volume | PIER Journals

Abstract

Feed forward neural Network (FNN) has been widely applied to many fields because of its ability to closely approximate unknown function to any degree of desired accuracy. Back Propagation (BP) is the most general learning algorithms, but is subject to local optimal convergence and poor performance even on simple problems when forecasting out of samples. Thus, we proposed an improved Bacterial Chemotaxis Optimization (BCO) approach as a possible alternative to the problematic BP algorithm, along with a novel adaptive search strategy to improve the efficiency of the traditional BCO. Taking the classical XOR problem and sinc function approximation as examples, comparisons were implemented. The results demonstrate that our algorithm is obviously superior in convergence rate and precision compared with other training algorithms, such as Genetic Algorithm (GA) and Taboo Search (TS).

1. Mohamed, M. A., E. A. Soliman, and M. A. El-Gamal, "Optimization and characterization of electromagnetically coupled patch antennas using RBF neural networks," Journal of Electromagnetic Waves and Applications, Vol. 20, No. 8, 1101-1114, 2006.
doi:10.1163/156939306776930240 Google Scholar

2. Guney, K., C. Yildiz, S. Kaya, and M. Turkmen, "Artificial neural networks for calculating the characteristic impedance of air-suspended trapezoidal and rectangular-shaped microshield lines," Journal of Electromagnetic Waves and Applications, Vol. 20, No. 9, 1161-1174, 2006.
doi:10.1163/156939306777442917 Google Scholar

3. Ayestar, R. G. and F. Las-Heras, "Near filed to far field transformation using neural networks and source reconstruction," Journal of Electromagnetic Waves and Applications, Vol. 20, No. 15, 2201-2213, 2006.
doi:10.1163/156939306779322594 Google Scholar

4. Ayestar, R. G., F. Las-Heras, and J. A. Martinez, "Non uniform-antenna array synthesis using neural networks," Journal of Electromagnetic Waves and Applications, Vol. 21, No. 8, 1001-1011, 2007. Google Scholar

5. Kizilay, A. and S. Makal, "A neural network solution for identification and classification of cylindrical targets above perfectly conducting flat surfaces," Journal of Electromagnetic Waves and Applications, Vol. 21, No. 14, 2147-2156, 2007.
doi:10.1163/156939307783152759 Google Scholar

6. Zainud-Deen, S. H., H. A. Malhat, K. H. Awadalla, and E. S. El-Hadad, "Direction of arrival and state of polarization estimation using radial basis function neural network (RBFNN)," Progress In Electromagnetics Research B, Vol. 2, 137-150, 2008.
doi:10.2528/PIERB07111801 Google Scholar

7. Panda, D. K. and A. Chakrabarty, "Multiple cavity modeling of a feed network for two dimensional phased array application," Progress In Electromagnetics Research Letters, Vol. 2, 135-140, 2008. Google Scholar

8. Engoziner, S. and E. Tomsen, "An accelerated learning algorithm for multiplayer perception: Optimization layer by layer," IEEE Trans. on Neural Network, Vol. 6, 31-42, 1995. Google Scholar

9. Lawrence, S., A. C. Tsoi, and C. L. Giles, Noisy time series prediction using symbolic representation and recurrent neural network grammatical inference, Technical report UMIACS-TR-96-27 and CS-TR-3625, Institute for Advanced Computer Studies, University of Maryland, 1996.

10. Miao, K., F. Chen, and Z. G. Zhao, "Stock price forecast based on bacterial colony RBF neural network," Journal of QingDao University, Vol. 20, 50-54, 2007. Google Scholar

11. Engoziner, S. and E. Tomesn, "An accelerated learning algorithm for multiplayer perception: Optimization layer by layer," IEEE Trans. on Neural Network, Vol. 6, 31-42, 1995. Google Scholar

12. Sexton, R. S., B. Alidaee, R. E. Dorsey, and J. D. Johnson, "Global optimization for artificial neural networks: A tabu search application," European Journal of Operational Research, Vol. 106, 570-584, 1998.
doi:10.1016/S0377-2217(97)00292-0 Google Scholar

13. Sexton, R. S., R. E. Dorsey, and J. D. Johnson, "Toward global optimization of neural networks: A comparison of the genetic algorithm and back-propagation," Decision Support System, Vol. 22, 171-185, 1998.
doi:10.1016/S0167-9236(97)00040-7 Google Scholar

14. Chiu, C.-C. and T.-C. Tu, "Path loss reduction in an urban area by genetic algorithms," Journal of Electromagnetic Waves and Applications, Vol. 20, No. 3, 319-330, 2006.
doi:10.1163/156939306775701696 Google Scholar

15. Tian, Y.-B. and J. Qian, "Ultraconveniently finding multiple solutions of complex transcendental equations based on genetic algorithm," Journal of Electromagnetic Waves and Applications, Vol. 20, No. 4, 475-488, 2006.
doi:10.1163/156939306776117090 Google Scholar

16. Lu, Y.-Q. and J.-Y. Li, "Optimization of broadband top-load antenna using micro-genetic algorithm," Journal of Electromagnetic Waves and Applications, Vol. 20, No. 6, 793-801, 2006.
doi:10.1163/156939306776143370 Google Scholar

17. Chen, X., D. Liang, and K. Huang, "Microwave imaging 3-D buried objects using parallel genetic algorithm with FDTD technique," Journal of Electromagnetic Waves and Applications, Vol. 20, No. 13, 1761-1774, 2006.
doi:10.1163/156939306779292264 Google Scholar

18. Tsaih, R., Y. Hsu, and C. C. Lai, "Forecasting S&P 500 stock index futures with a hybrid AI system," Decision Support System, Vol. 23, 161-174, 1998.
doi:10.1016/S0167-9236(98)00028-1 Google Scholar

19. Kohara, K., T. Ishikawa, Y. Fukuhara, and Y. Nakamura, "Stock price prediction using prior knowledge and neural networks," Int. J. Intelligence System Accounting Finance Manage, Vol. 6, 11-12, 1997.
doi:10.1002/(SICI)1099-1174(199703)6:1<11::AID-ISAF115>3.0.CO;2-3 Google Scholar

20. Gao, X. J., "Artificial neural network based on niche genetic algorithm applies to stock price prediction," Market Modernization, Vol. 500, 35, 2007. Google Scholar

21. Chen, F., Y. H. Chen, and J. Z. Zhang, "Stock index modeling using IP based gene expression programming," Computer Engineering and Applications, Vol. 43, 227-229, 2007. Google Scholar

22. Majhi, R. and G. Panda, "Stock market prediction of S&P 500 and DJIA using bacterial foraging optimization technique," IEEE Congress on Evolutionary Computation, 2007.

23. He, Y., Y. H. Qiu, G. Liu, and K. Y. Lei, "Optimizing weights of neural network using an adaptive tabu search approach," Proc. ISNN 2005, LNCS 349, 672-676, 2005.

24. Ayestaran, R. G., J. Laviada-Martinez, and F. Las-Heras, "Synthesis of passive-dipole arrays with a genetic-neural hybrid method," Journal of Electromagnetic Waves and Applications, Vol. 20, No. 15, 2123-2135, 2006.
doi:10.1016/0016-0032(74)90041-6 Google Scholar

25. Bremermann, H. J., "Chemotaxis and optimization," J. Franklin Inst., Vol. 297, 397-404, 1974. Google Scholar

26. Sibylle, D. M., M. Jarno, A. Stefane, et al. "Optimization based on bacterial chemotaxis," IEEE Trans. on Evolutionary Computation, Vol. 6, 17-19, 2002.
doi:10.1002/jss.400040304 Google Scholar

27. Dahlquist, F. W., R. A. Elwell, and P. S. Lovely, "Studies of bacterial chemotaxis in defined concentration gradients — A model for chemotaxis toward l-serine," J. Supramolecular Structure, Vol. 4, 329-342, 1976.
doi:10.1023/B:GEGE.0000025044.72718.db Google Scholar

28. Basma, A. A. and N. Kallas, "Modeling soil collapse by artificial neural networks," Geotechnical and Geological Engineering, Vol. 22, 427-438, 2004. Google Scholar

29. Dong, H. K., A. Ajith, and H. C. Jae, "A hybrid genetic algorithm and bacterial foraging approach for global optimization," Information Sciences, Vol. 177, No. 3918, 2007. Google Scholar

30. Passino, K. M., "Biomimicry of bacterial foraging for distributed optimization and control," IEEE Control System Magazine, Vol. 6, 52-67, 2007. Google Scholar

31. Li, W. W., H. Wang, Z. J. Zou, and J. X. Qian, "Function optimization method based on bacterial colony chemotaxis," Journal of Circuits and Systems, Vol. 10, 58-63, 2005. Google Scholar

Prof. Yudong Zhang

Dr. Lenan Wu