International Journal of Scientific & Technology Research

Home About Us Scope Editorial Board Blog/Latest News Contact Us
10th percentile
Powered by  Scopus
Scopus coverage:
Nov 2018 to May 2020


IJSTR >> Volume 5 - Issue 7, July 2016 Edition

International Journal of Scientific & Technology Research  
International Journal of Scientific & Technology Research

Website: http://www.ijstr.org

ISSN 2277-8616

Evolutionary Algorithms For Neural Networks Binary And Real Data Classification

[Full Text]



Dr. Hanan A.R. Akkar, Firas R. Mahdi



Artificial neural networks, Classifications, Evolutionary algorithms, Population-based algorithms, Meta-heuristics techniques, and Optimization.



Artificial neural networks are complex networks emulating the way human rational neurons process data. They have been widely used generally in: prediction, clustering, classification, and association. The training algorithms that used to determine the network weights are almost the most important factor that influence the neural networks performance. Recently many meta-heuristic and Evolutionary algorithms are employed to optimize neural networks weights to achieve better neural performance. This paper aims to use recently proposed algorithms for optimizing neural networks weights comparing these algorithms performance with other classical meta-heuristic algorithms used for the same purpose. However, to evaluate the performance of such algorithms for training neural networks we examine such algorithms to classify four opposite binary XOR clusters and classification of continuous real data sets such as: Iris and Ecoli.



[1] G. P. Zhang, "Neural networks for classification: a survey," in IEEE Transactions on Systems, Man, and Cybernetics, Part C (Applications and Reviews), vol. 30, no. 4, pp. 451-462, Nov 2000. doi: 10.1109/5326.897072.

[2] M. Iqbal Quraishi, J. Pal Choudhury and M. De, "Image recognition and processing using Artificial Neural Network," Proc. IEEE, Recent Advances in Information Technology (RAIT), 2012 1st International Conference on, Dhanbad, 2012, pp. 95-100. 2012. doi: 10.1109/RAIT.2012.6194487.

[3] P. V. Rao, S. Madhusudana, N. S. S. and K. Keerthi, "Image Compression using Artificial Neural Networks," Proc. IEEE , Machine Learning and Computing (ICMLC), 2010 Second International Conference on, Bangalore, pp. 121-124, 2010. doi: 10.1109/ICMLC.2010.33

[4] S. Nirkhi, "Potential use of Artificial Neural Network in Data Mining," Proc. IEEE, Computer and Automation Engineering (ICCAE), 2010 The 2nd International Conference on, Singapore, pp. 339-343. 2010. doi: 10.1109/ICCAE.2010.5451537.

[5] D. Katic and M. Vukobratovic, "Intelligent control of humanoid robots using neural networks," Neural Network Applications in Electrical Engineering, 2004. NEUREL 2004. 2004 7th Seminar on, pp. 31-35, 2004. doi: 10.1109/NEUREL.2004.1416526M.

[6] M. N. H. Siddique and M. O. Tokhi, "Training neural networks: backpropagation vs. genetic algorithms," Proc. IEEE, Neural Networks, 2001. Proceedings. IJCNN '01. International Joint Conference on, Washington, DC, pp. 2673-2678 vol.4.. 2001. doi: 10.1109/IJCNN.2001.938792

[7] K. Bai and J. Xiong, "A Method of Improved BP Neural Algorithm Based on Simulated Annealing Algorithm," proc. IEEE, Genetic and Evolutionary Computing, 2009. WGEC '09. 3rd International Conference on, Guilin, pp. 765-768. 2009. doi: 10.1109/WGEC.2009.39

[8] A. Rakitianskaia and A. P. Engelbrecht, "Training neural networks with PSO in dynamic environments," IEEE Congress on Evolutionary Computation, Trondheim, pp. 667-673. 2009. doi: 10.1109/CEC.2009.4983009

[9] C. Ozturk and D. Karaboga, "Hybrid Artificial Bee Colony algorithm for neural network training," IEEE Congress of Evolutionary Computation (CEC), New Orleans, LA, pp. 84-88, 2011. doi: 10.1109/CEC.2011.5949602.

[10] A. Slowik and M. Bialko, "Training of artificial neural networks using differential evolution algorithm," IEEE Conference on Human System Interactions, Krakow, pp. 60-65, 2008. doi: 10.1109/HSI.2008.4581409

[11] S. Mirjalili, S. M. Mirjalili, and A. Hatamlou, "Multi-Verse Optimizer: a nature-inspired algorithm for global optimization", Neural Computing and Applications, vol. 27, no.2, pp. 495-513, February 2016.

[12] M. Cheng, and D. Prayogo, " Symbiotic Organisms Search: A new metaheuristic optimization algorithm", Elsevier Ltd. Computers & Structures, vol. 139, pp. 98112, 2014.

[13] H. Salimi, "Stochastic Fractal Search: A powerful metaheuristic algorithm", Elsevier Ltd., Knowledge-Based Systems, vol. 75, pp. 118, 2015.

[14] X. Menga, X.Z. Gaob, Y. Liuc, and H. Zhanga, "A novel bat algorithm with habitat selection and Doppler effect in echoes for optimization" ,Elsevier Ltd., Expert Systems with Applications, vol. 42, no. 1718, pp. 63506364, 2015.

[15] X. Menga, X.Z. Gao, L. Lu, Y. Liu, and H. Zhang, A new bio-inspired optimization algorithm: Bird Swarm Algorithm, Experimental & Theoretical Artificial Intelligence, Mar. 2015.