基于zigbee的位置指纹法室内定位技术分析-analysis of indoor location technology based on zigbee location fingerprint method.docx

函数将位置指纹映射为特征空间中的一点,并在该空间中采用基于核方法的模糊k-means算法对其进行聚类。实验结果表明，基于两种方法得到的位置指纹集合聚类趋势更为明显，对位置指纹的分类效果好于k-means算法。为解决室内复杂环境下的定位实现问题，提出了一种基于D-S证据理论的位置指纹室内定位方法。构造了信度分配的mass函数，建立了一个基于pignistic概率的信度分配冲突程度评价指标。根据指标大小，采用信度打折的证据预处理方法消除定位过程中出现的合成悖论现象。为降低信任区间重叠时的决策风险，根据合成后焦元获得的信任区间确定分布函数，将两焦元信度在并集区间上降序排列的概率作为最终的决策依据。实验结果表明，该方法具有收敛速度快，决策风险低的优点。在证据间高冲突时的定位精度好于贝叶斯推理法。此外，针对基于位置指纹法的室内跟踪问题，提出了一种改进的粒子滤波跟踪算法。建立了二维平面内跟踪问题的状态空间模型，并根据本文提出的信号强度估计方法完成粒子权值的求解。实验结果表明，该方法对实际移动路线的跟踪精度好于KNN法和Kalman滤波器。关键词：位置指纹法；ZigBee；空间变异理论；聚类技术；证据理论；粒子滤波AbstractWiththesuccessfulapplicationsofglobalpositioningsystem(GPS)onoutdoorpositioning,thedemandsofindoorpositioningservicesaregettingshaper.Becauseofthelowpositioningcostandflexiblerealization,thelocationfingerprintmethod(LFM)isbecomingtheresearchfocusintheexistingindoorpositioningtechniques.However,thetimevariationofindoorwirelesssignalmakesitdifficultforLFMtorealizepinpoint.So,improvingthepositioningperformanceandpracticabilityofLFMinthecomplexindoorenvironmentnotonlyhasimportanttheoreticalvalue,butalsobecomesthekeyofacceleratingthetransitionfromtheoreticalstudytoapplication.Inthispaper,relatedtechniquesofLFMinthetwopositioningstagesarestudiedintheZigBeenetwork.BasedonanalyzingresearchstatusanddevelopmentofLFMathomeandabroad,itispointedoutthattheproblemofconstructionworkloadoflocationfingerprintdatabase,theproblemofmatchingefficiencyoflocationfingerprintsandtheproblemofindoorpositioningandtrackingrealizationsarethethreemainproblemsofLFM.Andthen,startingwithanalyzingsignalstrengthcharacteristics,methodsforresolvingtheseproblemsareproposedrespectively.Inordertoanalyzethedatacharacteristicsofsignalstrengthasthescenefeature,themanifestationsandcausesofcharacteristicsarestudiedbytheoreticalanalysisandexperimentalverificationwithactualZigBeesignalstrengthsamples.Andthen,aprobabilitymodelisgiventoestimatetheaveragepositioningerrorofLFM.Basedonthemodel,therelationshipsbetweenpositioningperformanceofLFMandspaceofsamplinglocationsandnumbersandlocationsofnetworkaccessdevices