论文信息 - A Study on Discriminant Analysis Based on Artificial Neural Networks

A Study on Discriminant Analysis Based on Artificial Neural Networks

This paper provides a method of discriminate analysis based on artificial neural network (ANN). 2-Class and multi-class discriminant analysis are separately discuss using Back Propagation network. The results of our study indicate that discriminate analysis based on ANN could classify the observation more accurately than the traditional methods.

[1] N. Lewis,et al. Comparison of Fisher's linear discriminant to multilayer perceptron networks in the classification of vapors using sensor array data , 2006 .

[2] Manoochehr Ghiassi,et al. Measuring effectiveness of a dynamic artificial neural network algorithm for classification problems , 2010, Expert Syst. Appl..

[3] Denis J. Dean,et al. Comparative accuracies of artificial neural networks and discriminant analysis in predicting forest cover types from cartographic variables , 1999 .

[4] Parag C. Pendharkar,et al. A threshold-varying artificial neural network approach for classification and its application to bankruptcy prediction problem , 2005, Comput. Oper. Res..

[5] Chih-Yang Tsai,et al. On detecting nonlinear patterns in discriminant problems , 2006, Inf. Sci..

[6] Parag C. Pendharkar,et al. A computational study on the performance of artificial neural networks under changing structural design and data distribution , 2002, Eur. J. Oper. Res..