Influence of clustering pre-processing on genetically generated fuzzy knowledge bases

• Autorzy: Przybylo A. , Achiche S. , Balazinski M. , Baron L.
• Języki publikacji: EN

Abstrakty

EN

Automatic knowledge base generation using techniques such as genetic algorithms tend to be highly dependent on the quality and size of the learning data. First of all, large data sets can lead to unnecessary time loss, when smaller data sets could describe the problem as well. Second of all, the presence of noise and outliers can cause the learning algorithm to degenerate. Clustering techniques allow compressing and filtering the data, thus making the generation of fuzzy knowledge bases faster and more accurate. Different clustering algorithms are compared and the validation of the results through a theoretical 3D surface, shows that when compressing the data to 5% of its original size, clustering algorithms accelerate the learning process by up to 94%. Moreover, when the learning data contains noise and/or a large amount of outliers, clustering algorithms can make the results more stable and improve the fitness of the obtained FKBs.

Słowa kluczowe

EN

genetic algorithms; knowledge base

PL

algorytm genetyczny; baza wiedzy

• Wydawca: Instytut Podstawowych Problemów Techniki PAN
• Czasopismo: Computer Assisted Mechanics and Engineering Sciences
• Rocznik: 2005
• Tom: Vol. 12, No. 2-3
• Strony: 207--221
• Opis fizyczny: Bibliogr. 21 poz., rys., tab., wykr.

Twórcy

autor

Przybylo A.

• École Polytechnique de Montréal, Mechanical Engineering Department, C. P. 6079, Succ. Centre-Ville, Montréal, H3C3A7, Canada

autor

Achiche S.

• École Polytechnique de Montréal, Mechanical Engineering Department, C. P. 6079, Succ. Centre-Ville, Montréal, H3C3A7, Canada

autor

Balazinski M.

• École Polytechnique de Montréal, Mechanical Engineering Department, C. P. 6079, Succ. Centre-Ville, Montréal, H3C3A7, Canada

autor

Baron L.

• École Polytechnique de Montréal, Mechanical Engineering Department, C. P. 6079, Succ. Centre-Ville, Montréal, H3C3A7, Canada

Bibliografia

• [1] S. Achiche, M. Balazinski, L. Baron. Real/binary-like coded genetic algorithm to automatically generate fuzzy knowledge bases. The .4-th International Conference on Control and Automation, June 2003.
• [2] S. Achiche, M. Balazinski, L. Baron. Multi-combinative strategy to avoid premature convergence in genetically-generated fuzzy knowledge Bases. Journal of Theoretical and Applied Mechanics, 42(3): 417-444, 2004.
• [3] M. Balazinski, M. Bellerose, E. Czogala. Application of fuzzy logic techniques to the selection of cutting para-meters in machining processes. International Journal for Fuzzy Sets and Systems, 61: 307-317, 1993.
• [4] L. Baron., S. Achiche, M. Balazinski. Fuzzy decisions system knowledge base generation using a genetic algorithm. International Journal of Approximate Reasoning, pp. 25-148, 2001.
• [5] T. Galiński, J. Harabasz. A dendrite method for cluster analysis. Communications in Statistics, 3: 1-27, 1974.
• [6] K. Deb, A. Pratap, S. Agarwal, T. Meyarivan. A fast and elitist multi-objective genetic algorithm: NSGA-II. IEEE Transactions on Evolutionary Computation, 6: 182-200, 2000.
• [7] D. E. Goldberg. Genetic Algorithms in Search, Optimization and Machine Learning. Addison-Wesley, Massachusetts, 1989.
• [8] J. Han, M. Kambler. Data Mining Concepts and Techniques. Morgan Kaufmann Publishers, 2001.
• [9| H. Hancock. Development of the Minkowski Geometry of Numbers. the Macmillan Company, New York, 1939.
• [10] J.A. Hartigan. Clustering Algorithms. 1975.
• [11] F. Herrera, M. Lozano. Gradual distributed real-coded genetic algorithms. IEEE Transactions on Evolutionary Computation, 4, pp. 43-63, 2000.
• [12] M. De Hoon, S. Imoto, S. Miyano. The C Clustering Library. Human Genome Center, University of Tokyo, 2004.
• [13] L. Kauffman, P.J. Roussewuw. Finding Groups in Data: An Introduction to Cluster Analysis. John Wiley and Sons, 1990.
• [14] M. G. Kendall. Rank Correlation Methods. Griffin, 1962.
• [15] E. L. Lehmann, H. J. M. D'abrera. Nonparametric: Statistical Methods Based on Ranks. Holden-Day, 1975.
• [16] F. G. Lobo, D. E. Goldberg, M. Pelikan. Time complexity of genetic algorithms exponentially scaled problems. GECCO 2000: Proceedings of the Genetic and Evolutionary Computation Conference, pp. 151-158, 2000.
• [17] J. MacQueen. Some methods for classification and analysis of multivariate observations. Proceedings of the Fifth Berkeley Symposium on Mathematical Statistics and Probability, 1: 281-297, 1967.
• [18] K. V. Mardia. J. T. Kent, J. M. Bibby, Multivariate Analysis. Academic Press, London, 1979.
• [19] Z. Michalewicz. Genetic Algorithms + Data Structure = Evolution Programs. Springer, New York, 1992.
• [20] Wikipedia, the Free Encyclopedia. http://www.wikipedia.org/. Consulted on January 27-th 2005.
• [21] L. A. Zadeh. Outline of new approach to the analysis of complex systems and decisions processes. IEEE Transactions of Systems, Man and Cybernetics, 3: 28-44, 1973.