Classification Using Unstructured Rules and Ant Colony Optimization
Negar Zakeri Nejad, Amir Hoshang Bakhtiary, Morteza Analoui · 2008
Abstract—In this paper a new method based on the Ant-Miner algorithm is proposed to discover sets of unstructured classification rules. This method, called the Tree-Miner, creates a directed graph made up of nodes representing operators and operands. Each ant in a colony of artificial ants traverses this graph to find routes that represent the best unstructured rule antecedents. These antecedents are used to classify the given data and are also interpreted as knowledge hidden in the training data. The performance of the Tree-Miner algorithm was evaluated against that of the Ant-Miner according to the accuracy and the simplicity of the constructed rules. The results showed that our method has an acceptable predictive accuracy while discovering rules that are simpler and more comprehensive. Index Terms—Ant Colony Optimization, rule based classifiers, unstructured rules.