Abstract
The paper addresses the problem of a radial basis function network initialization with feature section. Main idea of the proposed approach is to achieve the reduction of data dimensionality through feature selection carried-out independently in each hidden unit of the RBFN. To select features we use the so called cluster-dependent feature selection technique. In this paper three different algorithms for determining unique subset of features for each hidden unit are considered. These are RELIEF, Random Forest and Random-based Ensembles. The processes of feature selection and learning are carried-out by program agents working within a specially designed framework which is also described in the paper. The approach is validated experimentally. Classification results of the RBFN with cluster-dependent feature selection are compared with results obtained using RBFNs implementations with some other types of feature selection methods, over several UCI datasets.
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
Asuncion, A., Newman, D.J.: UCI Machine Learning Repository. Irvine, CA: University of California, School of Information and Computer Science (2007). http://www.ics.uci.edu/~mlearn/MLRepository.html (accessed June 24, 2009)
Barbucha, D., Czarnowski, I., Jędrzejowicz, P., Ratajczak-Ropel, E., Wierzbowska, I.: e-JABAT - an Implementation of the web-based a-team. In: Nguyen, N.T., Jain, I.C. (eds.) Intelligent Agents in the Evolution of Web and Applications. Studies in Computational Intelligence, vol. 167, pp. 57–86. Springer, Heidelberg (2009)
Bezdek, J.C., Kuncheva, L.I.: Nearest Prototype Classifier Design: An Experimental Study. International Journal of Intelligence Systems 16(2), 1445–1473 (2000)
Botsch, M., Nossek, J.A.: Construction of interpretable radial basis function classifier based on the random forest kernel. In: Proceedings of IEEE World Congress on Computational Intelligence, IEEE International Joint Conference on Neural Network, Hong Kong, pp. 220–227 (2008)
Breiman, L.: Random forests. Machine Learning 45, 5–32 (2001)
Broomhead, D.S., Lowe, D.: Multivariable Functional Interpolation and Adaptive Networks. Complex Systems 2, 321–355 (1988)
Czarnowski, I., Jędrzejowicz, P.: An approach to RBF initialization with feature selection. In: Plamen, P., et al. (eds.) Intelligent Systems 2014. AISC, vol. 322, pp. 671–682. (2015)
Czarnowski, I., Jędrzejowicz, P.: Designing RBF Networks Using the Agent-Based Population Learning Algorithm. New Generation Computing 32(3–4), 331–351 (2014)
Czarnowski, I.: Cluster-based Instance Selection for Machine Classification. Knowledge and Information Systems 30(1), 113–133 (2012)
Datasets used for classification: comparison of results. In: directory of data sets. http://www.is.umk.pl/projects/datasets.html. (accessed September 1, 2009)
Gao, H., Feng, B.-q., Hou, Y., Zhu, L.: Training RBF neural network with hybrid particle swarm optimization. In: Wang, J., Yi, Z., Żurada, J.M., Lu, B.-L., Yin, H. (eds.) ISNN 2006. LNCS, vol. 3971, pp. 577–583. Springer, Heidelberg (2006)
Grozavu, N., Bennani, Y., Lebbah, M.: Cluster-dependent feature selection through a weighted learning paradigm. In: Guillet, F., Ritschard, G., Zighed, D.A., Briand, H. (eds.) Advances in Knowledge Discovery and Management. SCI, vol. 292, pp. 133–147. Springer, Heidelberg (2010)
Jȩdrzejowicz, J., Jȩdrzejowicz, P.: Cellular GEP-induced classifiers. In: Pan, J.-S., Chen, S.-M., Nguyen, N.T. (eds.) ICCCI 2010, Part I. LNCS, vol. 6421, pp. 343–352. Springer, Heidelberg (2010)
Wang, L., Fu, X.: Evolutionary Computation in Data Mining. Studies in Fuzziness and Soft Computing, vol. 163, pp. 79–99 (2005)
Novakovic, J.: Wrapper approach for feature selections in RBF network classifier. Theory and Applications of Mathematics & Computer Science 1(2), 31–41 (2011)
Rodriguez, J.J., Maudes, J.M., Alonso, J.C.: Rotation-based ensembles of RBF networks. In: Proceedings of the European Symposium on Artificial Neural Networks, Bruges, Belgium, pp. 605–610 (2006)
Sun, Y., Wu, D.: A RELIEF based feature extraction algorithm. In: Proceedings of the SIAM International Conference on Data Mining, pp. 188–195 (2008)
Talukdar, S., Baerentzen, L., Gove, A., de Souza, P.: Asynchronous Teams: Co-operation Schemes for Autonomous, Computer-Based Agents. Technical Report EDRC 18-59-96, Carnegie Mellon University, Pittsburgh (1996)
Witten, I.H., Merz, C.J.: Data Mining: Practical Machine Learning Tools and Techniques, 2nd edn. Morgan Kaufmann (2005)
Zhang, D., Tian, Y., Zhang, P.: Kernel-based nonparametric regression method. In: Proceedings of the IEEE/WIC/ACM International Conference on Web Intelligence and Intelligent Agent Technology, pp. 410–413 (2008)
Zhu, W., Dickerson, J.A.: A Novel Class Dependent Feature Selection Methods for Cancer Biomarker Discovery. Computers in Biology and Medicine 47, 66–75 (2014)
Author information
Authors and Affiliations
Corresponding author
Editor information
Editors and Affiliations
Rights and permissions
Copyright information
© 2015 Springer International Publishing Switzerland
About this paper
Cite this paper
Czarnowski, I., Jędrzejowicz, P. (2015). Cluster-Dependent Feature Selection for the RBF Networks. In: Núñez, M., Nguyen, N., Camacho, D., Trawiński, B. (eds) Computational Collective Intelligence. Lecture Notes in Computer Science(), vol 9330. Springer, Cham. https://doi.org/10.1007/978-3-319-24306-1_22
Download citation
DOI: https://doi.org/10.1007/978-3-319-24306-1_22
Published:
Publisher Name: Springer, Cham
Print ISBN: 978-3-319-24305-4
Online ISBN: 978-3-319-24306-1
eBook Packages: Computer ScienceComputer Science (R0)