Evolutionary Approach to Data Discretization for Rough Sets Theory

• Autorzy: Czerniak J.
• Języki publikacji: EN

Abstrakty

EN

This article presents the LDGen method which is based on genetic algorithm. The author proposed evolutionary approach to the solution of the discretization problem for systems that induce rules on the basis of rough sets theory. The study describes details of the method with special focus on the crossing operator. The proposed approach concerns working with multidimensional samples. Thanks to application of the author's own method of for visualizing multidimensionality, i.e. so called Pipes of Samples, it was possible to visualize up to 360 dimensions, which is usually sufficient in case of problems the Rough Sets Theory deals with. Mutation and crossing methods were developed using this visualisation so that, for real numbers, it allowed to create individuals that describe one solution of the discretization. Hence the population is a set of many complete discretizations of all the attributes.

Słowa kluczowe

EN

discretization; LDGen; rough sets theory; genetic algorithm; Pipe of Samples

• Wydawca: IOS Press
• Czasopismo: Fundamenta Informaticae
• Rocznik: 2009
• Tom: Vol. 92, nr 1-2
• Strony: 43--61
• Opis fizyczny: Bibliogr. 26 poz., tab., wykr.

Twórcy

autor

Czerniak J.

• Systems Research Institute Polish Academy of Sciences ul. Newelska 6, Warszawa, Poland,

Bibliografia

• [1] Chmielewski M. R., Grzymala-Busse J. W.: Global discretization of continuous attributes as preprocessing for machine learning, [In:] Lin T. Y.,Wildberger A. (ed.), Soft Computing: Rough Sets, Fuzzy Logic, Neural Networks, Uncertainty Management, Knowledge Discovery, San Diego, Simulation Councils Inc., 1995, 294-297.
• [2] Brijs T., Vanhoof K.: Cost-sensitive Discretization of Numeric Attributes, in: 2nd European Symposium on Principles of Data Mining and Knowledge Discovery, Nantes, France, 1998.
• [3] Cerquides J., Mantaras R.L.: Proposal and empirical comparison of a parallelizable distance-based discretization method. in: Third International Conference on Knowledge Discovery and Data Mining, 1997, 139-142
• [4] Cios K. J., Pedrycz W., Świniarski R.W.: Data mining methods for knowledge discovery, Dordrecht, Kluwer Academic Publishers, 1999.
• [5] Czerniak J., Zarzycki H.: Application of rough sets in the presumptive diagnosis of urinary system diseases, in: Artificial Intelligence and Security in Computing Systems, Kluwer Academic Publishers, 41-51
• [6] Czerniak J., Zarzycki H.: Application of the LDGen Genetic Algorithm in a Discretization of Numerical Attributes, in: Proc. ACS'2003 10th International Conference, Miedzyzdroje, 189-198
• [7] Czerniak J.: The 'Pipes of Samples' approach as a method to visualization of multidimensionality - general conception, (in Polish), in: Proc. 7th Symposium of Computer Science, Faculty of Computer Science and Information Systems, Szczecin University of Technology, Informa Press, 2002, volume II, 375-381
• [8] Doherty P., Łukaszewicz W., Skowron A., Szaas A.: Knowledge representation techniques : a rough set approach, in: Studies in Fuzziness and Soft Computing, Vol. 202, Springer, 2006
• [9] Dougherty J., Kohavi R., Sahami M.: Supervised and unsupervised discretizations of continuous features, in: Proc. 12th Int. Conf. on Machine Learning, Morgan Kaufmann, 1995, 194-202.
• [10] Everitt B., Landau S., Leese M.: Cluster Analysis, 4th Edition, Arnold Publishers, London, 2001
• [11] Fayyad U., Irani K.: Multi-interval discretization of continuous-valued attributes for classification learning. in: Proc. Thirteenth International Joint Conference on Artificial Intelligence, San Mateo, CA: Morgan Kaufmann, 1993, 1022-1027
• [12] Fayyad U., Irani K.: On the handling of continuous-valued attributes in decision tree generation, in: Machine Learning, 1992, 87-102
• [13] Grzymala-Busse J. W., Stefanowski J.: Three approaches to numerical attribute discretization for rule induction, in: International Journal of Intelligent Systems, vol. 16 no. 1, 2001, 29-38
• [14] Holte R. C.: Very simple classification rules perform well on most commonly used datasets, in: Machine Learning, 1993, 63-90
• [15] Kerber R.: Chimerge: Discretization of numeric attributes, in: Proc. AAAI-92, Ninth National Confrerence Articial Intelligence, AAAI Press/The MIT Press, 1992, 123-128
• [16] Kohavi R., Sahami M.: Error-based and entropy-based discretization of continuos features, in: Proc. of the 2nd Int. Conf. on Knowledge Discovery and Data Mining, Portland, 1996, 114-119
• [17] Liu H., Setiono R.: Feature selection and discretization, in: IEEE Transactios on Knowledge and Data Engineering, 1997, 1-4
• [18] Nguyen H. S., Skowron A.: Quantization of Real Values Attributes, Rough set and Boolean Reasoning Approaches, in: Proc. of the Second Joint Conference on Information Sciences, Wrightsville Beach, NC, 1995, 34-37
• [19] Nguyen H. S.: Discretization of real value attributes. Boolean reasoning approach. Ph.D. Thesis, University of Warsaw, Warszawa 1997
• [20] Polkowski L.: Rough Sets, Mathematical Foundations, Physica-Verlag, Heidelberg, 2002
• [21] Rakus-Andersson, E.: Fuzzy and rough techniques in medical diagnosis and medication, in: Studies in Fuzziness and Soft Computing, Vol 212, Springer, 2007
• [22] Stefanowski J.: Algorithms of rule induction for knowledge discovery. (In Polish), Habilitation Thesis published as Series Rozprawy no. 361, Poznan Univeristy of Technology Press, Poznan 2001.
• [23] Stefanowski J., Nowaczyk S.: An Experimental Study of Using Rule Induction Algorithm in Combiner Multiple Classifier, in: International Journal of Computational Intelligence Research, Vol.3, No.4, 2007, 335-342
• [24] Susmaga R.: Analyzing discretization of continuous attributes given a monotonic discrimination function, in: Journal Intelligent Data Analysis, Vol. 1, No. 3, 1997, 157-179
• [25] Wróblewski J.: Finding minimal reducts using genetic algorithm, in: Proc. of Second Joint Annual Conference on Information Sciences, Wrightsville Beach, North Carolina, 28 September-1 October, USA, 1995, 186-189
• [26] Yanushkevich S., Shmerko V., Lu D. C., Adams K., McGregor J.: Spectra of Boolean Functions: Computation of Reed-Muller, in: Arithmetic and Walsh Spectrum via Taylor Expansion, IEEE Trans. Computers, 2004