A CBPSOGSA-SVM hybrid system for classification

The feature subset selection and parameter optimization influence the classification accuracy of support vector machines (SVM) significantly. In order to solve the problems and improve the performance of SVM for classification, a new proposed chaos-optimized binary version of PSOGSA which is the hybrid of particle swarm optimization (PSO) and gravitational search algorithm (GSA), termed CBPSOGSA, is developed in this paper to build a novel hybrid system (CBPSOGSA-SVM) for classification. In this system, features and SVM parameters are encoded together to form the binary code strings and the feature subset and SVM parameters are optimized simultaneously. A proper fitness function is also designed to convert this multi-objective optimization problem to be single objective, meanwhile, evaluate the binary code strings produced by CBPSOGSA. Eight standard datasets are employed in experiments to validate the performance of the proposed CBPSOGSA-SVM hybrid system for classification. The binary version of both PSO and PSOGSA are also used to do comparisons. The results of experiments demonstrate that the proposed CBPSOGSA-SVM hybrid system for classification is effective and has better performance and stronger capability of searching for the global best solutions.

[1]  Cheng-Lung Huang,et al.  A distributed PSO-SVM hybrid system with feature selection and parameter optimization , 2008, Appl. Soft Comput..

[2]  Surjya K. Pal,et al.  Tool condition monitoring by SVM classification of machined surface images in turning , 2015, The International Journal of Advanced Manufacturing Technology.

[3]  Hossein Nezamabadi-pour,et al.  GSA: A Gravitational Search Algorithm , 2009, Inf. Sci..

[4]  Yue-Shi Lee,et al.  Robust and efficient multiclass SVM models for phrase pattern recognition , 2008, Pattern Recognit..

[5]  Xiaoming Chang,et al.  A chaotic digital secure communication based on a modified gravitational search algorithm filter , 2012, Inf. Sci..

[6]  Bo Liu,et al.  Improved particle swarm optimization combined with chaos , 2005 .

[7]  T. Joachims.  Support Vector Machines , 2002 .

[8]  Guangyi Chen,et al.  Pattern recognition with SVM and dual-tree complex wavelets , 2007, Image Vis. Comput..

[9]  Leandro dos Santos Coelho,et al.  Use of chaotic sequences in a biologically inspired algorithm for engineering design optimization , 2008, Expert Syst. Appl..

[10]  Joseph Picone,et al.  Applications of support vector machines to speech recognition , 2004, IEEE Transactions on Signal Processing.

[11]  Zhiwei Ye,et al.  Remote sensing image classification based on the optimal support vector machine and modified binary coded ant colony optimization algorithm , 2017, Inf. Sci..

[12]  Rajdeep Chatterjee,et al.  EEG Based Motor Imagery Classification Using SVM and MLP , 2016, 2016 2nd International Conference on Computational Intelligence and Networks (CINE).

[13]  Corinna Cortes,et al.  Support-Vector Networks , 1995, Machine Learning.

[14]  Chih-Jen Lin,et al.  LIBSVM: A library for support vector machines , 2011, TIST.

[15]  Marie Chupin,et al.  Spatial and anatomical regularization of SVM for brain image analysis , 2010, NIPS.

[16]  Takuya Maekawa,et al.  Toothbrushing Performance Evaluation Using Smartphone Audio Based on Hybrid HMM-recognition/SVM-regression Model , 2016, J. Inf. Process..

[17]  Leandro dos Santos Coelho,et al.  Binary optimization using hybrid particle swarm optimization and gravitational search algorithm , 2014, Neural Computing and Applications.

[18]  Shen Yin,et al.  Tuning kernel parameters for SVM based on expected square distance ratio , 2016, Inf. Sci..

[19]  Juan Wang,et al.  Chaos-enhanced Cuckoo search optimization algorithms for global optimization , 2016 .

[20]  Yaonan Wang,et al.  Hybrid chaos optimization algorithm with artificial emotion , 2012, Appl. Math. Comput..

[21]  Razvan Andonie,et al.  Incremental and Decremental SVM for Regression , 2016, Int. J. Comput. Commun. Control.

[22]  A. Ebrahimzadeh,et al.  Application of the PSO-SVM model for recognition of control chart patterns. , 2010, ISA transactions.

[23]  Guoqiang Peter Zhang,et al.  Neural networks for classification: a survey , 2000, IEEE Trans. Syst. Man Cybern. Part C.

[24]  Chih-Jen Lin,et al.  Asymptotic Behaviors of Support Vector Machines with Gaussian Kernel , 2003, Neural Computation.

[25]  S. Mirjalili,et al.  A new hybrid PSOGSA algorithm for function optimization , 2010, 2010 International Conference on Computer and Information Application.

[26]  Cheng-Lung Huang,et al.  A GA-based feature selection and parameters optimizationfor support vector machines , 2006, Expert Syst. Appl..

[27]  Zhiqiang Li,et al.  Wi-Fi Fingerprinting using SVM Classification and Regression , 2016, Ad Hoc Sens. Wirel. Networks.

[28]  Thorsten Joachims,et al.  Learning to classify text using support vector machines - methods, theory and algorithms , 2002, The Kluwer international series in engineering and computer science.

[29]  Chih-Jen Lin,et al.  A comparison of methods for multiclass support vector machines , 2002, IEEE Trans. Neural Networks.