Abstract
Partitional clustering approaches have been used in initialization of resources allocation network (RAN). However, they are sensitive to the clustering number and susceptible to local optima. This paper proposes a new RAN initialization algorithm based on pipelined genetic algorithm. It initializes the hidden layer with much less centers and improves the performance of RAN with higher clustering validity as well as parsimonious structure. Simulation results show RBF modulation classifier trained with the new algorithm can get higher accuracy.
This is a preview of subscription content, log in via an institution.
Buying options
Tax calculation will be finalised at checkout
Purchases are for personal use only
Learn about institutional subscriptionsPreview
Unable to display preview. Download preview PDF.
References
Nandi, A.K., Azzouz, E.E.: Algorithms for Automatic Modulation Recognition of Communication Signals. J. Communications 46, 431–436 (1998)
De Castro, L.N., Hruschka, E.R., Campello, R.J.G.B.: An Evolutionary Clustering Technique with Local Search to Design RBF Neural Network Classifiers. In: International Joint Conferenceonon Neural Networks, vol. 3, pp. 2083–2088. IEEE Press, Budapest (2004)
Jian, C., Kuo, Y., Li, J., Fu, F.: Neural Network Application in Automatic Recognition of Communication Signals. In: Fifth International Conference on Computational Intelligence and Multimedia Applications, pp. 457–462. IEEE Press, Xi’an (2003)
Yang, C., Zhong, Z., Yang, J.: Recognition of Digital Modulation Using Radial Basis Funcition Neural Networks. In: Second International Conference on Machine Learning and Cybernetics, pp. 3012–3015. IEEE Press, Xi’an (2003)
Haykin, S.: Neural Networks: A Comprehensive Fundation, 2nd edn. Tsinghua University Press, Beijing (2001)
Platt, J.C.: A Resource Allocating Network for Function Interpolation. J. Neural Computation 3, 213–225 (1991)
Kadirkamanathan, V., Niranjan, M.: A Function Estimation Approach to Sequential Learning with Neural Networks. J. Neural Computation 5, 954–975 (1993)
Lu, Y.W., Sundararajan, N., Saratchandran, P.: A Sequential Minimal Radial Basis Function(RBF) Neural Network Learning Algorithm. J. Neural Networks 9, 308–318 (1998)
Han, M., Guo, W., Mu, Y.: A Modified RBF Neural Network in Pattern Recognition, Oriando, pp. 2527–2532 (2007)
Wallace, M., Tsapatsoulis, N., Kollias, S.: Intelligent Initialization of Resource Allocating RBF Networks. Neural network 18, 117–122 (2005)
Zhou, M., Sun, S.: Genetic Algorithms Theory and Applications. Publishing House of National Defence Industry, Beijing (1999)
Li, Y., Sundararajan, N., Saratchandran, P.: Analysis of Minimal Radial Basis Function Network Algorithm for Real-Time Identification of Nonlinear Dynamic Systems. Control Theory and Applications 147(4), 476–484 (2000)
Pakhira, M.K., De, R.K.: Function Optimization Using a Pipelined Genetic Algorithm. Intelligent Sensors, Sensor Networks and Information Processing Conference, pp. 253–257 (2004)
Xu, X., Wunsch, D.: Survey of Clustering Algorithms. J. Neuranl Networks 16, 645–678 (2005)
Sheng, W., Swift, S., Zhang, L., Liu, X.: A Weighted Sum Validity Function for Clustering With a Hybrid Niching Genetic Algorithm. J. Systems, Man, and Cybernetics 35, 1156–1167 (2005)
Theodoridis, S., Koutroumbas, K.: Pattern Recognition, 3rd edn. Publishing House of Electronics Industry, Beijing (2006)
Xue, F., Ge, L.: Improved Genetic Algorithm for Feature Selection of Mdulation Signal. J. Computer engineering 34, 213–214 (2008)
Author information
Authors and Affiliations
Editor information
Editors and Affiliations
Rights and permissions
Copyright information
© 2009 Springer-Verlag Berlin Heidelberg
About this paper
Cite this paper
Xue, F., Ge, L., Wang, B. (2009). Pipelined Genetic Algorithm Initialized RAN Based RBF Modulation Classifier. In: Yu, W., He, H., Zhang, N. (eds) Advances in Neural Networks – ISNN 2009. ISNN 2009. Lecture Notes in Computer Science, vol 5552. Springer, Berlin, Heidelberg. https://doi.org/10.1007/978-3-642-01510-6_83
Download citation
DOI: https://doi.org/10.1007/978-3-642-01510-6_83
Publisher Name: Springer, Berlin, Heidelberg
Print ISBN: 978-3-642-01509-0
Online ISBN: 978-3-642-01510-6
eBook Packages: Computer ScienceComputer Science (R0)