A rule induction algorithm in incomplete decision table based on attribute order

Article type: Research Article

Authors: Guan, Lihe^{a; *} | Hu, Feng^b | Han, Fengqing^a

Affiliations: [a] School of Mathematics and Statistics, Chongqing Jiaotong University, Chongqing, P.R. China | [b] Chongqing Key Laboratory of Computational Intelligence, Chongqing University of Posts and Telecommunications, Chongqing, P.R. China

Correspondence: [*] Corresponding author. Lihe Guan, School of Mathematicsand Statistics,Chongqing Jiaotong University, Chongqing 400074, P.R. China. Tel.: +86 023 62652254; E-mail: guanlihe@cqjtu.edu.cn.

Abstract: In data mining, many real-life data sets are not only incomplete, but also encompass various kinds of knowledge and are shared by many users. Different users may prefer different kinds of knowledge. Nowadays how to mine rules meeting users’ requirements from incomplete data sets has become one of the important research issues of data mining. In this paper, we investigate decision rules induction methods in incomplete decision tables by considering attribute order. The users’ requirements are described by an attribute order. Then a hierarchical algorithm of decision rules mining based on the attribute order is proposed, and its properties and complexity are examined. An example is given to illustrate the algorithm. Simulation experimental results show that compared with the algorithm MLEM2, the proposed algorithm is valid and effective.

Keywords: Data mining, rough set, incomplete decision table, knowledge discovery

DOI: 10.3233/IFS-151818

Journal: Journal of Intelligent & Fuzzy Systems, vol. 30, no. 2, pp. 961-969, 2016