Fuzzy support vector machine based on hyperbolas optimized by the quantum-inspired gravitational search algorithm

Fuzzy support vector machines (FSVMs) are known for their excellent antinoise performance, but there is no general rule when the fuzzy membership function (FMF) is set up. A novel FSVM based on hyperbolas optimized by the quantum-inspired gravitational search algorithm (QGSH-FSVM) is proposed to handle this question. In the proposed QGSH-FSVM, the FMF is defined by two disparate hyperbolas, whose eccentricities are optimized by the quantum-inspired gravitational search algorithm. A variable called diversity, revealing the percentage of a sample in different classes, is proposed to distinguish outliers or noises from valid samples. Experimental results confirm that the QGSH-FSVM is able to provide the best solutions to different situations by optimizing its eccentricities. The traditional support vector machine and the FSVM based on affinity or the distance between a sample and its cluster center, however, can only succeed in some particular problems while failing in others.

PDF

___

[1] Vapnik V. The Nature of Statistical Learning Theory. New York, NY, USA: Springer-Verlag, 1995.
[2] Cristianini N, Schawe TJ. An Introduction to Support Vector Machines. Cambridge, UK: Cambridge University Press, 2000.
[3] Zhang XG. Using class-center vectors to build support vector machine. In: Proceedings of the 1999 IEEE signal processing society workshop; 2325 August 1999; Madison, WI, USA. New York, USA: IEEE. pp. 3-11.
[4] Lin CF, Wang SD. Fuzzy support vector machines. IEEE T Neural Network 2002; 13: 464-471.
[5] Li ST, Member IEEE, Chen CC. A regularized monotonic fuzzy support vector machine model for data mining with prior knowledge. IEEE T Fuzzy Syst 2015; 23: 1713-1727.
[6] Huang HP, Liu YH. Fuzzy support vector machines for pattern recognition and data mining. Int J Fuzzy Syst 2002; 4: 826-835.
[7] Chiang JH, Hao PY. A new kernel-based fuzzy clustering approach: support vector clustering with cell growing. IEEE T Fuzzy Syst 2003; 11: 518-527.
[8] Tang J, Shi Y. New method of analog circuit fault diagnosis using fuzzy support vector machine. J Electron Meas Instrum 2009; 6: 7-12.
[9] Zhang GX, Fei L, Du Z, Liu SY. Fuzzy support vector machine based on cluster hyperplane. Computer Engineering and Design 2008; 29: 3177-3178 (in Chinese with an abstract in English).
[10] Wu Q, Liu SY, Du Z. Fuzzy support vector machine method based on border vector extraction. PR & AI 2008; 21: 332-337 (in Chinese with an abstract in English).
[11] Ding SF, Han YZ, Yu JZ. A fast fuzzy support vector machine based on information granulation. Neural Comput Appl 2013; 23: 139-144.
[12] Zhang X, Xiao XL, Xu GY. Fuzzy support vector machine based on affinity among samples. Journal of Software 2006; 17: 951-958 (in Chinese with an abstract in English).
[13] An WJ, Liang MG. Fuzzy support vector machine based on within-class scatter for classification problems with outliers or noises. Neurocomputing 2013; 110: 101-110.
[14] Shigeo A. Fuzzy support vector machines for multi label classification. Pattern Recogn 2015; 48: 2110-2117.
[15] Mohadeseh S, Hossein N, Malihe M. A quantum inspired gravitational search algorithm for numerical function optimization. Inform Sciences 2014; 267: 83-100.
[16] Esmat R, Hossein N, Saeid S. GSA: A gravitational search algorithm. Inform Sciences 2009; 179: 2232-2248.
[17] Bezdek JC, Hathaway RJ. Convergence and theory for fuzzy c-means clustering: counterexamples and repairs. IEEE T Pattern Anal 1987; 17: 873-877.
[18] Krishnapuram R, Keller JM. The possibilistic c-means algorithm: insights and recommendations. IEEE T Fuzzy Syst 1996; 4: 385-393.
[19] Pal NR, Pal K, Keller JM, Bezdek JC. A possibilistic fuzzy c-means clustering algorithm. IEEE T Fuzzy Syst 2005; 13: 517-530.