Abstract
In this article we investigate some approaches to the artificial neural networks training with use of hybrid algorithms. Algorithms which are based on the back propagation algorithm and the ant colony algorithm are considered in detail. The article describes the application of the artificial neural network with the authors’ hybrid training algorithm. The preliminary studies have shown that the algorithm improves the efficiency of the problems on standard test databases. The application of the algorithm for practical problems solution in the field of medicine, namely the definition of danger level determination of tuberculosis carriers is described. It was shown that the accuracy of the hybrid algorithm is up to 22% higher than of the classical one.
[1] S. Haykin, Neural Networks A Comprehensive Foundation Second Edition (Prentice Hall Inc., 1999) pp. 842 Search in Google Scholar
[2] M. Dorigo, The Ant System: Optimization by a Colony of Cooperating Agents, IEEE T. Syst Man Cyber. B 26(1), 1–13, 1996 10.1109/3477.484436Search in Google Scholar PubMed
[3] M. Tim Jones, Al Application Programming (Charles River Media Inc. Hingham, Massachusetts, 2003) p. 363 Search in Google Scholar
[4] C. Blum, K. Socha, Training feed-forward neural networks with ant colony optimization: An application to pattern classification, Proceedings of the Fifth International Conference on Hybrid Intelligent Systems, Barcelona, Spain, 2005, pp. 233–238 10.1109/ICHIS.2005.104Search in Google Scholar
[5] L. Xiaoyue, S. Jiping, F. Sumin, Neural Network Based on Ant Colony Clustering Algorithm Applied to Predict the Stability of the Roof in Coal Mining, Proc. ISDA’06 01, 396–399, 2006 Search in Google Scholar
[6] L. Yan-Peng, W. Ming-Guang, Q. Ji-Xin, Evolving Neural Networks Using the Hybrid of Ant Colony Optimization and BP Algorithms, Advances in Neural Networks, ISNN 2006, Lecture Notes in Computer Science, 3971, 714–722, 2006 http://dx.doi.org/10.1007/11759966_10510.1007/11759966_105Search in Google Scholar
[7] W. Gao, New Neural Network Based on Ant Colony Algorithm for Financial Data Forecasting, 4th International Conference on Intelligent Information Hiding and Multimedia Signal Processing (IIH-MSP 2008), Harbin, China, 15–17 August 2008, Proceedings of Intelligent Information Hiding and Multimedia Signal Processing, 1437–1440, 677–681, 2008 10.1109/IIH-MSP.2008.126Search in Google Scholar
[8] H. Mei, Y. Wang, Ant Colony Optimization for Neural Network, Key Engineering Materials, Manufacturing Automation Technology, 392–394, 2008 10.4028/www.scientific.net/KEM.392-394.677Search in Google Scholar
[9] M. Conforth, Y. Meng, Toward Evolving Neural Networks using Bio-Inspired Algorithms (Department of Electrical and Computer Engineering, Stevens Institute of Technology, 2008) pp. 413–419 Search in Google Scholar
[10] H. Mei, Y. Wang, R. Zhao, Study on the Feed forward Neural Network Based on Ant Colony Optimization, J. Wuhan Univ. Technol. (Transportation Science & Engineering) 3, 270–276, 2009 Search in Google Scholar
[11] S. Huawang, L. Wanqing, Artificial neural networks with ant colony optimization for assessing performance of residential buildings, BioMedical Information Engineering, International Conference on Future, Sanya, 13–14 December 2009, IEEE, 379–382, 2009 Search in Google Scholar
[12] R. Tehrani, F. Khodayar, Optimization of the Artificial Neural Networks Using Ant Colony Algorithm to Predict the Variation of Stock Price Index, Asian Network for Scientific Information, J. Appl. Sci. 10, 221–225, 2010 http://dx.doi.org/10.3923/jas.2010.221.22510.3923/jas.2010.221.225Search in Google Scholar
[13] M. Shuiling, W. Wan, R. Wang et al., The application of ant colony algorithm and artificial neural network in tax assessment, Audio Language and Image Processing 1, 1433–1436, 2010 Search in Google Scholar
[14] M. Unal, M. Onat, A. Bal, Cellular Neural Network training by ant colony optimization algorithm, Signal Processing and Communications Applications Conference, Diyarbakir, 22–24 April 2010, IEEE, 471–474, 2010 http://dx.doi.org/10.1109/SIU.2010.565391710.1109/SIU.2010.5653917Search in Google Scholar
[15] L. Ling, Y. Huang, L. Qu, Research on Fault Diagnosis Based on BP Neural Network Optimized by Chaos Ant Colony Algorithm (School of Electric and Information Engineering, Anhui University of Science and Technology, 2010) pp. 257–264 10.1007/978-3-642-13495-1_32Search in Google Scholar
[16] H. Movahedipour, Application of Continuous ACOR to Neural Network Training: Direction of Arrival Problem, Ant Colony Optimization — Methods and Applications, 159–178, 2011 10.5772/13611Search in Google Scholar
[17] N. Sudarshan, S. Partha Pratim, D. Achintya, Training a Feed-Forward Neural Network with Artificial Bee Colony Based Back Propagation Method, Int. J. Comp. Sci. Inf. Tech. 4(4), 33–46, 2012 10.5121/ijcsit.2012.4404Search in Google Scholar
[18] R. Irania, R. Nasimia, An Evolving Neural Network Using an Ant Colony Algorithm for a Permeability Estimation of the Reservoir, Pet. Sci. Technol. 30(4), 375–384, 2012 http://dx.doi.org/10.1080/10916466.2010.48344210.1080/10916466.2010.483442Search in Google Scholar
[19] E. Kotlyarov, T. Petrushina, Hybrid training method of artificial neural network on the basis of the modified ant algorithm, East. Eur. J. Entr. Technol. 5/4(59), 16–21, 2012 (in Russian) Search in Google Scholar
[20] E. V. Kotlyarov, Neural network learning method based on ant colony algorithm for classification problems solution, Electrotechnic and Computer Systems, Informational Systems and Technologies 8(84), 122–129, 2012 (in Russian) Search in Google Scholar
[21] E. V. Kotlyarov, The application analysis of hybrid artificial neural network training algorithm for some classification problems, Bulletin of Taras Shevchenko National University of Kyiv, Ser. Phys. Math. 4, 139–144, 2012 Search in Google Scholar
© 2014 Versita Warsaw
This work is licensed under the Creative Commons Attribution-NonCommercial-NoDerivatives 3.0 License.
