In machine learning, classification is a technique to identify the category to which an observation belongs, based on a labeled training data. It is a task of approximating a mapping function from input variables to discrete output variables. Pattern classification delivers this approximation by automatically discovering the regularities in the data using learning algorithms. It is an important sub-topic of machine learning with interesting applications like speech recognition and classification of rocks. In this paper, propose a hybrid approach Artificial Neural Network with Particle Swarm Optimization (ANNPSO) algorithm for pattern recognition. The ANNPSO works under the two main principles, first the error is calculated by using artificial neural network and second, error is optimized using Particle swarm optimization algorithms. Model tested on well known standard pattern IRIS flower dataset. Performance of presented model is evaluated with five-fold cross validation which produces 99.33% testing accuracy. Experimental results are superior than the existing ones. Therefore, ANNPSO provides better testing results in Iris pattern classification problems.

Artificial Neural Network, Pattern Classification, Particle Swarm Optimization

[1] Kennedy James and Eberhart, Russell, “Particle swarm Optimizat-
ion”, in Proceedings of IEEE International Conference on Neural Networks, Volume 4,pp. 1942 -1948, 1995.
[2] R. A. Fisher, “The use of multiple measurements in taxonomic problems”, Annals of Eugenics, Volume 7 (2), pp.179-188, 1936.
[3] V. Borovinskiy, “Classification of Iris data set”, University of Ljubljana, Ljubljana, 2009.
[4] H. Chang and A. Astolfi, “Gaussian Based classification with application of the iris dataset”, In Proceedings of the 18th World Congress The International Federation of Automatic Control Milano (Italy) August 28 - September 2, 2011.
[5] V. Kumar and N. Rathee, “Knowledge discovery from database Using an integration of clustering and classification”, International Journal of Advanced Computer Science and Application, Volume 2, No.3,pp. 29-33, 2011.
[6] D. Dutta, A. Roy and K. Choudhury, “Trainning Aritificial Neural Network using Particle swarm Optimization Algorithms”, IJARCSSE , volume 3, Issue 3, pp. 430-434, 2013.
[7] S. Vyas 1 and D. Upadhyay, “Identification of Iris Plant Using Feed Forward Neural Network On The Basis Of Floral Dimensions”, IJIRSET, Volume 3, Issue 12, pp. 18200 - 18204 2014.
[8] Shashidhar T. Halakatti and Shambulinga T. Halakatti, “Identification Of Iris Flower Species Using Machine Learning”, International Journal of Computer Science, Volume 5, Issue 8, pp. 59-69, 2017.
[9] K. H. Wandra1 and L.P. Gagnani, “Classification Techniques in WEKA: A Review”, International Journal of Computer Sciences and Engineering,Volume 5, Issue 8, pp. 49-52, 2017.
[10] Mohan P.M, Paul N. K, Prakash M., Praveen K. D and Chidambaram S, “Comparative Evaluation of Various Techniques for Fisher’s Iris Classification”, International Journal of Innovative Research in Science, Engineering and Technology, Volume 7, Issue 1, pp. 198-202, 2018.
[11] D. E. Rumelhart, G. E. Hinton, and R. J. Williams, “Learning internal representations by error propagation”, in Parallel Distributed Processing: Explorations in the Microstructure of Cognition, Vol. 1, D. E. Rumelhart, J. L. McClelland, and PDP Research Group, Eds., pp. 318–362, MIT Press, Cambridge, Mass, USA, 1986.
[12] R C, Eberhart and Kennedy, James, “A New Optimizer Using Particle Swarm Theory”, MHS`95. Proc. Sixth Int. Symp. Micro Mach. Hum. Sci., pp.39 - 43, 1995.