Mining Hierarchical Decision Rules from Hybrid Data with Categorical and Continuous Valued Attributes  

作　　者：MIAO Duo-qian QIAN Jin LI Wen ZHANG Ze-hua 

机构地区：[1]Department of Computer＇Science and Technology, Tongji University, Shanghai 201804, China [2]College of Computer Engineering, Jiangsu Teachers University of Technology, Changzhou 213015, China [3]Key Laboratory of Embedded System and Service Computing, Ministry of Education of China, Tongji University, Shanghai 201804, China

出　　处：《浙江海洋学院学报（自然科学版）》2010年第5期420-427,共8页Journal of Zhejiang Ocean University(Natural Science Edition)

基　　金：The research was supported by the National Natural Science Foundation of China under grant No:60775036, 60970061;the Higher Education Nature Science Research Fund Project of Jiangsu Province under grant No: 09KJD520004.

摘　　要：Decision rules mining is an important issue in machine learning and data mining.However,most proposed algorithms mine categorical data at single level,and these rules are not easily understandable and really useful for users.Thus,a new approach to hierarchical decision rules mining is provided in this paper,in which similarity direction measure is introduced to deal with hybrid data.This approach can mine hierarchical decision rules by adjusting similarity measure parameters and the level of concept hierarchy trees.Decision rules mining is an important issue in machine learning and data mining.However,most proposed algorithms mine categorical data at single level,and these rules are not easily understandable and really useful for users.Thus,a new approach to hierarchical decision rules mining is provided in this paper,in which similarity direction measure is introduced to deal with hybrid data.This approach can mine hierarchical decision rules by adjusting similarity measure parameters and the level of concept hierarchy trees.

关 键 词：Similarity relation Attribute reduction Hierarchical decision rules Hybrid data 

分 类 号：TP18[自动化与计算机技术—控制理论与控制工程]