Attributes regrouping in fuzzy rule based classification systems

In fuzzy rule based classification systems, a high number of predictive attributes leads to an explosion of the number of generated rules and can affect the learning algorithm precision. Thus, the increase of the number of features can degrade the predictive capacity of the fuzzy rule based classification systems. In this article, we propose a supervised learning method by automatic generation of fuzzy classification rules, entitled SIFCO. This method is adapted to the representation and the prediction of high-dimensional pattern classification problems. This characteristic is obtained by studying the attributes regrouping by correlation research among the training set elements. This approach, checked experimentally, guarantees an important reduction of rules number without altering too much good classification rates. Several experiences were carried out on various data in order to compare SIFCO with other rules based learning methods.

[1]  Chih-Ming Chen,et al.  An efficient fuzzy classifier with feature selection based on fuzzy entropy , 2001, IEEE Trans. Syst. Man Cybern. Part B.

[2]  Hisao Ishibuchi,et al.  Selecting fuzzy rules with forgetting in fuzzy classification systems , 1994, Proceedings of 1994 IEEE 3rd International Fuzzy Systems Conference.

[3]  Michel Verleysen,et al.  On the Effects of Dimensionality on Data Analysis with Neural Networks , 2009, IWANN.

[4]  Hisao Ishibuchi,et al.  Fuzzy rule selection by multi-objective genetic local search algorithms and rule evaluation measures in data mining , 2004, Fuzzy Sets Syst..

[5]  Stéphane Lallich,et al.  Maps Ensemble for Semi-Supervised Learning of Large High Dimensional Datasets , 2008, ISMIS.

[6]  Giorgio Valentini,et al.  Ensembles of Learning Machines , 2002, WIRN.

[7]  Sam Kwong,et al.  Combining interpretable fuzzy rule-based classifiers via multi-objective hierarchical evolutionary algorithm , 2011, 2011 IEEE International Conference on Systems, Man, and Cybernetics.

[8]  Sushmita Mitra,et al.  Neuro-fuzzy rule generation: survey in soft computing framework , 2000, IEEE Trans. Neural Networks Learn. Syst..

[9]  Sergey Ablameyko,et al.  Limitations and Future Trends in Neural Computation , 2003 .

[10]  Yoav Freund,et al.  Boosting a weak learning algorithm by majority , 1990, COLT '90.

[11]  Seyed Mostafa Fakhrahmad,et al.  Efficient Fuzzy Rule Generation: A New Approach Using Data Mining Principles and Rule Weighting , 2007, Fourth International Conference on Fuzzy Systems and Knowledge Discovery (FSKD 2007).

[12]  Amel Borgi Ben Bouzid.  Apprentissage supervise par generation de regles : le systeme sucrage , 1999 .

[13]  Ian H. Witten,et al.  Generating Accurate Rule Sets Without Global Optimization , 1998, ICML.

[14]  H. Ishibuchi,et al.  Input selection in fuzzy rule-based classification systems , 1997, Proceedings of 6th International Fuzzy Systems Conference.

[15]  H. Ishibuchi,et al.  Distributed representation of fuzzy rules and its application to pattern classification , 1992 .

[16]  Francisco Herrera,et al.  A Genetic Algorithm for Feature Selection and Granularity Learning in Fuzzy Rule-Based Classification Systems for Highly Imbalanced Data-Sets , 2010, IPMU.

[17]  Pierre Demartines.  Analyse de donnees par reseaux de neurones auto-organises , 1994 .

[18]  Ron Kohavi,et al.  The Power of Decision Tables , 1995, ECML.

[19]  Hisao Ishibuchi,et al.  Analysis of interpretability-accuracy tradeoff of fuzzy systems by multiobjective fuzzy genetics-based machine learning , 2007, Int. J. Approx. Reason..

[20]  Hisao Ishibuchi,et al.  Selecting fuzzy if-then rules for classification problems using genetic algorithms , 1995, IEEE Trans. Fuzzy Syst..

[21]  E. M. Wright,et al.  Adaptive Control Processes: A Guided Tour , 1961, The Mathematical Gazette.

[22]  Hideo Tanaka,et al.  Construction of fuzzy classification systems with rectangular fuzzy rules using genetic algorithms , 1994, CVPR 1994.

[23]  Hisao Ishibuchi,et al.  Efficient fuzzy partition of pattern space for classification problems , 1993 .

[24]  Herman Akdag,et al.  Two Methods of Linear Correlation Search for a Knowledge Based Supervised Classification , 1998, IEA/AIE.

[25]  Stéphane Lallich,et al.  Ensemble prédicteur fondé sur les cartes auto-organisatrices adapté aux données volumineuses , 2007, European Grid Conference.

[26]  Hisao Ishibuchi,et al.  Rule weight specification in fuzzy rule-based classification systems , 2005, IEEE Transactions on Fuzzy Systems.

[27]  William W. Cohen.  Fast Effective Rule Induction , 1995, ICML.

[28]  E. Lughofer,et al.  Evolving fuzzy classifiers using different model architectures , 2008, Fuzzy Sets Syst..

[29]  Ryan M. Rifkin,et al.  In Defense of One-Vs-All Classification , 2004, J. Mach. Learn. Res..

[30]  Leo Breiman,et al.  Bagging Predictors , 1996, Machine Learning.

[31]  Soo-Young Lee,et al.  Extraction of independent discriminant features for data with asymmetric distribution , 2011, Knowledge and Information Systems.

[32]  Robert C. Holte,et al.  Very Simple Classification Rules Perform Well on Most Commonly Used Datasets , 1993, Machine Learning.

[33]  Hisao Ishibuchi,et al.  Simple fuzzy rule-based classification systems perform well on commonly used real-world data sets , 1997, 1997 Annual Meeting of the North American Fuzzy Information Processing Society - NAFIPS (Cat. No.97TH8297).