Title: Directed clonal selection algorithm for associative classification

Authors: Lihua Zhao; Jin Pan

Addresses: Key Lab of Intelligent Perception and Image Understanding of Ministry of Education, Xidian University, Wangqu Town, Changan Area, Xian City, Shaanxi Province, 710106, China ' Key Lab of Intelligent Perception and Image Understanding of Ministry of Education, Xidian University, Wangqu Town, Changan Area, Xian City, Shaanxi Province, 710106, China; Xian Communication Institute, Wangqu Town, Changan Area, Xian City, Shaanxi Province, 710106, China

Abstract: In this paper, we present an directed clonal selection algorithm (DCLONALG) for mining association rules. Different from the traditional evolutionary algorithms, DCLONALG firstly scans dataset one time to find frequent rules with only one item. Then, these items were used to generate new rules and the mutation operation was limited in it. We evaluate the performance of the proposed DCLONALG approach for AC and the performance results have shown that the proposed approach is efficient in dealing with the problem on the complexity of the rule search space. At the same time, good classification accuracy has been achieved. This is especially important for mining association rules from large datasets in which the search space of rules is huge.

Keywords: clonal selection algorithm; directed CLONALG; artificial immune systems; AIS; associative classification; evolutionary computation; mining association rules; classification accuracy.

DOI: 10.1504/IJMIC.2013.052815

International Journal of Modelling, Identification and Control, 2013 Vol.18 No.3, pp.218 - 225

Published online: 16 Aug 2014 *

Full-text access for editors Full-text access for subscribers Purchase this article Comment on this article