Yeast is among the various important components for the formulation of medicine and various chemical products, so yeast data classification is an important bioinformatics task. Yeast data classification has been approached by various machine learning techniques for last few years. In this paper, an artificial neural network system with back propagation training algorithm is presented with different training functions for the classification of yeast dataset. Here an effort has been made to decide the suitable training functions of artificial neural network system for the classification of yeast protein. The training functions that have been used are, respectively, Batch Training, Batch Gradient Descent, Gradient Descent with momentum, Resilience back propagation, One-step secant back propagation, Scaled Conjugate back propagation, Conjugate Gradient back propagation with Polak-Riebre updates (CGP) and Conjugate Gradient back propagation with Fletcher-Reeves updates (CGF), BFGS and Levenberg-Marquardt training algorithm . The yeast dataset used for this purpose has been chosen and from UCI machine learning repository. The performance of the classification network has been tested by various performance measures like correctness of classification, mean square error, and regression analysis.

Yeast Dataset Classification, Back Propagation Artificial Neural Network, Training Function Of Artificial Neural Network

[1] BB. Alberts, D. Bray, J. Lewis, M. Raff, K. Roberts, J.D. Watson, Molecular Biology of the Cell, Garland, New York, 1994.
[2] Shavlik, J., Hunter, L. &Searls, D. (1995).Introduction. Machine Learning, 21: 5-10.
[3] Nakai, K., Kanehisa, M.: Expert system for predicting protein localization sites in gram-negative bacteria. Proteins: Structure, Function, and Genetics.11,95-110 (1991).
[4] Nakai, K., Kanehisa, M.: A knowledge base for predicting protein localization sites in eukaryotic cells. Genomics. 14, 897-911 (1992).
[5] Horton, P., Nakai, K.: A probabilistic classification system for predicting the cellular localization sites of proteins. In :Proceedings of Intelligent Systems in Molecular Biology, pp 109-115. St. Louis, USA (1996).
[6] Horton, P. ,Nakai, K.: Better prediction of protein cellular localization sites with the k Nearest Neighbors classifier, pp. 147-152. AAAI Press. Halkidiki, Greece (1997).
[7] Yetian Chen, Predicting the Cellular Localization Sites of Proteins Using Decision Tree and Neural Networks, http://www.cs.iastate.edu/~yetianc/cs572/files/CS572_Project_YETIANCHEN.pdf.unpublished.
[8] Support Vector Machine with the Fuzzy Hybrid Kernel for Protein Subcellular Localization Classification ";Bo Jin, Yuchun Tang, Yan-Qing Zhang, Chung-Dar Lu and Irene Weber; The 2005 IEEE International Conference on Fuzzy Systems;pages 420-423.
[9] M. Barman,Dr. J Palchoudhury, S. Biswas,"A Framework for the Neuro Fuzzy Rule Base System in the diagonosis of heart disease", International journal of Scientific and Engineering Research,vol-4,Issue 11,November 2013.
[10] S.Datta,Dr. J Palchoudhury,"A Comparative Study on the Performance of Fuzzy Rule Base andArtificial Neural Network towards Classification of Yeast Data",International Journal of Information Technology and Computer science,in press.
[11] S.Datta,Dr. J Palchoudhury,"A Framework for Selection of Membership function using Fuzzy Rule Base System for the Classification of Yeast Data", Proceeding of international conference on Emerging trends in Computer science and Information Technology(ETCSIT 2015),Department of Information Technology,KalyaniGovernment Engineering College,West Bengal,India.January,2015.
[12] UCI machine learning repository, :http://archive.ics.uci.edu/ml.