基于nsga-ⅱ和免疫算法的多目标优化与分类

基于nsga-ⅱ和免疫算法的多目标优化与分类

ID:32056123

大小:2.27 MB

页数:68页

时间:2019-01-31

基于nsga-ⅱ和免疫算法的多目标优化与分类_第1页
基于nsga-ⅱ和免疫算法的多目标优化与分类_第2页
基于nsga-ⅱ和免疫算法的多目标优化与分类_第3页
基于nsga-ⅱ和免疫算法的多目标优化与分类_第4页
基于nsga-ⅱ和免疫算法的多目标优化与分类_第5页
资源描述:

《基于nsga-ⅱ和免疫算法的多目标优化与分类》由会员上传分享,免费在线阅读,更多相关内容在学术论文-天天文库

1、ABSTRACTIIIABSTRACTMulti—objectiveoptimization(MO)algorithmistofindasetofnondominatedandwelldistributedsolutions.Intheareaofdatamining,imagesengmentationandimageclustering,wealwaysneedtofindproperparameters,andmulti-objectiveoptimizationalgorithmsCanhelpUSfindasetofsolutions,then

2、weselectwhichonetouse.Inordertoimprovetheperformanceofmulti—objectiveoptimizationalgorithms,alotofresearchersbroughtindifferentkindsofstrategies.Sofar,therearesomekindoffamousmulti·objectiveoptimizationalgotihomssuch豁NSGA-II,SPEA2,MOPSOandMOEAkD.Meanwhile,inpraticalproblems,there

3、arealwaysconstraints,andhowtodeal、析t11theconstraintsisahotspotformanyresearchers.Firstly,thispaperimprovedthecrowding—distancecomputation,secondly,basedonImmuneClonalalgorithm,thispaperproposedanewconstrainedmulti—objectiveoptimizationalgorithm,finalll,thispapermadeadeeperanalysi

4、sintheapplicationofmulti—objectiveoptimizationalgorithmsinmulti—classclaSsification.Theprimarycoverageofthisarticleincludes:‘(1)Inrecentyears,NSGA-IIisoneofthemostfamousmultiobjectiveevolutionaryalgorithms,butwhendealingwiththree—objectivetestproblems,itcallnotfindawelldistribute

5、dpopulationbecauseofthedrawbackofthemethodfortllecrowding—distancecomputation.Aimingatthis,weproposedanewmethodforthecrowding-distancecomputation.Bybringinginalocalcrowding-distancevalue,thismethodcompletestheupdatingoperationofthepopulation,andtheselectionofthesub-populationfrom

6、theparentpopulationisdonethroughaglobalcrowding-distancevalue.Thenwemadeabriefanalysisofthenewalgorithm’Sparameter.Finally,attheappropriateparameter,thenewproposedalgorithmWastestedontwoandthreedimensionaltestproblems,andcomparedwiththeotherthreefamousmultiobjectiveoptimizational

7、gorithms.ThetestresultshowsthatthenewproposedalgorithmachievesabetterconvergenceanddiversitythanNSGA—IIandothertwoalgorithms.(2)ProposedanewImmuneClonalConstrainedMulti—objectiveAlgorithmforconstrainedmulti—objectiveoptimizationproblems.Bybringinginanewconstrainedhandlingstrategy

8、tomodifytheobjectivevaluesofindividuals,

当前文档最多预览五页,下载文档查看全文

此文档下载收益归作者所有

当前文档最多预览五页,下载文档查看全文
温馨提示:
1. 部分包含数学公式或PPT动画的文件,查看预览时可能会显示错乱或异常,文件下载后无此问题,请放心下载。
2. 本文档由用户上传,版权归属用户,天天文库负责整理代发布。如果您对本文档版权有争议请及时联系客服。
3. 下载前请仔细阅读文档内容,确认文档内容符合您的需求后进行下载,若出现内容与标题不符可向本站投诉处理。
4. 下载文档时可能由于网络波动等原因无法下载或下载错误,付费完成后未能成功下载的用户请联系客服处理。