Scholarlink

<p>This paper develops a novel heterogeneous simultaneous evaluation of criteria and alternatives method based on disappointment theory for handling multi-attribute decision-making problems with qualitative and quantitative information and disappointment-averse decision-makers (DMs). First, to characterize heterogeneous information, we employ intuitionistic fuzzy sets, 2D uncertain linguistic variables, linguistic distributions, and interval values to represent fuzzy and uncertain evaluation information. Then, building on this foundation, we propose a heterogeneous disappointment-elation utility function to compute the comprehensive performance values for all alternatives, quantifying DMs’ aversion to unfavorable outcomes. Furthermore, an innovative multi-objective mathematical programming model is formulated to maximize the comprehensive performance values while minimizing discrepancies between both metrics and attribute weights, thereby determining optimal weights and deriving the ranking. Finally, within physician selection case study, the method’s robustness and superiority are demonstrated through experimental, sensitivity, and comparative analyses.</p>

错误：搜索内容不能为空，请输入英文关键词
错误：关键词超出字数限制，请精简
高级检索

A Novel Heterogeneous SECA Method with Disappointment Aversion for Multi-attribute Physician Selection

  • 期刊论文

  • 发表日期：

    2026年3月9日

查看全文
  • Jizheng Wang,
  • Guolin Tang,
  • HuaJie Wang,
  • Peide Liu

摘要

This paper develops a novel heterogeneous simultaneous evaluation of criteria and alternatives method based on disappointment theory for handling multi-attribute decision-making problems with qualitative and quantitative information and disappointment-averse decision-makers (DMs). First, to characterize heterogeneous information, we employ intuitionistic fuzzy sets, 2D uncertain linguistic variables, linguistic distributions, and interval values to represent fuzzy and uncertain evaluation information. Then, building on this foundation, we propose a heterogeneous disappointment-elation utility function to compute the comprehensive performance values for all alternatives, quantifying DMs’ aversion to unfavorable outcomes. Furthermore, an innovative multi-objective mathematical programming model is formulated to maximize the comprehensive performance values while minimizing discrepancies between both metrics and attribute weights, thereby determining optimal weights and deriving the ranking. Finally, within physician selection case study, the method’s robustness and superiority are demonstrated through experimental, sensitivity, and comparative analyses.