distributed estimation and quantization

distributed estimation and quantization

ID:34470975

大小:176.44 KB

页数:5页

时间:2019-03-06

distributed estimation and quantization_第1页
distributed estimation and quantization_第2页
distributed estimation and quantization_第3页
distributed estimation and quantization_第4页
distributed estimation and quantization_第5页
资源描述:

《distributed estimation and quantization》由会员上传分享,免费在线阅读,更多相关内容在教育资源-天天文库

1、IEEETRANSACTIONSONINFORMATIONTHEORY,VOL.39,NO.4,PP.1456{1459,JULY1993DistributedEstimationandQuantizationJohnA.Gubner,Member,IEEEAbstract

2、AnalgorithmisdevelopedforthedesignofaconsiderationsareimportantiftheestimateofXmustnonlinear,n-sensor,distributedestimationsystemsubjecttobecomputedinrealtime.By

3、usingasuboptimales-communicationandcomputationconstraints.ThealgorithmtimatorofXforwhichsomeoftheprocessingcanbeusesonlybivariateprobabilitydistributionsandyieldslocallydonelocallyatthesensorplatforms,itmaybepossi-optimalestimatorsthatsatisfytherequiredsystemconstraints.bletodesignanacceptableestim

4、atorthatcanoperateItisshownthatthealgorithmisageneralizationoftheclassicalinrealtime.Lloyd{Maxresults.3)AsindicatedinFig.1,thesensorplatformstransmitIndexTerms

5、Nonlinearestimation,distributedestima-theirdatatothefusioncenter.However,usinganytion,sensorfusion,Lloyd{Maxalgorithm.physicalcommunication

6、system,itisnotpossibletotransmitreal-valuedquantitieswithoutdistortion.InI.Introductionthissituation,theconditionalexpectation,oreventhebestlinearestimate,isgenerallyaphysicallyunreal-ONSIDERthedistributedestimationsystemshowninizablesolution.CFig.1.Thesystemconsistsofnsensorplatformswhoserespectiv

7、emeasurements,Y;:::;Y,arerelatedtosome1nInthispaperwedevelopanalgorithmtodesignsolutionsunobservablequantity,sayX.Eachsensorplatformpro-tothedistributedestimationproblemthatdonotsu ercessesitsrespectivemeasurementandtransmitstheresultfromthesediculties.overacommunicationchanneltoacommonfusioncen-t

8、er.Thesensorsdonotcommunicatewitheachother,andYY1nthereisnofeedbackfromthefusioncentertothesensorplatforms.Thetaskofthefusioncenteristoestimatethe^unobservedquantityX.WedenotethisestimatebyX.??^Clearly,XisafunctionofY;:::;Y,andwecanwrite1nSensorSensor...^Platform1PlatformnX=f(Y;:::;Y)forsomefunctio

9、nf.Theproblemthen1n^istochoosethefunctionfsothatXisclosetoXinsome@?sense.Forexample,itiswellknownthatintheappropriate@?@?probabilisticsetting,theminimum-mean-square-erroresti-@?mateofXgivenY;:::;Yisthecondi

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。