Two Step Ant Colony System to Solve the Feature Selection Problem

In this paper we propose a new model of ACO called Two-Step AntColony System. The basic idea is to split the heuristic search performed by ants into two stages. We have studied the performance of this new algorithm for the Feature Selection Problem. Experimental results obtained show the Two-Step approach significantly improves the Ant Colony System in term of computation time needed.

[1]  Luca Maria Gambardella,et al.  Ant Algorithms for Discrete Optimization , 1999, Artificial Life.

[2]  Lida Xu,et al.  Feature space theory - a mathematical foundation for data mining , 2001, Knowl. Based Syst..

[3]  Peter Vrancx,et al.  Using ACO and rough set theory to feature selection , 2005 .

[4]  M Dorigo,et al.  Ant colonies for the travelling salesman problem. , 1997, Bio Systems.

[5]  Andrzej Skowron,et al.  Rough-Fuzzy Hybridization: A New Trend in Decision Making , 1999 .

[6]  Hongbin Zhang,et al.  Feature selection using tabu search method , 2002, Pattern Recognit..

[7]  Mineichi Kudo,et al.  Comparison of algorithms that select features for pattern classifiers , 2000, Pattern Recognit..

[8]  Pavel Pudil,et al.  Feature selection toolbox , 2002, Pattern Recognit..

[9]  Marco Dorigo,et al.  Ant system: optimization by a colony of cooperating agents , 1996, IEEE Trans. Syst. Man Cybern. Part B.

[10]  Ravi Kothari,et al.  Feature subset selection using a new definition of classifiability , 2003, Pattern Recognit. Lett..

[11]  Pedro Larrañaga,et al.  Feature Subset Selection by Bayesian network-based optimization , 2000, Artif. Intell..

[12]  Rafael Bello,et al.  A model based on ant colony system and rough set theory to feature selection , 2005, GECCO '05.

[13]  Catherine Blake,et al.  UCI Repository of machine learning databases , 1998 .

[14]  Jerzy Stefanowski,et al.  An experimental evaluation of improving rule based classifiers with two approaches that change representations of learning examples , 2004, Eng. Appl. Artif. Intell..