Edge Based Graph Neural Network to Recognize Semigraph Representation of English Alphabets
Graph Neural Network based on edges is introduced in this paper and is used to recognize the English uppercase alphabets treating their corresponding graphs as semigraphs. Graph Neural Network(GNN) is a connectionist model comprising of two feedforward neural networks (FNN) called transition network and output network connected by recurrent architecture according to the graph topology. The characteristics of the edges in a graph are considered as input for the transition network and the stabilized output of the transition network are taken as input for the output network. Edge based GNN is trained using error gradient method. Experimental results show that GNN is able to identify all the 26 graphs of alphabets correctly.
KeywordsGraph neural network Graph structured data Feedforward network Recurrent network Semigraph
Unable to display preview. Download preview PDF.
- 1.Aribowo, A., Lukas, S., Handy : Hand written alphabet recognition using hamming network. Seminar Nasional Aplikasi Teknologi Informasi, G-1–G-5 (2007)Google Scholar
- 4.Dutt, V., Dutt, S.: Hand written character recognition using artificial neural network. Advances in Computing 1, 18–23 (2011)Google Scholar
- 7.Jeya Bharathi, S., Padmashree, J., Sinthanai Selvi, S., Thiagarajan, K.: Semigraph structure in DNA splicing system. In: Sixth International Conference on Bio-inspired Computing- Theories and Applications. IEEE Conf. publication 27-29 (2011)Google Scholar
- 10.Pradeep, J., Srinivasan, E., Himavathi, S.: Diagonal based feature extraction for hand written alphabet recognition system using neural network. In: IEEE Explore Digital Library, International Conference on Electronics Computer Technology, vol. 4, pp. 364–368 (2011)Google Scholar
- 11.Pucci, A., Gori, M., Hagenbuchner, M., Scarselli, F., Tsoi, A.C.: Applications of Graph neural networks to Large-Scale Recommender Systems some results. In: Proceedings of International Multiconference on Computer Science and Information Technology, pp. 189–195 (2006)Google Scholar
- 12.Reddy, S.K.D., Rao, S.A.: Hand written character recognition using back propagation network. Journal of Theoretical and applied Information Technology 5, 257–269 (2005)Google Scholar
- 13.Saha, S., Som, T.: Hand written character recognition by using neural network and Euclidean distance metric. International Journal of Computer Science and Intelligent Computing 2, 1–5 (2010)Google Scholar
- 14.Sampathkumar, E.: Semigraphs and their applications. Report on the DST(Department of Science and Technology) project submitted to DST, India (May 2000)Google Scholar
- 15.Scarselli, F., Yong, S.L., Gori, M., Hagenbuchner, M., Tsoi, A.C., Maggini, M.: Graph neural networks for ranking web pages. In: Proceedings of the 2005 IEEE/WIC/ACM Conference on Web Intelligence, Washington, DC, USA, pp. 666–672 (2005)Google Scholar
- 18.Venkatakrishnan, Y.B., Swaminathan, V.: Bipartite theory of semigraphs. WSEAS Trans. on Mathematics 11, 1–9 (2012)Google Scholar