| IMPROVEMENTS TO THE CLASSIFICATION PERFORMANCE OF RDA |
| |
| 作者姓名： | STEFANAEBERHARD DANNYCOOMANS OLIVIERDEVEL |
| |
| 作者单位： | Department of Computer Science Department of Mathematics and Statistics，James Cook University，Townsville，QLD 4811，Australia，Department of Computer Science，Department of Mathematics and Statistics，James Cook University，Townsville，QLD 4811，Australia，Department of Computer Science，Department of Mathematics and Statistics，James Cook University，Townsville，QLD 4811，Australia |
| |
| 摘 要： | Regularized discriminant analysis has proven to be a most effective classifier for problems wheretraditional classifiers fail because of a lack of sufficient training samples,as is often the case in high-dimensional settings.However,it has been shown that the model selection procedure of regularizeddiscriminant analysis,determining the degree of regularization,has some deficiencies associated with it.We propose a modified model selection procedure based on a new appreciation function.By means ofan extensive simulation it was shown that the new model selection procedure performs better than theoriginal one.We also propose that one of the control parameters of regularized discriminant analysis beallowed to take on negative values.This extension leads to an improved performance in certain situations.The results are confirmed using two chemical data sets.
|
IMPROVEMENTS TO THE CLASSIFICATION PERFORMANCE OF RDA |
| |
| STEFANAEBERHARD,DANNYCOOMANS,OLIVIERDEVEL.IMPROVEMENTS TO THE CLASSIFICATION PERFORMANCE OF RDA[J].Journal of Geographical Sciences,1993(2). |
| |
| Authors: | STEFAN AEBERHARD DANNY COOMANS OLIVIER DE VEL |
| |
| Institution: | STEFAN AEBERHARD DANNY COOMANS OLIVIER DE VEL Department of Computer Science,Department of Mathematics and Statistics,James Cook University,Townsville,QLD,Australia |
| |
| Abstract: | Regularized discriminant analysis has proven to be a most effective classifier for problems where traditional classifiers fail because of a lack of sufficient training samples,as is often the case in high- dimensional settings.However,it has been shown that the model selection procedure of regularized discriminant analysis,determining the degree of regularization,has some deficiencies associated with it. We propose a modified model selection procedure based on a new appreciation function.By means of an extensive simulation it was shown that the new model selection procedure performs better than the original one.We also propose that one of the control parameters of regularized discriminant analysis be allowed to take on negative values.This extension leads to an improved performance in certain situations. The results are confirmed using two chemical data sets. |
| |
| Keywords: | Classification Appreciation function Regularized discriminant analysis |
| 本文献已被 CNKI 等数据库收录！ |
| 点击此处可从《地理学报(英文版)》浏览原始摘要信息 |
| 点击此处可从《地理学报(英文版)》下载免费的PDF全文 |
