Strategy selection under entropy measures in movement-based three-way decision
作者: Chunmao JiangDoudou GuoYing DuanYue Liu
作者单位: 1College of Computer Science and Information Engineer, Harbin Normal University, Harbin, Heilongjiang Province, 150025, China
2Department of Computer Science, University of Regina, Regina, Saskatchewan, S4S 0A2, Canada
刊名: International Journal of Approximate Reasoning, 2020, Vol.119 , pp.280-291
来源数据库: Elsevier Journal
DOI: 10.1016/j.ijar.2020.01.013
关键词: Trisecting-acting-outcomeThree-way decisionProbabilistic movement modelCross entropyConditional entropy
原始语种摘要: Abstract(#br)The trisecting-acting-outcome (TAO) model of three-way decisions comprises three components, i.e., constructing a trisection, strategies for action, and measuring the outcome. Existing research seldom involves the third component, i.e., measuring the effectiveness of the outcome. A previous study provides a strategy select method by analyzing benefits or costs in the movement-based three-way decision. However, we often choose a strategy depend on the probability or distribution of three regions instead of the benefits or costs. In this paper, we propose a probabilistic movement model of three-way decision and give a strategy selection mechanism based on information entropy. Conditional entropy and cross entropy are used to select strategies by measuring these probabilities...
全文获取路径: Elsevier  (合作)

  • entropy 平均信息量
  • decision 决定
  • three 
  • selection 选择
  • strategy 战略
  • probabilistic 概率的
  • movement 运动
  • costs 费用
  • based 基于
  • expected 预期