Identifying Datasets by Pattern Recognition Techniques using Neural Networks

Authors

  • Bosubabu Sambana Assistant Professor, Dept.of CSE, Avanthi’s Research Technological Academy, Jawaharlal Nehru Technological University - Kakinada, Andha Pradesh, India

DOI:

https://doi.org/10.51983/ajcst-2017.6.1.1774

Keywords:

Pattern Recognition, Hopfield network, Back Propagation Network, Training Set, Fault Tolerance

Abstract

The process of Pattern Recognition neural network is found to be an effective tool. Different combinations of neural networks are used for this technique. Earlier works are based on only back propagation network but the proposed work is based on the combination of Hopfield network and Back propagation network. The success rate for recognizing known and unknown pattern is relatively very high with this combination of networks when compare to other techniques. As the fault tolerance of the Hopfield network is more than back propagation so required percentage accuracy of output of the new combined network should be more as compared to only back propagation network. The objective of the neural network is to transform the inputs into meaningful outputs. The signals are transmitted by the means of connections links. It is inspired by the character set nervous connected system. We proposed new techniques for better character set reorganization using various implementation methods evolution analysis and identification needs. It is very helpful and vast scope for future research.

References

H. A. Al Hamad, "Use an Efficient Neural Network to Improve the Arabic Handwriting Recognition," in International Conference on Systems, Control, Signal Processing and Informatics, pp. 269-274, 2013.

K. Prasad, D. C. Nigam, A. Lakhotiya, and D. Umre, "Character Recognition using Matlab’s Network Toolbox," in International Journal Service, Science and Technology, vol. 6, no. 1, pp. 2013.

Y. Shi, W. Fan, and G. Shi, "The Research of Printed Character Recognition Based on Neural Network," in International Symposium on Parallel Architectures, Algorithms and Programming, pp. 119-122, 2011.

B. P. Chacko, V. Krishnan, and G. Raju, "Handwritten character recognition using wavelet energy and extreme learning machine," in International Journal of Machine Learning and Cybernetics, vol. 3, no. 2, pp. 149-161, June 2012.

F. Kurniawan, M. S. M. Rahim, N. Sholihah, A. Rakhmadi, and D. Mohamad, "Characters Segmentation of Cursive Handwritten Words based on Contour Analysis and Neural Network Validation," in ITB J. ICT, vol. 5, no. 1, 2011.

J. K. Basu, D. Bhattacharyya, and T. Kim, "Use of Artificial Neural Network in Pattern Recognition," in International Journal of Software Engineering and Its Applications, vol. 4, no. 2, April 2010.

D. Qi, P. Zhang, X. Jin, and X. Zhang, "Study on Wood Image Edge Detection Based on Hopfield Neural Network," in Proceedings of the International Conference on Information and Automation, pp. 1942-1946, IEEE, 2010.

Z. Ahmad, J. K. Orakzai, I. Shamsher, "Urdu compound Character Recognition using feed forward neural networks," in 2nd IEEE International Conference on Computer Science and Information Technology, pp. 457-462, 2009.

M. P. Singh, V. S. Dhaka, "Handwritten Character Recognition Using Modified Gradient Descent Technique of Neural Networks and Representation of Conjugate descent For Training Patterns," in IJE Transactions A: Basics, vol. 22, no. 2, June 2009.

A. G. Kothari, A. G. Keskar, A. Gokhale, R. Deshpande, P. Deshmukh, "Rough Set Approach for Feature Reduction in Pattern Recognition through Unsupervised Artificial Neural Network," in Emerging Trends in Engineering and Technology, ICETET '08. First International Conference on 16-18 July 2008, pp. 1196-1199, 2008.

All images & Related Information - https://www.google.com/

Downloads

Published

23-05-2017

How to Cite

Sambana, B. (2017). Identifying Datasets by Pattern Recognition Techniques using Neural Networks. Asian Journal of Computer Science and Technology, 6(1), 34–39. https://doi.org/10.51983/ajcst-2017.6.1.1774