ChannelEnvironmentRecognitionforOFDM-UWBCommunicationSystemBasedonDeepLearning

  • SongTao, ShaopingLiu
DOI: https://doi.org/10.17762/de.vi.768
Keywords: UWBCommunication,NLOSChannel,ChannelEnvironmentIdentification,ShortTimeFourierTransformation,DeepConvolutionNeuralNetwork.

Abstract

wideband(UWB)wirelesscommunicationbasedonshortpulseiswidelyusedinindoorpositioningandotherresearchfields.However,duetothenon-lineofsight(NLOS)propagationerrorinthechannelenvironment,itwillnotonlycausealotofenergylossinthetransmissionprocess,butalsoleadtotheindoorpositioningaccuracy,whichisnothightoacertainextent.InordertoidentifyNLOSchannelaccurately,thispaperproposesachannelenvironmentrecognitionmethodbasedondeeplearning.Firstly,theimpulseresponsetime-domainsignalistransformedintoenergyspectrumbyshort-timeFouriertransformation(STFT),andthentheenergyspectrumisinputintoCNNmodelasanimage,andthefeaturesareextractedbyconvolutionaloperationsintimedirectionandfrequencydirection,respectively.Finally,thecombinedfeaturesareusedtorecognizethecommunicationchannelenvironment.Inthecommunicationsystembasedonorthogonalfrequencydivisionmultiplexing(OFDM)-UWB,thesimulationresultsshowthattheproposedalgorithmisobviouslysuperiortothetraditionalSVMrecognitionmethod,andachievesgoodrecognitionaccuracyindifferentSNRenvironments.Whenthesignal-to-noiseratioisEbN0=22dB,therecognitionaccuracytendstobestable,andthehighestrecognitionaccuracyreaches90.58%.

Published
2020-09-29
How to Cite
SongTao, ShaopingLiu. (2020). ChannelEnvironmentRecognitionforOFDM-UWBCommunicationSystemBasedonDeepLearning. Design Engineering, 660 - 667. https://doi.org/10.17762/de.vi.768
Issue
Vol 2020: Issue 8
Section
Articles