Using a rough set model to extract rules in dominance-based interval-valued intuitionistic fuzzy information systems

  • Authors:

  • Bing Huang;Da-Kuan Wei;Hua-Xiong Li;Yu-Liang Zhuang

  • Affiliations:

  • School of Information Sciences, Nanjing Audit University, Nanjing 211815, PR China and Information Systems Auditing Experimental Center, Nanjing Audit University, Nanjing 211815, PR China;School of Information Engineering, Hunan Science and Technology University, Yongzhou 425100, PR China;School of Engineering and Management, Nanjing University, Nanjing 210093, PR China;School of Information Sciences, Nanjing Audit University, Nanjing 211815, PR China and Information Systems Auditing Experimental Center, Nanjing Audit University, Nanjing 211815, PR China

  • Venue:
  • Information Sciences: an International Journal
  • Year:
  • 2013

Quantified Score

Hi-index 0.07

Visualization

Abstract

Interval-valued intuitionistic fuzzy information systems are generalizations of conventional fuzzy-valued information systems. We introduce a dominance relation in the framework of interval-valued intuitionistic fuzzy information systems to come up with the concept we call a dominance-based interval-valued intuitionistic fuzzy information system (DIIFIS). This system is used to establish a dominance-based rough set model, which is grounded primarily on the substitution of the indiscernibility relation in the classic rough set theory with the aforementioned dominance-based relation. This relation is defined by the score and accuracy of interval-valued intuitionistic fuzzy value. To simplify knowledge representation and extract useful and simple dominance-based interval-valued intuitionistic fuzzy rules, we present two attribute reduction approaches to eliminating redundant information. To demonstrate the potential of these approaches, we apply them to computer auditing risk assessment, decision-making problems in wealth management, and pattern classification. Our findings confirm that the proposed rough set model is an effective means of extracting knowledge from dominance-based interval-valued intuitionistic fuzzy information systems.