A PSO and pattern search based memetic algorithm for SVMs parameters optimization

被引:157
作者
Bao, Yukun [1 ]
Hu, Zhongyi [1 ]
Xiong, Tao [1 ]
机构
[1] Huazhong Univ Sci & Technol, Sch Management, Dept Management Sci & Informat Syst, Wuhan 430074, Peoples R China
关键词
Parameters optimization; Support vector machines; Memetic algorithms; Particle swarm optimization; Pattern search; SUPPORT VECTOR MACHINES; MODEL SELECTION;
D O I
10.1016/j.neucom.2013.01.027
中图分类号
TP18 [人工智能理论];
学科分类号
081104 ; 0812 ; 0835 ; 1405 ;
摘要
Addressing the issue of SVMs parameters optimization, this study proposes an efficient memetic algorithm based on particle swarm optimization algorithm (PSO) and pattern search (PS). In the proposed memetic algorithm, PSO is responsible for exploration of the search space and the detection of the potential regions with optimum solutions, while pattern search (PS) is used to produce an effective exploitation on the potential regions obtained by PSO. Moreover, a novel probabilistic selection strategy is proposed to select the appropriate individuals among the current population to undergo local refinement, keeping a well balance between exploration and exploitation. Experimental results confirm that the local refinement with PS and our proposed selection strategy are effective, and finally demonstrate the effectiveness and robustness of the proposed PSO-PS based MA for SVMs parameters optimization. (C) 2013 Elsevier B.V. All rights reserved.
引用
收藏
页码:98 / 106
页数:9
相关论文
共 40 条
[1]   Optimizing resources in model selection for support vector machine [J].
Adankon, Mathias M. ;
Cheriet, Mohamed .
PATTERN RECOGNITION, 2007, 40 (03) :953-963
[2]   Model selection for the LS-SVM. Application to handwriting recognition [J].
Adankon, Mathias M. ;
Cheriet, Mohamed .
PATTERN RECOGNITION, 2009, 42 (12) :3264-3270
[3]   Effective Memetic Algorithms for VLSI design = genetic algorithms plus local search plus multi-level clustering [J].
Areibi, S ;
Yang, Z .
EVOLUTIONARY COMPUTATION, 2004, 12 (03) :327-353
[4]   Automatic model selection for the optimization of SVM kernels [J].
Ayat, NE ;
Cheriet, M ;
Suen, CY .
PATTERN RECOGNITION, 2005, 38 (10) :1733-1745
[5]  
Chang C.-C., LIBSVM: a Library for Support Vector Machines
[6]   Choosing multiple parameters for support vector machines [J].
Chapelle, O ;
Vapnik, V ;
Bousquet, O ;
Mukherjee, S .
MACHINE LEARNING, 2002, 46 (1-3) :131-159
[7]   A Multi-Facet Survey on Memetic Computation [J].
Chen, Xianshun ;
Ong, Yew-Soon ;
Lim, Meng-Hiot ;
Tan, Kay Chen .
IEEE TRANSACTIONS ON EVOLUTIONARY COMPUTATION, 2011, 15 (05) :591-607
[8]  
Cherkassky V, 1997, IEEE Trans Neural Netw, V8, P1564, DOI 10.1109/TNN.1997.641482
[9]   Radius margin bounds for support vector machines with the RBF kernel [J].
Chung, KM ;
Kao, WC ;
Sun, CL ;
Wang, LL ;
Lin, CJ .
NEURAL COMPUTATION, 2003, 15 (11) :2643-2681
[10]   On the local convergence of pattern search [J].
Dolan, ED ;
Lewis, RM ;
Torczon, V .
SIAM JOURNAL ON OPTIMIZATION, 2003, 14 (02) :567-583