Output details
11 - Computer Science and Informatics
University of Kent
cAnt-Miner: An Ant Colony Classification Algorithm to Cope with Continuous Attributes
<24> This paper proposes the first version of the Ant-Miner classification algorithm capable of dealing with continuous attributes. Many variations of the Ant-Miner algorithm (2002) have been proposed since the original highly influential paper, but until this publication all of those had the limitation of coping only with categorical (not continuous) attributes. After six years, this paper enabled ant colony classification algorithms to be used in new domains: e.g. gene expression data analysis and stock market trend prediction. The paper was published in the main international conference on Swarm Intelligence (acceptance rate of full papers: 18%).