简介：Fuzzyassociationrules(FARs)canbepowerfulinassessingregionalsoilquality,acriticalsteppriortolandplanningandutilization;however,traditionalFARsminedfromsoilqualitydatabase,ignoringtheimportancevariabilityoftherules,canberedundantandfarfromoptimal.Inthisstudy,wedevelopedamethodapplyingdifferentweightstotraditionalFARstoimproveaccuracyofsoilqualityassessment.AftertheFARsforsoilqualityassessmentweremined,redundantruleswereeliminatedaccordingtowhethertherulesweresignificantornotinreducingthecomplexityofthesoilqualityassessmentmodelsandinimprovingthecomprehensibilityofFARs.Theglobalweights,eachrepresentingtheimportanceofaFARinsoilqualityassessment,werethenintroducedandrefinedusingagradientdescentoptimizationmethod.ThismethodwasappliedtotheassessmentofsoilresourcesconditionsinGuangdongProvince,China.Thenewapproachhadanaccuracyof87%,when15rulesweremined,ascomparedwith76%fromthetraditionalapproach.Theaccuracyincreasedto96%when32rulesweremined,incontrastto88%fromthetraditionalapproach.TheseresultsdemonstratedanimprovedcomprehensibilityofFARsandahighaccuracyoftheproposedmethod.

简介：本文通过对理想点法进行分析，认为该法取不同的ｐ值代表决策者对不同目标的偏爱程度；但ｐ值过大模型求解比较困难，故实际应用时ｐ值取较大的值并不现实．为进一步突出决策人对不同目标的偏爱程度，作者对理想点法进行改进，引进了各目标的权重，提出了加权理想点法．与前者比较，它进一步突出了不同目标对决策结果的影响，使决策结果更符合决策者的愿望，便于在生产中实施．通过用该法对山西省千秋沟林场某经营类型进行收获调整，表明用该法进行森林收获调整，到调整期末龄级结构基本达到完全调整林状态，且可将决策者对不同目标的要求落实到合理水平上．