CFP last date
20 June 2024
Reseach Article

An Effective Intelligent Self-Construction Multilayer Perceptron Neural Network

by Amany S. Saber, Mohamed A. El-rashidy
International Journal of Computer Applications
Foundation of Computer Science (FCS), NY, USA
Volume 98 - Number 11
Year of Publication: 2014
Authors: Amany S. Saber, Mohamed A. El-rashidy
10.5120/17228-7552

Amany S. Saber, Mohamed A. El-rashidy . An Effective Intelligent Self-Construction Multilayer Perceptron Neural Network. International Journal of Computer Applications. 98, 11 ( July 2014), 23-28. DOI=10.5120/17228-7552

@article{ 10.5120/17228-7552,
author = { Amany S. Saber, Mohamed A. El-rashidy },
title = { An Effective Intelligent Self-Construction Multilayer Perceptron Neural Network },
journal = { International Journal of Computer Applications },
issue_date = { July 2014 },
volume = { 98 },
number = { 11 },
month = { July },
year = { 2014 },
issn = { 0975-8887 },
pages = { 23-28 },
numpages = {9},
url = { https://ijcaonline.org/archives/volume98/number11/17228-7552/ },
doi = { 10.5120/17228-7552 },
publisher = {Foundation of Computer Science (FCS), NY, USA},
address = {New York, USA}
}
%0 Journal Article
%1 2024-02-06T22:25:56.684067+05:30
%A Amany S. Saber
%A Mohamed A. El-rashidy
%T An Effective Intelligent Self-Construction Multilayer Perceptron Neural Network
%J International Journal of Computer Applications
%@ 0975-8887
%V 98
%N 11
%P 23-28
%D 2014
%I Foundation of Computer Science (FCS), NY, USA
Abstract

A new classifier algorithm based on Multilayer Perceptron Neural Network (MPNN), Apriori association rules, and Particle Swarm Optimization (PSO) models is proposed. It provides a comprehensive analytic method for establishing an Artificial Neural Network (ANN) with self-organizing architecture by finding an optimal number of hidden layers and their neurons, less number of effective features of data set, and better topology for internal connections. The performance of the proposed algorithm is evaluated using a number of benchmark data sets including Breast Cancer, Iris, and Yeast. Experimental results demonstrate the effectiveness and the notability of the proposed algorithm comparing with recently existed ANN learning and classification algorithms.

References
  1. Agrawal, R. , Imieliski, T. , and Swami, A. 1993. Mining association rules between sets of items in large databases. In Proceedings of ACM SIGMOD International Conference on Management of Data (SIGMOD-1993).
  2. Bortman, M. and Aladjem, M. 2009. A growing and pruning method for radial basis function networks. IEEE Trans. Neural Networks. 20(6),1039–1045.
  3. Caballero, J. C. F. , Martinez, F. J. , Hervas, C. , and Gutierrez, P. A. 2010. Sensitivity versus accuracy in multiclass problems using memeticpareto evolutionary neural networks. IEEE Trans. Neural Networks. 21(5), 751–770.
  4. Fritzke, B. 1994. Growing cell structures a self-organizing network for unsupervised and supervised learning. Neural Networks. 7(9),1441–1460.
  5. Han, H. G. and Qiao, J. F. 2013. A structure optimization algorithm for feed-forward neural network construction. Neurocomputing. 99, 347–357.
  6. Han, H. G. , Wang, L. D. , and Qiao, J. F. 2013. Efficient self-organizing multilayer neural network for nonlinear system modeling. Neural Networks. 43, 22–32.
  7. Hsu, C. F. 2008. Adaptive growing-and-pruning neural network control for a linear piezo electric ceramic motor. Eng. Appl. Artif. Intell. 21(8), 1153–1163.
  8. Huang, G. and Chen, L. 2008. Enhanced random search based incremental extreme learning machine. Neurocomputing. 71, 3460–3468.
  9. Huang, D. S. and Du, J. X. 2008. A constructive hybrid structure optimization methodology for radial basis probabilistic neural networks. IEEE Trans. Neural Networks. 19(12), 2099–2115.
  10. Islam, M. M. , Sattar, M. A. , Amin, M. F. , Yao, X. , and Murase, K. 2009. A new adaptive merging and growing algorithm for designing artificial neural networks. IEEE Transactions on Systems, Man, and Cybernetics, Part B: Cybernetics. 39(3), 705–722.
  11. John, G. H. and Langley, P. 1995. Estimating continuous distributions in baysian classifiers. In Proceedings of the 11th conference on uncertainty in artificial intelligence. Montreal, Canada, 338–345.
  12. Kennedy, J. and Eberhart, R. 1995. Particle Swarm Optimization. In Proceedings of the IEEE International Conference on Neural Networks, 1942-1948.
  13. Lauret, P. , Fock, E. and Mara, T. A. 2006. A node pruning algorithm based on a Fourier amplitude sensitivity test method. IEEE Trans. Neural Networks. 17 (2), 273–293.
  14. Lehtokangas, M. 1999. Modelling with constructive back-propagation. Neural Networks. 12(4–5), 707–716.
  15. Leung, C. S. , Wong, K. W. , Sum, P. F. and Chan, L. W. 2001. A pruning method for the recursive least squared algorithm. Neural Networks. 14(2), 147–174.
  16. Ma, L. and Khorasani, K. 2003. A new strategy for adaptively constructing multilayer feed-forward neural networks. Neurocomputing. 51, 361–385.
  17. Nielsen, A. B. and Hansen, L. K. 2008. Structure learning by pruning in independent component analysis. Neurocomputing. 71(10–12),2281–2290.
  18. Platt, J. 1999. Using analytic QP and sparseness to speed training of support vector machines. In Proceedings of the 13th annual conference on neural information processing systems. Denver, Colorado, 557–563.
  19. Rojas, R. 1996. Neural Networks: A Systematic Introduction. Berlin, Springer-Verlag.
  20. Shi, Y. and Eberhart, R. 1998. A modified particle swam optimizer. IEEE Word Congress on Computational Intelligence. 69-73.
  21. Sun, J. 2010. Application of Data Mining for Decision Tree Model of Multi-variety Discrete Production and Manufacture. Intelligent Information Technology and Security Informatics (IITSI). Jinggangshan, 724 – 728.
  22. UCI Machine Learning Repository websitehttp://archive. ics. uci. edu:80/ml/datasets. html.
  23. Zhang, R. , Lan, Y. , Huang, G. B. , and Xu, Z. B. 2012. Universal approximation of extreme learning machine with adaptive growth of hidden nodes. IEEE Trans. Neural Networks Learn. Syst. . 23(2), 365–371.
Index Terms

Computer Science
Information Sciences

Keywords

Classification Artificial neural network Apriori association rules Particle swarm optimization.