ENHANCEMENT OF QUANTUM PARTICLE SWARM OPTIMIZATION IN ELMAN RECURRENT NETWORK WITH BOUNDED VMAX FUNCTION
DOI:
https://doi.org/10.11113/jt.v78.10121Keywords:
Particle Swarm Optimization, Elman Recurrent Neural Network, Quantum, classificationAbstract
There are many drawbacks in BP network, such as trap into local minima and may get stuck at regions of a search space. To solve these problems, Particle Swarm Optimization (PSO) has been executed to improve ANN performance. In this study, we exploit errors optimization of Elman Recurrent Neural Network (ERNN) with a new enhance method of Particle Swarm Optimization with an addition of quantum approach to optimize the performance of both networks with bounded Vmax function. Main characteristics of Vmax function are to control the global exploration of particles in Particle Swarm Optimization and Quantum approach is used to improve the searching ability of the individual particle of PSO. The results show that for cancer dataset, Quantum Particle Swarm Optimization in Elman Recurrent Neural Network (QPSOERN) with bounded Vmax of hyperbolic tangent depicted 96.26% and Vmax sigmoid function with 96.35% which both furnishes promising outcomes and better value in terms of classification accuracy and convergence rate compared to bounded standard Vmax function with only 90.98%.Â
References
Geib, J., & Serpen, G. 2004. Computational Promise Of Simultaneous Recurrent Network With A Stochastic Search Mechanism. Proc. IEEE International Joint Conference On Neural Networks. 3: 2239-2244.
Michel, A., & Farrell, J. 1990. Associative Memories Via Artificial Neural Networks. IEEE Control Systems Magazine. 10(3): 6-17.
Robinson, B. 2003. Evolutionary Artificial Neural Networks in Problem Solving. University of Manitoba,
Luger, G. F. 2002. Artificial Intelligence: Structures and Strategies for Complex Problem Solving. 4th ed. Addison Wesley/Pearson Education Limited, Harlow, England. 417-473.
G. Dib. 2000. Artificial Neural Networks. ELE82 Biomedical Engineering Seminar 1. Kingston.
Krose, B. and Van der Smagt, P. 1996. An Introduction to Neural Networks. 8th ed., University of Amsterdam.
R. C. Eberhart and J. Kennedy. 1995. A New Optimizer using Particle Swarm Theory. Proceedings of the Sixth International Symposium on Micromachine and Human Science. 39-43.
F. Van den Bergh. 1999. Particle Swarm Weight Initialization In Multi-Layer Perceptron Artificial Neural Networks. Accepted for ICAI. Durban, South Africa. 41-45.
J. L. Elman. 1990. Finding Structure In Time. Cognitive Science. 14: 179-211.
S. Ujjin and P. J. Bentley. 2003. Particle Swarm Optimization Recommender System. IEEE Swarm Intelligence Symposium 2003. 24-26 April. 124-131.
R. C. Eberhart and Y. Shi. 1998. Comparison between Genetic Algorithms and Particle Swarm Optimization. Proceedings of the 7th International Conference on Evolutionary Programming VII, March 25-27 1. 611-616.
Bishop, C. M. 1995. Neural Networks for Pattern Recognition. Oxford University Press, Oxford,
Ripley, B. D. 1996. Pattern Recognition and Neural Networks. Cambridge University Press, Cambridge.
F. Van den Bergh, and A. P. Engelbrecht. 2000. Cooperative Learning in Neural Networks using Particle Swarm Optimizers. South African Computer Journal. 26: 84-90.
Ahmed, T. 2004. Adaptive Particle Swarm Optimizer for Dynamic Environments. The University Of Texas: Master Thesis.
Lin, L. I. 2005. Particle Swarm Optimization for Solving Constraint Satisfaction Problems. Simon Fraser University: Master Thesis.
Shi, Y., Eberhart, R. 1998. Parameter Selection in Particle Swarm Optimization. Proc. Seventh Annual Conf. on Evolutionary Programming. 591-601.
Shamsuddin, S. M. 2004. Lecture Note Ad Advanced Artificial Intelligence: Number of Hidden Neurons. Universiti Teknologi Malaysia. Unpublished.
Shi, Y., Eberhart, R. 1998. A Modified Particle Swarm Optimizer. IEEE International Conf. An Evolutionary Computation Anchorage, Alaska. USA. 69-73.
Downloads
Published
Issue
Section
License
Copyright of articles that appear in Jurnal Teknologi belongs exclusively to Penerbit Universiti Teknologi Malaysia (Penerbit UTM Press). This copyright covers the rights to reproduce the article, including reprints, electronic reproductions, or any other reproductions of similar nature.
