Email this article 
Open Access
Subscription or Fee Access
Comparison of LIF and Izhikevich Spiking Neural Models for Recognition of Uppercase and Lowercase English Characters
Abstract
This paper depicts pattern classification of uppercase and lower case English character, using Leaky integrated and fire neuron model and Izhikevich neuron model of spiking neural network. Spiking neural network is one of the best artificial neural networks, which are widely used in the field of neuron science. In this paper we focused on spiking mechanism of both models and compare them in terms of accuracy and simulation time.
Leaky integrate and fire neuron model which is one of the simple and efficient model of spiking neural network that analyze and simulate efficiently. On the other hand Izhikevich model is one of the powerful models which can simulate thousands of neurons in real time. Using these two models simulation results are obtained for recognition of uppercase and lower case English characters. Finally we report on simulation results of both models and discuss their performance, in terms of recognition rate and speed.
Keywords
References
Soni Chaturvedi, Neha R. Sondhiya, Rutika N. Titre, “Izhikevich Model Based Pattern Classifier for Hand Written Character Recognition-A ReviewAnalysis“atICESC2014,IEEEExplore,DOI-10.1109/ICESC2014,65 in SPEC accNo.14117533,page346-349 .
Ankit Sharma, Dipti R. Chaudhary, “ Character Recognition Using Neural Network” at International Journal of Engineering trends and Technology, IJETT volume 4 Issue 4 April 2013.
Kauleshwar Prasad, Devrat C. Nigam, Ashmika Lakhotiya , Dheeren Umere,“ Character Recognition Using MATLAB’s Neural Network Toolbox” at International journal of u and e service, Science and technology vol.66,No.1,February 2013.
Soni Chaturvedi, Maftah Boudjelal, A.A.Khurshid, “Image Segmentation Using Leaky Integrated and Fire Model of Spiking Neural Network” International Journal of Wisdom Based Computing, vol 2(1) , April 2012.
Sameeksha Brave, “Artificial Neural Network Based on Optical Character Recognition “at International Journal of Engineering Research and Technology. IJERT, ISSN: 2278-0181, vol.1Issue4.June 2012.
Soni Chaturvedi, A.A.Khurshid, Meftah Boadjelal,“Review Analysis Of Pattern Recognition by Neural Network “at Trends in Innovative Computing 2012-Pattern Recognition.
Vinita Dutt, Sunil Dutt, “ Hand Written Character Recognition Using Artificial Neural Network” Advance in Computing :2011;1(1):18-23 DOI:10.5923/j.ac.20110101.03.
Stuti Astana, Farah Haneef, Rakesh K. Bhijade“Hand Written Multiscript Numeral Recognition using Artificial Neural Networks” at International Journal of Soft Computing and Engineering , IJSCE ISSN: 2231-2307, volume1, Issue-1, March2011.
Sonu Nobukawa, Haruhiko Nishimura Teruga Yamanish, Jian-Qinliu, “Signal Response Efficiency in Izhikevich neuron model” at SICE Annual Conference 2011 p. 13-18 , wasela university, Tokyo Japan .
Eugene M. Izhikevich, “Hybrid Spiking Models” at Phil.Trans.R.Soc A (2010) 368, 5061-5070 doi:10.1098/rsta.2010.0130.
Kira Radinsky, Michael Galdish, “Pavilovian and Instrumental Conditioning in Spiking Neural Network” Techno Israel Institute of Technology Haifa3200, Israel, Unpublished.
A.N.Burkitt,. “A Review Analysis of Integrated and Fire neuron Model: I. Homogeneous Synaptic Input” at Biol Cybern (2006) 95:1.19, Received: 2August 2005 / Accepted: 20 March2006 / published online: 19 April 2006, Springer-Verlag 2006.
Eugene M. Izhikevich, “Which Model to Use for Cortical Spiking Neurons?” at IEEE transactions on neural network, vol.15, No. 5, September 2004.
Eugene M. Izhikevich, “ Simple Model of Spiking Neurons” at IEEE Transactions on neural networks,Vol.14 , No. 6 , November 2003.
Vamsi K.Madaasu, Brian C. Lovell, M.Hanmandlu,” Hand Printed Character Recognition Using Neural Network” at au/ eserv / UQ8573/ICCK espace library.uq.edu.
Ankur Gupta, Lyle N. Long, “Character Recognition Using Spiking Neural Network”, at IEEE Neural Network Conference Orlando FL August 2007.
Refbacks
- There are currently no refbacks.
This work is licensed under a Creative Commons Attribution 3.0 License.