzy Kernel Perceptron[J]. IEEE TRANSACTIONS ON NEURAL NETWORKS, 2002,13(6):1364-1373
[67] J. M. Keller D.J.Hunt.Incorporating fuzzy membership functions into the perceptron algorithm[J]. IEEE Trans. Pattern Anal. Machine Intell.,1985,PAMI-7: 693-699.
[68] Blake, C.L.Merz, C.J. UCI Repository of machine learning databases[EB/OL] http://www.ics.uci.edu/~mlearn/MLRepository.html,1998.
[69] G. Ratsch,T.Onoda,K.-R.Muller.Soft margins for AdaBoost[J]. Machine Learning Machine Leaming,2001,42(3): 287-320.
[70] Kearns.M,Ron.C.Algorithmicstabilityandsanity-checkboundsforleave-one-outcros svalidation[C].In:ProclOthConfer-enceonComputationalLearningTheory.NewYor k:ACM Press, 1997:152-162
[71] D.Tax,R.Duin.Support vector domain description[J].Pattern Recognition Letters, 1999,20:1191-1199.
[72] A.Ben-Hur,D.Horn, H.T.Siegelmann.V.Vapnik.A kernel clustering method [C].15th International Conference on Pattern Recognition (ICPR), 2000:728-731,.
[73] A.Ben-Hur,D.Horn,H.T.Siegelmann,V.Vapnik.Support vector clustering[J]. Journal of Machine Learning Research,2001,2:125-137.
[74] A.Ben-Hur,D.Horn,H.T.Siegelmann,V.Vapnik.A support vector method for clustering [J].Advances in Neural Information Processing Systems,2001,13:367-373.
[75] D.GLuenberger.linear and nonlinear programming.Addison-Wesley Pub.,Massachusets, 1984
[76] Hng.L,Inoue.H.Automatic generation of fuzzy classification systems using hyper-cone membership function[C].Computational Intelligence in Robotics and Automation, 2003 IEEE International Symposium.New York:IEEE Press,2003: 658-663.
[77] Kaieda.K,Abe,S.A.kernel fuzzy classifier with ellipsoidal regions[C].Neural Networks,2003. Proceedings of the International Joint Conference on, New York:IEEEpress,2003,3:2043-2048,2003.
[78] Yang Ai-Min,Chen Yi,Hu Yun-Fa.A Method of Generating Fuzzy Classification Rules with Ellipsoidal Regions[C].Proceeding of 2004 International Conference on Machine Learning and Cybernetics.New York:IEEE Press,2004:1778-1783
[79] Takuya Inoue, Shigeo Abe. Fuzzy Support Vector Machines for Pattern Classification[C]. Neural Networks, 2001. Proceedings. IJCNN '01. International Joint Conference.New York: IEEE.2001,2:1449-1454.
[80] Shigeo Abe,Takuya Inoue.Fuzzy Support Vector Machines for Multiclass ProbIems[C].ESANN'2002 proceedings-European Symposium on Artificial Neural Networks. Bruges, 2002,2:113-118.
[81] Chun-Fu Lin,Sheng-De Wang.Fuzzy Support Vector Machines[J].IEEE TRANSACTIONS ON NEURAL NETWORK, 2002,13(2):464- 471.
[82] Han-Pang Huang,Yi-Hung Liu.Fuzzy Support Vector Machines for Pattern Recognition Data Mining[J].International Journal of Fuzzy Systems,2002,4: 826 -835.
[83] Qing He,Xi-Zhao Wang, Hong-Jie Xing.A Fuzzy Classification Method Based On Support Vector Machine[R].Proceedings of the Second International Conference on Machine Learning and Cybernetics.New York:IEEE Press,2003:1237-1240.
[83] Weston,C Watkins.Multi-class Support Vector machines[R]. London:Department of Computer Science,Royal Holloway University of, England, 1998.
[84] A. J. Smola, B. SchAolkopf, K.-R. MAuller.The Connection Between Regularization Operators and Support Vector Kernels[J]. Neural Networks, 1998,11(4): 637-649.
[85] Singh, S. Neural Learning of Spiral Structures[C]. Proc. International Conference on Advances in Pattern Recognition (ICAPR'98).New York:Springer, 1998:226 -231.
[86] Nadal.C, Legault.R,Suen.C.Y.Complementary algorithms for recognition of totally unconstrained handwritten numerals[C].Proc 10th Int.Conf. Pattern Recogrnition.New York:IEEE,1990 :434- 449
[87] Kittler J.Improving Recognition Rates by Classifier Combination: A Theortical Framework[C] .In: Downtown AC, Impedovos(eds), Progress in Handwriting Recognition. New York:World Scientific, 1997:231-248
[88] Ali.K.M,Pazzani.M.J.On the link between error correlation and error reduction in decision tree ensembles(Technical report 95-38, ICS-UCI)[R].California: Department of Information and Computer Science,University of California, 1995
[89] Ahmed Al-Ani,Mohamed Deriche.A New Technique for Combining Multiple Classifiers using The Dempster-Shafer Theory of Evidence[J].Journal of Artificial Intelligence Research,2002,17:333-361
[90] Rahman A.F.R, Fairhurst M.C.Serial combination of multiple experts:a unifed Valuation[J].Pattern Analysis&Application,1999,2:292-311
[91] Xu.Lei et al. Methods of Combining Multiple Classifiers and Their Application to Handwriting Recognition[J]. IEEE Trans on System, Man And Cybernetics 1992, 22:418-435
[92] L.Xu, A.Krzyzak ,C.Y. Suen.Methods for Combining Multiple Classifiers and their Applications to Handwriting Recognition[J].IEEE Trans.on Systems, Man, and Cybernetics, 1992,22:418-435
[93] J.Kittler,M. Hatef, R. P.W. Duin, Jiri Matas.On Combining Classifiers[J], IEEE Transactions on Pattern Analysis and Machine Intelligence, 1998, 20(3):226-239
[94] M. P. Perrone ,L. N. Cooper.When networks disagree: ensemble methods for hybrid neural networks, In R.J. Mammone (Ed.), Artificial Neural Networks for Speech and Vision. London: Chanman&Hall, 1993:126-142.
[95] T. Denoeux.A Neural Network Classifier Based on Dempster-Shafer Theory[J]. IEEE Transaction on System, Man, and Cybernetics, 2000,30(2):131-150
[96] E. Mandler,J.Schuerrmann.Combining the classification results of independent classifiers based on the Dempster/Shafer theory of evidences[C].Pattern Recognition and Artificial Intelligence, Gelsema and Kanal, Eds.New York:Elsevier Secience, 1988,381 -393
[97] Y.S.Huang, K.Liu,C.Y. Suen.The Combination of Multiple Classifiers by a Neural Network Approach[J].Journal of Pattern Recognition and Artificial Intelligence, 1995, 9:579-597.
[98] Wierzechon.S.T.On fuzzy measure and fuzzy integral[C]. Fuzzy information and decision processes, New York: North-Holland, 1982,78-86
[99] Schapire R E.The strength of weak learn ability[J].Machine Learning, 1990, 5(2): 197 -227.
[100] Breiman L.Bagging predictors[J].Machine Learning, 1996,24(2):123-140.
[101] Freund Y.Boosting a weak algorithm by majority[J].Information and Computation, 1995,121(2):256-285
[102] Freund Y,Schapire R E.A decision-theoretic generalization of on-linelearning and an application to boosting[J].Journal of Computer and System Sciences,1997,55(l): 119-139.
[103] Efron B,Tibshirani R.An Introduction to the Bootstrap/New York:Chapman&Hall, 1993.
[104] Hampshire J,Waibel A.A novel objective function for improved phoneme recognition using time-delay neural networks[J].IEEE Trans Neural Networks, 1990,1(2):216-228
[105] Maclin R,Shavlik J W.Combining the predictions of multiple classifiers:Using competitive learning to initialize neuralnet works[C].In:Proc the 14th
© 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 |