Abstract
This paper proposes a new algorithm for the implementation of Support Vector Machines using Particle Swarm Optimization (PSO), called Intelligently Initialized Particle Swarm Classifier (I2PSC). Initialization of the particles is done close to the optimal solution by using basic concepts of Geometry and Statistics, so that the rate of convergence of the swarm towards the optimal solution is better as compared to a randomly initialized swarm. The fitness function is designed in such a way that the trade-off between the distance between the bounding planes and the number of misclassifications is greatly reduced compared to traditional SVMs.
This is a preview of subscription content, log in via an institution to check access.
Access this chapter
Tax calculation will be finalised at checkout
Purchases are for personal use only
Preview
Unable to display preview. Download preview PDF.
References
Vapnik, V.N.: Statistical learning theory. John Wiley & Sons, New York (1998)
Kennedy, J., Eberhart, R.C.: Particle swarm optimization. In: Proceedings of IEEE International Conference on Neural Networks, Piscataway, NJ, pp. 1942–1948 (1995)
Li, Y.-b., Zhang, N., Li, C.-b.: Support Vector Machine forecasting method by chaotic particle swarm optimization and its application. Journal of South University of Technology volume 13 (2009)
Sivakumari, S., Praveena Priyadarsini, R., Amudha, P.: Performance evaluation of svm kernels using hybrid pso-svm. ICGST-AIML Journal (2009)
Lin, S.-W., Ying, K.-C., Chen, S.-C., Lee, Z.J.: Particle swarm optimization for parameter determination and feature selection of support vector machines. Expert systems with applications 35 (2008)
Kapp, M.N., Sabourin, R., Maupin, P.: Proceedings of the 11th Annual Conference on Genetic and Evolutionary Computation (2009)
Zahiri, S.-H., Seyedin, S.-A.: Swarm Intelligent based classifiers. Journal of Franklin University (2007)
CristiaTrelea, I.: The particle swarm optimization algorithm: convergence analysis and parameter selection. Inf. Process. Lett. 85(6), 317–325 (2003)
Author information
Authors and Affiliations
Editor information
Editors and Affiliations
Rights and permissions
Copyright information
© 2011 Springer-Verlag Berlin Heidelberg
About this paper
Cite this paper
Karadkal, S., Putty, S.N., Manikantan, K. (2011). A Novel Algorithm for the Implementation of PSO-Based SVM. In: Das, V.V., Stephen, J., Chaba, Y. (eds) Computer Networks and Information Technologies. CNC 2011. Communications in Computer and Information Science, vol 142. Springer, Berlin, Heidelberg. https://doi.org/10.1007/978-3-642-19542-6_66
Download citation
DOI: https://doi.org/10.1007/978-3-642-19542-6_66
Publisher Name: Springer, Berlin, Heidelberg
Print ISBN: 978-3-642-19541-9
Online ISBN: 978-3-642-19542-6
eBook Packages: Computer ScienceComputer Science (R0)