Use of Gaussian-Euclidean Hybrid Function Based Artificial Immune System for Breast Cancer Diagnosis

Authors: Cuneyt Yucelbas, Seral Ozsen, Sule Yucelbas, Gulay Tezel

Abstract:

Due to the fact that there exist only a small number of complex systems in artificial immune system (AIS) that work out nonlinear problems, nonlinear AIS approaches, among the well-known solution techniques, need to be developed. Gaussian function is usually used as similarity estimation in classification problems and pattern recognition. In this study, diagnosis of breast cancer, the second type of the most widespread cancer in women, was performed with different distance calculation functions that euclidean, gaussian and gaussian-euclidean hybrid function in the clonal selection model of classical AIS on Wisconsin Breast Cancer Dataset (WBCD), which was taken from the University of California, Irvine Machine-Learning Repository. We used 3-fold cross validation method to train and test the dataset. According to the results, the maximum test classification accuracy was reported as 97.35% by using of gaussian-euclidean hybrid function for fold-3. Also, mean of test classification accuracies for all of functions were obtained as 94.78%, 94.45% and 95.31% with use of euclidean, gaussian and gaussian-euclidean, respectively. With these results, gaussian-euclidean hybrid function seems to be a potential distance calculation method, and it may be considered as an alternative distance calculation method for hard nonlinear classification problems.

Keywords: Artificial Immune System, Breast Cancer Diagnosis, Euclidean Function, Gaussian Function.

Digital Object Identifier (DOI): doi.org/10.5281/zenodo.1092481

References:

[1] X.L. Du, C.R. Key, C. Osborne, J.D. Mahnken and J.S. Goodwin, "Discrepancy between Consensus Recommendations and Actual Community Use of Adjuvant Chemotherapy in Women with Breast Cancer," Annals of Internal Medicine, vol. 138, 2003, pp. 90-97.
[2] Wikipedia, Breast Cancer. Available at: http://en.wikipedia.org/wiki/ Breast_cancer, (last accessed: 25 December 2013).
[3] P. Kemal, S. Seral, K. Halife and G. Salih, "Breast cancer and liver disorders classification using artificial immune recognition system (AIRS) with performance evaluation by fuzzy resource allocation mechanism," Expert Systems with Applications, vol. 32, 2007, pp. 172–183.
[4] O. Seral, G. Salih, K. Sadık and L. Fatma, "Use of Kernel Functions in Artificial Immune Systems for the Nonlinear Classification Problems," IEEE Transactions On Information Technology In Biomedicine, vol. 13, no. 4, July 2009, p. 621.
[5] J.H. Carter, "The immune system as a model for pattern recognition and classification,” J. Amer. Med. Inf. Assoc., vol. 7, no. 1, 2000, pp. 28–41.
[6] W.-D. Sun, Z. Tang, H. Tamura, and M. Ishii, "A hierarchical artificial immune architecture and its applications,” in Proc. SICE Annu. Conf., Fukui, Japan, 2003, pp. 3265–3270.
[7] D. Dasgupta, S. Yu, and N. S. Majumdar, "MILA-multilevel immune learning algorithm,” (Lecture Notes in Computer Science) in Proc. GECCO 2003, vol. 2723, 2003, pp. 183–194.
[8] P. Bentley, J. Greensmith, and S. Ujjin, "Two ways to grow tissue for artificial immune systems,” (Lecture Notes in Computer Science) in Proc. ICARIS 2005, vol. 3627, 2005, pp. 139–152.
[9] J.R. Quinlan, "Improved use of continuous attributes in C4.5," Journal of Artificial Intelligence Research, vol. 4, 1996, pp. 77-90.
[10] H.J. Hamilton, N. Shan and N. Cercone, "RIAC: A Rule Induction Algorithm Based on Approximate Classification," Tech. Rep. CS 96-06, Regina University, 1996.
[11] D. Nauck, and R. Kruse, "Obtaining Interpretable Fuzzy Classification Rules From Medical Data," Artificial Intelligence in Medicine, vol. 16, 1999, pp. 149-169.
[12] E.D. Goodman, C.L. Boggess and A. Watkins, "Artificial Immune System Classification of Multiple-Class Problems, In Intelligent Engineering Systems through Artificial Neural Networks: Smart Engineering System Design: Neural Networks, Fuzzy Logic, Evolutionary Programming," Complex Systems and Artificial Life, vol. 12, 2002, pp. 179-184.
[13] I. Salama, M. B. Abdelhalim, and Z.M.A. Gouda, "Experimental Comparison of Classifiers for Breast Cancer Diagnosis," Seventh International Conference on Compute Engineering & Systems (ICCES), 21-29 Nov. 2012, pp. 180-185.
[14] C.L. Blake and C.J. Merz, UJI Repository of Machine Learning Databases, Available at: "ftp://ftp.ics.uci.edu/pub/machine-learning-databases" (last accessed: 7 April 2010).
[15] O.F. Nasaroui, F. Gonzalez and D. Dasgupta, "The Fuzzy Artificial Immune System: Motivation, Basic Concepts, and Application to Clustering and Web Profiling," International Joint Conference on Fuzzy Systems, 2002, pp. 711-717.
[16] S. Şahan, H. Kodaz, S. Güneş and K. Polat, "A New Classifier Based on Attribute Weighted Artificial Immune System," Lecture Notes in Computer Science (LNSC 3280), 2004, pp. 11-20.
[17] L.N. De Castro and J. Timmis, Artificial Immune Systems: A New Computational Intelligence Approach, Springer-Verlag Press, 2002.
[18] Wikipedia, Normal distrubition. Available at: "http://en.wikipedia.org/wiki/Normal_distribution" (last accessed: 25 December 2013).