DocumentCode :
2924441
Title :
Rule induction for tolerance relation-based rough sets
Author :
Meng, Jun ; Wang, Peng ; Wang, Xiukun ; Lin, Tsau Young
Author_Institution :
Sch. of Comput. Sci. & Technol., Dalian Univ. of Technol., Dalian, China
fYear :
2011
fDate :
8-10 Nov. 2011
Firstpage :
445
Lastpage :
450
Abstract :
Tolerance relation, derived partition, quotient set and named quotient space are very important concepts based on tolerance relations. In this paper, we review them at first. Then we present the construction of three spaces, namely, granular, quotient and knowledge spaces. We define the concepts of knowledge dependency in rough set models based on tolerance relations, such as weak dependency, strong dependency and central dependency, as well as the relationships among them. We present the process how to obtain the tolerance information table from knowledge base. An example is given to illustrate extracting rules from tolerance information table.
Keywords :
data mining; knowledge based systems; rough set theory; derived partition; knowledge base; knowledge dependency; named quotient space; quotient set; rough set models; rule induction; tolerance information table; tolerance relation; Approximation methods; Computed tomography; Data mining; Information systems; Knowledge based systems; Rough sets; Knowledge dependency; Rough set theory; Rule induction; Tolerance relation;
fLanguage :
English
Publisher :
ieee
Conference_Titel :
Granular Computing (GrC), 2011 IEEE International Conference on
Conference_Location :
Kaohsiung
Print_ISBN :
978-1-4577-0372-0
Type :
conf
DOI :
10.1109/GRC.2011.6122638
Filename :
6122638
Link To Document :
بازگشت