Paper Details

[ Downloads: 0 | Abstract Viewed: 632 | Pages: 5 ]

Abstract of the Article

Note: English CIVILICA is in its Trial Period so Full Texts can not be provided! Persian users can download it here

Improving Classification accuracy and Solving Trace Ratio Problem simultaneously with use of Ant colony optimization

Authors:

[ Saman Poursiah navi ] - Department of Computer Engineering, Islamic Azad University-Quchan branch, Quchan, Iran
[ Hossein moeenzadeh ] -
[ Ehsan asgarian ] -

Abstract:

The selection of a classifier is only one aspect of the problem of data classification. Equally important (if not, more so) is the pre-processing strategy to be employed. In this paper, a pre-processing step is proposed in order to increase accuracy of classification. The objective of this pre-processing step is to achieve a high degree of separation among classes before the classifier is trained or tested. This results into a trace ratio problem which is difficult to solve. Methods such as Linear Discriminant Analysis (LDA) have already been used for the solution of this problem by turning it into a simpler yet inexact problem. In our approach ACO is used to solve the trace ratio problem directly also can increase classification accuracy by finding a transformation matrix to discriminate between classes.

Keywords:

Linear Discriminant Analysis; Pre-processing; Classification; GeneticAlgorithm; AntClonyOptimization