Call for Paper - November 2020 Edition
IJCA solicits original research papers for the November 2020 Edition. Last date of manuscript submission is October 20, 2020. Read More

Improved PSO Algorithm for Training of Neural Network in Co-design Architecture

Print
PDF
International Journal of Computer Applications
Foundation of Computer Science (FCS), NY, USA
Year of Publication: 2019
Authors:
Tuan Linh Dang, Yukinobu Hoshino
10.5120/ijca2019918583

Tuan Linh Dang and Yukinobu Hoshino. Improved PSO Algorithm for Training of Neural Network in Co-design Architecture. International Journal of Computer Applications 182(44):1-7, March 2019. BibTeX

@article{10.5120/ijca2019918583,
	author = {Tuan Linh Dang and Yukinobu Hoshino},
	title = {Improved PSO Algorithm for Training of Neural Network in Co-design Architecture},
	journal = {International Journal of Computer Applications},
	issue_date = {March 2019},
	volume = {182},
	number = {44},
	month = {Mar},
	year = {2019},
	issn = {0975-8887},
	pages = {1-7},
	numpages = {7},
	url = {http://www.ijcaonline.org/archives/volume182/number44/30442-2019918583},
	doi = {10.5120/ijca2019918583},
	publisher = {Foundation of Computer Science (FCS), NY, USA},
	address = {New York, USA}
}

Abstract

This paper proposes a new version of the standard particle swarm optimization (SPSO) algorithm to train a neural network (NN). The improved PSO, called the wPSOd_CV algorithm, is the improved version of the PSOd_CV algorithm presented in a previous study. The wPSOd_CV algorithm is introduced to solve the issue of premature convergence of the SPSO algorithm. The proposed wPSOd_CV algorithm is used in a co-design architecture. Experimental results confirmed the effectiveness of the NN trained by the wPSOd_CV algorithm when compared with the NN trained by the SPSO algorithm and the PSOd_CV algorithm concerning the minimum learning error and the recognition rates.

References

  1. P.M. Ravdin, G. M. Clark GM, A practical application of neural network analysis for predicting outcome of individual breast cancer patients, Breast Cancer Research and Treatment, vol. 22, no. 3, pp. 285-293, 1992
  2. A. E. Celik, Y. Karatepe, Evaluating and forecasting banking crises through neural network models: An application for Turkish banking sector, Expert Systems with Applications vol. 33, no. 4, pp. 809-815, 2007
  3. S. Haykin, Neural networks and learning machines, 3rd edn, Prentice Hall, 2008
  4. R. H. Nielsen, Theory of the backpropagation neural network, In processing of the international conference on neural networks, pp. 693-605, 1989
  5. R. Rojas, Neural networks - a systematic introduction, Springer-Verlag, 1996
  6. J. R. Zhang, J. Zhang, T. M. Lok. M. R. Lyu, A hybrid particle swarm optimizationback-propagation algorithm for feedforward neural network training, Applied mathematics and computation, vol. 185, pp. 10261037, 2007
  7. Z.A. Bashir, M.E. El-Hawary, Applying Wavelets to Short- Term Load Forecasting Using PSO-Based Neural Networks, IEEE transactions on power systems, vol. 46, pp. 268-275, 2016
  8. A. Suresh, K. V. Harish, N. Radhika, Particle Swarm Optimization over Back Propagation Neural Network for Length of Stay Prediction, In processing of the international conference on information and communication technologies, vol. 24, no.1, pp. 20-27, 2009
  9. V. G. Gudise, G. K. Venayagamoorthy, Comparison of particle swarm optimization and backpropagation as training algorithms for neural networks, In processing of 2003 IEEE swarm intelligence symposium, pp. 110-117, 2003
  10. J. Kennedy, R. Eberhart, Particle swarm optimization, In processing of the IEEE international conference on neural networks, vol. 4, pp.1942-1948, 1995
  11. R. Eberhart, Y. Shi, Particle swarm optimization: developments, applications and resources, In processing of the 2001 IEEE international conference on congress on evolutionary computation, vol. 1, pp. 81-86, 2001
  12. R. Mendes, et al., Particle swarms for feedforward neural network training, In processing of the IEEE international joint conference on neural networks, vol.2, pp.1895-1899, 2002
  13. K. W. Chau, Application of a PSO-based neural network in analysis of outcomes of construction claims. Automation in construction, vol. 16, no. 5, 642-646, 2007
  14. G. Montavon, G. B. Orr, K. R. Muller Neural networks: tricks of the trade, 2nd edn, Springer, 2012
  15. T. L. Dang, Y. Hoshino, Hardware/Software Co-design for a Neural Network Trained by Particle Swarm Optimization Algorithm, Neural Processing Letters, pp. 1-25, 2018
  16. T. L. Dang, C. Thang, Y. Hoshino, Hybrid hardware-software architecture for neural networks trained by improved pso algorithm, ICIC Expree Letters, pp. 565-574, 2017
  17. T. L. Dang, Y. Hoshino, An-FPGA based classification system by using a neural network and an improved particle swarm optimization algorithm, In processing of the 2016 Joint 8th International Conference on Soft Computing and Intelligent Systems (SCIS) and 17th International Symposium on Advanced Intelligent Systems, pp.97-102, 2016
  18. Y. Hoshino, H. Takimoto, PSO training of the neural network application for a controller of the line tracing car, In: Proceedings of the IEEE International Conference on Fuzzy Systems, pp.1-8, 2012
  19. Y. Shi. R.Eberhart R, A modified particle swarm optimizer, In Proceedings of 1998 IEEE International Conference on Evolutionary Computation, pp 69-73, 1998
  20. Altera company, SoC product brochure. https://www.altera.com/products/soc/overview.html, accessed 07 February 2019
  21. Terasic company, DE1-SoC user manual, http://de1-soc.terasic.com, accessed 07 February 2019
  22. M Lichman, UCI Machine Learning Repository, http://archive.ics.uci.edu/ml, accessed 07 February 2019

Keywords

Neural network, Particle swarm optimization, FPGA, ARM, codesign architecture