2012_Robust Estimation in Signal Processing_SPM

2012_Robust Estimation in Signal Processing_SPM

ID:40554494

大小:1.56 MB

页数:20页

时间:2019-08-04

2012_Robust Estimation in Signal Processing_SPM_第1页
2012_Robust Estimation in Signal Processing_SPM_第2页
2012_Robust Estimation in Signal Processing_SPM_第3页
2012_Robust Estimation in Signal Processing_SPM_第4页
2012_Robust Estimation in Signal Processing_SPM_第5页
资源描述:

《2012_Robust Estimation in Signal Processing_SPM》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、[AbdelhakM.Zoubir,VisaKoivunen,YacineChakhchoukh,andMichaelMuma]RobustEstimationinSignalProcessing[Atutorial-stylehewordrobusthasbeenusedinmanycontextsinsignalprocessing.Ourtreatmentconcernsstatisticalrobustness,whichdealswithdeviationsfromtreatmentthedistributionalass

2、umptions.ManyproblemsencounteredinengineeringpracticerelyontheGaussiandistributionofthedata,whichinmanysitua-offundamentalTtionsiswelljustified.Thisenablesasimplederivationofoptimalestimators.Nominaloptimality,however,isuselessiftheestimatorwasderivedunderdistributiona

3、lassumptionsonthenoiseandthesignalthatdonotholdinpractice.Evenslightdevia-concepts]tionsfromtheassumeddistributionmaycausetheestimator’sperformanceto©EYEWIREDigitalObjectIdentifier10.1109/MSP.2012.2183773Dateofpublication:12June20121053-5888/12/$31.00©2012IEEEIEEESIGNA

4、LPROCESSINGMAGAZINE[61]JULY2012drasticallydegradeortocompletelybreakdown.Thesignalpro-naturaldisasters[8].Moreover,onacomputerplatform,variouscessingpractitionershould,therefore,askwhethertheperfor-components,suchastheliquidcrystaldisplay(LCD)pixelclockmanceofthederive

5、destimatorisacceptableinsituationswhereandtheperipheralcomponentinterconnect(PCI)expressbus,thedistributionalassumptionsdonothold.Isn’titrobustnesscauseimpulsiveinterferencethatdegradestheperformanceofthatisofamajorconcernforengineeringpractice?Manyareasoftheembeddedwi

6、relessdevices[9].engineeringtodayshowthatthedistributionofthemeasure-ThesesituationsenforcetheneedforrobustsignalprocessingmentsisfarfromGaussianasitcontainsoutliers,whichcausemethods,whichareclosetooptimalinnominalconditionsandthedistributiontobeheavytailed.Undersuchs

7、cenarios,wehighlyreliableforreal-lifedata,eveniftheassumptionsareonlyaddresssingleandmultichannelestimationproblemsaswellasapproximatelyvalid[10].Inestimation,optimalityunderthelinearunivariateregressionforindependentlyandidenticallydis-exactmodeliscommonlymeasuredbyth

8、eefficiencyoftheesti-tributed(i.i.d.)data.Aratherextensivetreatmentoftheimpor-mator,whilenear-optimalityundercontamin

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。