Mining classification rules by using genetic algorithms with non-random initial population and uniform operator

KARCI, Ali; GÜNDOĞAN, Korkut Koray; Alatas, Bilal

Mining classification rules by using genetic algorithms with non-random initial population and uniform operator

Korkut Koray GÜNDOĞAN, (Fırat Üniversitesi, Mühendislik Fakültesi, Bilgisayar Mühendisliği Bölümü, Elazığ, Türkiye)

Bilal ALATAŞ, (Girilmedi)

Ali KARCI (Girilmedi)

Turkish Journal of Electrical Engineering and Computer Sciences

4 0

Yıl: 2004 Cilt: 12 Sayı: 1 Sayfa Aralığı: 43 - 52 Metin Dili: İngilizce İndeks Tarihi: 29-07-2022

Mining classification rules by using genetic algorithms with non-random initial population and uniform operator

Öz:

Classification is a supervised learning method that induces a classification model from a database and is one of the most commonly applied data mining task. The frequently employed techniques are decision tree or neural network-based classification algorithms. This work presents an efficient genetic algorithm (GA) for classification rule mining technique that discovers comprehensible IF-THEN rules using a generalized uniform population method and a uniform operator inspired from the uniform population method. Initial population is generated by methodically eliminating the randomness by generalized uniform population method. In the subsequence generations, genetic diversity is ensured and premature convergence is prevented by the uniform operator. From the experimental results, it was observed that, this method handled the problems of GAs in the task of classification and guaranteed to get rid of any local solution and rapidly found comprehensible rules.

Anahtar Kelime:

Konular: Mühendislik, Elektrik ve Elektronik

Belge Türü: Makale Makale Türü: Araştırma Makalesi Erişim Türü: Erişime Açık

References [1] J. Han, M. Kamber, Data Mining: Concepts and Techniques, Morgan Kaufmann Publishers Academic Press, 2001.
[2] X. Wang, B. Chen, G. Qian, and F. Ye. "On the optimization of fuzzy decision trees", Fuzzy Sets and Systems, Vol. 2, pp. 117-125/2000.
[3] Y. Freund, and R.E. Schapire, "Experiments with a new boosting algorithm", in L. Saitta Machine Learning, Proceedings of the Thirteeth International Conference, pp. 148-156, 1996.
[4] Z. Michalewicz, Genetic Algorithms+Data Structures=Evolution Programs, 3th Edition, Springer-Verlag, 1999.
[5] W. Kwedlo, M. Kretowski, "An Evolutionary Algorithm for Cost-Sensitive Decision Rule Learning", European Conference on Machine Learning, ECML'01. Freiburg, Germany. Springer LNCS 2167, 2001.
[6] W. Kwedlo, M. Kretowski, "Learning Decision Rules using a Distributed Evolutionary Algorithm", Proc. of 8th Workshop" Simulation in Research and Development. Gdask, Poland, 2001.
[7] J.L. Alvarez, J. Mata, J.C. Riquelme, "CG03: An oblique classification system using an evolutionary algorithm and C4.5", International Journal of Computer, Systems and Signals, Vol. 2, No. 1, pp. 1 - 15, 2001.
[8] A.A. Freitas, "A Genetic Algorithm for Generalized Rule Induction", Advances in Soft Computing-Engineering Design and Manufacturing, Springer-Verlag, pp. 340-353, 1999.
[9] K.K. Giindogan, B. Alata§, A. Karci, Y. Tatar, "Comprehensible Classification Rule Mining With Two-Level Genetic Algorithm", 2nd FAE International Symposium, TRNC, pp. 373-377, 2002.
[10] B. Alata§, A. Karci, "Genetik Surecin Diizenlilik Operatoriiyle Global Cozume Dogru Harekete Zorlanmasi", ELECO'2002, pp. 364-368, 18-22, Bursa 2002.
[11] A. Karci, A. Arslan, "Uniform population in genetic algorithms" I.U. Journal of Electrical & Electronics, Vol. 2 (2), pp. 495-504, 2002
[12] A. Karci, A. C. mar, "Comparison of Uniform Distributed Initial Population Method and Random Initial Popu¬lation Method in Genetic Search", 15th International Symposium on Computer and Information Sciences, pp. 159-166, Istanbul, Turkey, 2000.
[13] A. Karci, A. Arslan, "Genetik Algoritmalarda Diizenli Populasyon", GAP IV. Miihendislik Kongresi, pp. 601-607, 2002.
[14] G. Demiroz, H.A. Giivenir, N. liter, "Learning differential diagnosis for concept learning", Machine Learning, Vol. 13, pp. 147-165, 1998.
[15] P. Clark, T. Niblett, "Induction in Noisy Domains", Progress in Machine Learning, pp. 11-30, Sigma Press, 1987.

APA	GÜNDOĞAN K, Alatas B, KARCI A (2004). Mining classification rules by using genetic algorithms with non-random initial population and uniform operator. , 43 - 52.
Chicago	GÜNDOĞAN Korkut Koray,Alatas Bilal,KARCI Ali Mining classification rules by using genetic algorithms with non-random initial population and uniform operator. (2004): 43 - 52.
MLA	GÜNDOĞAN Korkut Koray,Alatas Bilal,KARCI Ali Mining classification rules by using genetic algorithms with non-random initial population and uniform operator. , 2004, ss.43 - 52.
AMA	GÜNDOĞAN K,Alatas B,KARCI A Mining classification rules by using genetic algorithms with non-random initial population and uniform operator. . 2004; 43 - 52.
Vancouver	GÜNDOĞAN K,Alatas B,KARCI A Mining classification rules by using genetic algorithms with non-random initial population and uniform operator. . 2004; 43 - 52.
IEEE	GÜNDOĞAN K,Alatas B,KARCI A "Mining classification rules by using genetic algorithms with non-random initial population and uniform operator." , ss.43 - 52, 2004.
ISNAD	GÜNDOĞAN, Korkut Koray vd. "Mining classification rules by using genetic algorithms with non-random initial population and uniform operator". (2004), 43-52.

APA	GÜNDOĞAN K, Alatas B, KARCI A (2004). Mining classification rules by using genetic algorithms with non-random initial population and uniform operator. Turkish Journal of Electrical Engineering and Computer Sciences, 12(1), 43 - 52.
Chicago	GÜNDOĞAN Korkut Koray,Alatas Bilal,KARCI Ali Mining classification rules by using genetic algorithms with non-random initial population and uniform operator. Turkish Journal of Electrical Engineering and Computer Sciences 12, no.1 (2004): 43 - 52.
MLA	GÜNDOĞAN Korkut Koray,Alatas Bilal,KARCI Ali Mining classification rules by using genetic algorithms with non-random initial population and uniform operator. Turkish Journal of Electrical Engineering and Computer Sciences, vol.12, no.1, 2004, ss.43 - 52.
AMA	GÜNDOĞAN K,Alatas B,KARCI A Mining classification rules by using genetic algorithms with non-random initial population and uniform operator. Turkish Journal of Electrical Engineering and Computer Sciences. 2004; 12(1): 43 - 52.
Vancouver	GÜNDOĞAN K,Alatas B,KARCI A Mining classification rules by using genetic algorithms with non-random initial population and uniform operator. Turkish Journal of Electrical Engineering and Computer Sciences. 2004; 12(1): 43 - 52.
IEEE	GÜNDOĞAN K,Alatas B,KARCI A "Mining classification rules by using genetic algorithms with non-random initial population and uniform operator." Turkish Journal of Electrical Engineering and Computer Sciences, 12, ss.43 - 52, 2004.
ISNAD	GÜNDOĞAN, Korkut Koray vd. "Mining classification rules by using genetic algorithms with non-random initial population and uniform operator". Turkish Journal of Electrical Engineering and Computer Sciences 12/1 (2004), 43-52.