Back Propagation Based Firefly Algorithm for Character Recognition
AbstractBack Propagation (BP) in neural networks is a common technique used for character recognition which compute the output using feed forward network, calculate and back propagate the error signal through the network. The performance of back propagation falls off rapidly into local minima and suffers from slow convergences. To overcome this, back propagation is combined with other search algorithms such as genetic algorithm, firefly algorithm, particle swarm optimization, etc. The firefly algorithm which has advantage of high convergence rate and each firefly individually finds global optima in less number of iterations. In proposed work, firefly algorithm is combined with back propagation for character recognition.
Li Fuliang, Gao Shuangxi, (2010) â€™Character Recognition System Based on Back-propagation Neural Networkâ€™, International Conference on Ma-chine Vision and Human-machine Interface, China, 978-0-7695-4009-2/10.
M Abdul Rahiman, M S Rajasree, (2009) â€™Printed Malayalam Character Recognition Using Back-propagation Neural Networksâ€™, IEEE Interna-tional Advance Computing Conference, India, 978-1-4244-2928-8/09.
Lina Liu, Huijuan Qi, Jia Liu, (2012) â€™The Research of Alphabet Identi-fication Based on Genetic BP Neural Networkâ€™, International Conference on Intelligent Human-Machine Systems and Cybernetics.
Gill.J, Singh.B, Singh.S, (2010) â€™Training Back Propagation Neural Networks with Genetic Algorithm for Weather Forecastingâ€™, Intelligent Systems and Informatics, 8th International Symposium.
Cao Bu-Qing, Liu Jian-xun, (2010) â€™Currency Recognition Modelling Research Based on BP Neural Network Improved by Gene Algorithmâ€™, Cambridge, MA: MIT Press, 2nd International Conference.
Jiao Aihong, Yuan Lizhe, (2012) â€™City Fire Risk Assessment Model Based on the Adaptive Genetic Algorithm and BP Networkâ€™, International Conference on Industrial Control and Electronics Engineering.
Noraini Mohd Razali, John Geraghty (2011) â€™Genetic Algorithm Perfor-mance with Different Selection Strategies in Solving TSPâ€™, Proceedings of the World Congress on Engineering,U.K, Vol. 02.
Mohammad Hamdan, (2010) â€™On The Disruption-Level Of Polynomial Mutation For Evolutionary Multi-Objective Optimization Algorithmsâ€™ , Jordan, pp.783800.
F. Herrera, M. Lozano, A. M. Sa nchez, (2003) â€™A Taxonomy for the Crossover Operator for Real-Coded Genetic Algorithms: An Experimental Studyâ€™, Spain, Vol. 18, pp. 309338.
Garima Singh, Laxmi Srivastava â€™Genetic Algorithm-Based Artificial Neural Network for Voltage Stability Assessmentâ€™, Hindawi Publishing Corporation, Advances in Artificial Neural Systems Volume 2011, Article ID 532785.
Sudarshan Nandy, Partha Pratim Sarkar, Achintya Das, (2012) â€™Analysis of a Nature Inspired Firefly Algorithm based Back-Propagation Neural Network Trainingâ€™, International Journal of Computer Applications.
Luthra.J, Pal.S.K, (2011) â€™A Hybrid Firefly Algorithm using Genetic Operators for the Cryptanalysis of a Monoalphabetic Substitution Cipherâ€™, Information and Communication Technologies (WICT), World Congress.
Theofanis Apostolopoulo, Aristidis Vlachos, (2011) â€™Application of the Firefly Algorithm for Solving the Economic Emissions Load Dispatch Problemâ€™, Greece, doi:10.1155/2011/523806.
The submitter hereby warrants that the Work (collectively, the “Materials”) is original and that he/she is the author of the Materials. To the extent the Materials incorporate text passages, figures, data or other material from the works of others, the undersigned has obtained any necessary permissions. Where necessary, the undersigned has obtained all third party permissions and consents to grant the license above and has all copies of such permissions and consents.
The submitter represents that he/she has the power and authority to make and execute this assignment. The submitter agrees to indemnify and hold harmless the COMPUSOFT from any damage or expense that may arise in the event of a breach of any of the warranties set forth above. For authenticity, validity and originality of the research paper the author/authors will be totally responsible.