基于多粒度概率粗糙集与MULTIMOORA的q-RO模糊多属性群决策  

q-RO fuzzy multi-attribute group decision making based on multigranulation probabilistic rough sets and MULTIMOORA

作　　者：白文慧 张超[1,2] 陈炜哲 李德玉 上官学奎[3] 马瑾男 BAI Wenhui;ZHANG Chao;CHEN Weizhe;LI Deyu;SHANGGUAN Xuekui;MA Jinnan(School of Computer and Information Technology,Shanxi University,Taiyuan 030006,P.R.China;Key Laboratory of Computational Intelligence and Chinese Information Processing of Ministry of Education(Shanxi University),Taiyuan 030006,P.R.China;Shanxi Information Industry Technology Research Institute Co.Ltd.,Taiyuan 030012,P.R.China)

机构地区：[1]山西大学计算机与信息技术学院,太原030006 [2]计算智能与中文信息处理教育部重点实验室(山西大学),太原030006 [3]山西省信息产业技术研究院有限公司,太原030012

出　　处：《重庆邮电大学学报（自然科学版）》2021年第5期769-779,共11页Journal of Chongqing University of Posts and Telecommunications(Natural Science Edition)

基　　金：国家自然科学基金(61806116,62072294,61972238);山西省重点研发计划(国际科技合作)项目(201903D421041,201803D421004);2020年小店区-山西大学产学研合作项目;山西省高等学校青年科研人员培育计划;山西省高等学校优秀成果培育项目(2019SK036);山西省自然科学基金(201801D221175,201901D211176,201901D211414)。

摘　　要：为了探索q-RO(q-rung orthopair)模糊信息系统中具备稳定决策结果的多属性群决策方法,依据多粒度概率粗糙集与MULTIMOORA(multi-objective optimization by ratio analysis plus the full MULTIplicative form)建立了一种新的q-RO模糊多粒度计算模型,并用于求解多属性群决策问题。结合q-RO模糊概率粗糙集与多粒度粗糙集,提出了多粒度q-RO模糊概率粗糙集模型。利用离差最大化法计算属性权重与决策者权重,进一步建立了基于多粒度概率粗糙集与MULTIMOORA的q-RO模糊多属性群决策方法,该方法考虑了决策风险与容错能力,可提供稳定的决策结果。通过2个实际算例验证了所建立方法的可行性与有效性。In order to explore stable multi-attribute group decision-making results in q-RO(q-rung orthopair)fuzzy information systems,a new q-RO fuzzy multi-granularity computing model is constructed in light of multigranulation probabilistic rough sets and MULTIMOORA(multi-objective optimization by ratio analysis plus the full multiplicative form)for solving multi-attribute group decision making problems.First,multigranulation q-RO fuzzy probabilistic rough set models are put forward by combining q-RO fuzzy probabilistic rough sets with multigranulation rough sets.Then,the maximum deviation method is utilized to calculate attribute weights and expert weights,and a q-RO fuzzy multiple-attribute group decision making method is further constructed based on multigranulation probabilistic rough sets and MULTIMOORA,which can provide stable decision making results via considering decision risks and fault-tolerance capabilities.Finally,the validity and the effectiveness of the established method are verified by two realistic case studies.

关 键 词：多粒度 概率粗糙集 q-RO模糊信息系统 多属性群决策 MULTIMOORA 

分 类 号：TP18[自动化与计算机技术—控制理论与控制工程]