Questions of handling unbalanced data considered in this article. As models for classification, PNN and MLP are used. Problem of estimation of model performance in case of unbalanced training set is solved. Several methods (clustering approach and boosting approach) considered as useful to deal with the problem of input data.
Keywords
unbalanced dataprobabilistic neural netmultilayer perceptronclassificationevaluation of performancepreparation of data
References
Basmanov M., Menshikov S., Morozov I., Strebkov A.,” System of parameter’s diagnostic of GTU: modern approach” Delovaya Rossia N7, 2011.-42-43 p. (In Russian)
Icamaan B. Viegas da Silva; Paulo J. L. Adeodato, “PCA and Gaussian noise in MLP neural network training improve generalization in problems with small and unbalanced data sets” Proceedings of International Joint Conference on Neural Networks, San Jose
Robert E. Schapire, “The Strength of Weak Learnability” Machine Learning, 5(2):197–227, 1990
Statsoft program "Statistica". [Online]. Available: http://www.statsoft.ru/
Dolina O.N. and Kyzmin A.K. Particularities of developing expert systems based on neural net modeling” Journal of Saratov technic state university, 2009.-266-272 p. (In Russian)
S. Sathyanarayana, “A gentle introduction to backpropagation”, July 22, 2014
Specht, D. F. "Probabilistic neural networks". Neural Networks 3:1990.- 109–118 p.
A.I. Gavrilov and P.V. Evdokimov, “Neural Network optimum parameters determining under industrial process mathematical model construction” Vestnik of ISPU N4, 2007 (In Russian)
·
This work is licensed under a
Creative Commons Attribution-ShareAlike 4.0 International License
