J4

• 计算机科学 • Previous Articles     Next Articles

CORS Methodology and Rule Generation Algorithm GRs

SUN Chengmin, LIU Dayou, SUN Shuyang   

  1. College of Computer Science and Technology, Jilin University, Changchun 130012, China; Key Laboratory of Symbolic Computation and Knowledge Engineering of Ministry of Education, Jilin University, Changchun 130012, China
  • Received:2006-01-09 Revised:1900-01-01 Online:2006-11-26 Published:2006-11-26
  • Contact: LIU Dayou

Abstract: Based on preference order information carried by criteria and dominance relation between them, deduction of ordered information rules was solved. New rule generation algorithm GRs was proposed and a simple comparison with other algorithms was carried out. The rules are generated from strong to weak according to strength of rules’consequent. The algorithm ensures the minima lity of rules. In some degree, the rule set is complete and nonredundant. Corresponding definition and notation, data analysis method, rule types on Containing Order Rough Set Methodology (CORS) are introduced also.

Key words: criteria, dominance relation, containing order rough set methodology, rules generation algorithm, completeness

CLC Number: 

  • TP18