资源描述:
《Indoor Location Detection with a RSS-based Short Term Memory Technique.pdf》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、EighthIEEEPerComWorkshoponPervasiveWirelessNetworking2012,Lugano(23March2012)IndoorLocationDetectionwithaRSS-basedShortTermMemoryTechnique(KNN-STM)BulutAltintasTachaSerifDepartmentofComputerEngineeringDepartmentofComputerEngineeringYeditepeUniversityYeditepeUniversityIstanbul,TurkeyIstanbul,Turkeyb
2、altintas@cse.yeditepe.edu.trtserif@cse.yeditepe.edu.trAbstract—Theinteractionbetweendevicesandusershascoordinatesofuser’spreviouspositionsandhis/herspeedchangeddramaticallywiththeadvancesinmobilehavealreadybeendevelopedinthepastandcanbefoundintechnologies.Userfriendlydevicesandservicesareofferedbyt
3、heliterature.However,tothebestofourknowledge,noutilizingsmartsensingcapabilitiesandusingcontext,locationpreviousworkhasutilizedamemorywhichstoredtheuser’sandmotionsensordata.However,indoorlocationsensingisprevioussignalstrengthobservationvaluestoimprovethemostlyachievedbymeasuringradiosignal(WiFi,B
4、luetooth,KNNalgorithmperformance.GSMetc.)strengthandnearestneighboridentification.TheHence,thispaperisstructuredasfollows:sectiontwoalgorithmthatismostcommonlyusedforReceivedSignalintroducesthekeyelementsofindoorlocationsensingStrength(RSS)basedlocationdetectionistheKNearesttechniquesanddetailsthep
5、opularpositioningmethods.Neighbor(KNN).KNNalgorithmidentifiesanestimateFurthermore,itbrieflydescribestheworkdonetoimprovelocationusingtheKnearestneighboringpoints.Accordingly,KNNalgorithms.Thethirdsectiondiscussesthephasesofinthispaper,weaimtoimprovetheKNNalgorithmbyfingerprintingandelaboratesonthe
6、ideabehindlocationintegratingashorttermmemory(STM)wherepastsignalsensingusingfingerprintingbyprovidingadetailedstrengthreadingsarestored.Consideringthelimitedmovementcapabilitiesofamobileuserinanindooroverviewofthealgorithmsused.Thefourthsectionisonenvironment,user'spreviouslocationscanbetakenintoe
7、xperimentsandevaluation,whichdetailsthetestsconsiderationtoderivehis/hercurrentposition.Hence,intheundertakenandpresentstheirfindings.Inthelastsection,proposedapproach,thesignalstrengthreadingsarerefinedcon