Rough Sets and Colonies of Artificial Ants for the Improvement of Training Sets

Improving training sets is an area of active research within l to Artificial Intelligence. In particular, it is of particular interest in supervised classification systems, where the quality of training data is crucial. This paper presents a new method for the improvement of training sets, based on approximate sets and artificial ant colonies. The experimental study carried out with international databases allows us to guarantee the quality of the new algorithm, which has a high efficiency.