Skip to main content
QUICK REVIEW

[论文解读] Perceptual reasoning based solution methodology for linguistic optimization problems

Prashant Gupta, Pranab K. Muhuri|arXiv (Cornell University)|Apr 30, 2020
Multi-Criteria Decision Making参考文献 26被引用 5
一句话总结

本文提出了一种基于感知推理(PR)的解决方案方法,用于语言优化问题(LOPs),在计算词汇(CWW)框架内利用区间直觉2型模糊集,以更好地建模语言语义。该方法将感知推理从单目标扩展到多目标LOPs,通过一种新颖的CWW引擎,克服了现有2-元组模型和Tsukamoto推理的局限性,提高了处理人类语言输入和约束的准确性。

ABSTRACT

Decision making in real-life scenarios may often be modeled as an optimization problem. It requires the consideration of various attributes like human preferences and thinking, which constrain achieving the optimal value of the problem objectives. The value of the objectives may be maximized or minimized, depending on the situation. Numerous times, the values of these problem parameters are in linguistic form, as human beings naturally understand and express themselves using words. These problems are therefore termed as linguistic optimization problems (LOPs), and are of two types, namely single objective linguistic optimization problems (SOLOPs) and multi-objective linguistic optimization problems (MOLOPs). In these LOPs, the value of the objective function(s) may not be known at all points of the decision space, and therefore, the objective function(s) as well as problem constraints are linked by the if-then rules. Tsukamoto inference method has been used to solve these LOPs; however, it suffers from drawbacks. As, the use of linguistic information inevitably calls for the utilization of computing with words (CWW), and therefore, 2-tuple linguistic model based solution methodologies were proposed for LOPs. However, we found that 2-tuple linguistic model based solution methodologies represent the semantics of the linguistic information using a combination of type-1 fuzzy sets and ordinal term sets. As, the semantics of linguistic information are best modeled using the interval type-2 fuzzy sets, hence we propose solution methodologies for LOPs based on CWW approach of perceptual computing, in this paper. The perceptual computing based solution methodologies use a novel design of CWW engine, called the perceptual reasoning (PR). PR in the current form is suitable for solving SOLOPs and, hence, we have also extended it to the MOLOPs.

研究动机与目标

  • 解决现有方法(如Tsukamoto推理和2-元组语言模型)在处理语言优化问题(LOPs)时的局限性。
  • 通过用区间直觉2型模糊集替代类型1模糊集和序数术语集,改进语言信息的语义表示。
  • 为单目标语言优化问题(SOLOPs)开发一种基于感知推理(PR)的解决方案方法。
  • 将感知推理框架扩展至处理多目标语言优化问题(MOLOPs)。
  • 在目标和约束以自然语言表达的真实场景中,提升决策能力。

提出的方法

  • 采用基于感知推理(PR)的计算词汇(CWW)方法,以建模语言输入和约束。
  • 设计一种新颖的CWW引擎,利用区间直觉2型模糊集,比2-元组模型更准确地表示语言术语的语义。
  • 利用if-then规则连接LOPs中的目标函数和约束,其中目标值在所有决策点均未知。
  • 通过结构化的推理机制处理语言输入,应用感知推理引擎推断最优解。
  • 通过调整多语言目标的聚合与去模糊化过程,将PR框架扩展至多目标场景。
  • 将语言变量及其相关语义整合到统一的计算框架中,以支持不确定性与不精确性下的优化。

实验结果

研究问题

  • RQ1如何改进感知推理以更有效地解决单目标语言优化问题(SOLOPs),相比现有CWW方法?
  • RQ22-元组语言模型和Tsukamoto推理在建模优化中的语言语义时存在哪些局限性?
  • RQ3与类型1模糊集相比,区间直觉2型模糊集是否能改善优化问题中语言语义的表示?
  • RQ4如何将感知推理扩展至处理多目标语言优化问题(MOLOPs),同时保持语言可解释性?
  • RQ5基于CWW的感知推理引擎在处理具有语言输入的真实决策场景时,在准确性与鲁棒性方面具有哪些优势?

主要发现

  • 所提出的基于感知推理的方法通过使用区间直觉2型模糊集替代类型1模糊集,提供了更准确的语言语义表示。
  • 该方法成功将感知推理从单目标扩展至多目标语言优化问题,增强了应用范围。
  • 通过用基于区间直觉2型模糊集的CWW引擎替代2-元组语言模型,该方法降低了语言输入处理中的语义近似误差。
  • 该框架通过基于if-then规则的推理,有效处理了目标函数值不完整或不精确的情况,保持了决策的一致性。
  • 该解决方案方法在涉及人类偏好和语言约束的真实优化场景中,表现出更高的鲁棒性与可解释性。
  • 感知推理的使用实现了人类语言表达与计算优化之间的更自然映射,提升了实际应用中的可用性。

更好的研究,从现在开始

从阅读论文到最终审阅,大幅缩短您的研究时间。

无需绑定信用卡

本解读由 AI 生成,并经人工编辑审核。