Show simple item record

dc.contributor.advisorMao, Shiwen
dc.contributor.authorYu, Zhitao
dc.date.accessioned2018-11-05T22:00:20Z
dc.date.available2018-11-05T22:00:20Z
dc.date.issued2018-11-05
dc.identifier.urihttp://hdl.handle.net/10415/6440
dc.description.abstractWith the fast increasing demands of location-based service and the proliferation of smartphones and other mobile devices, accurate indoor localization has attracted great interest. In this thesis, we present DeepML, a deep long short-term memory (LSTM) based system for indoor localization using smartphone magnetic and light sensors. We verify the feasibility of using bimodal magnetic and light data for indoor localization through experiments. We then design the DeepML system, which first builds bimodal images by data preprocessing, and then trains a deep LSTM network to extract the location features. Newly received magnetic field and light intensity data are then exploited for estimating the location of the mobile device using an improved probabilistic method. Our extensive experiments verify the effectiveness of the proposed DeepML system.en_US
dc.subjectElectrical and Computer Engineeringen_US
dc.titleSmartphone Sensor Fusion For Indoor Localization: A Deep LSTM Approachen_US
dc.typeMaster's Thesisen_US
dc.embargo.lengthen_US
dc.embargo.statusNOT_EMBARGOEDen_US
dc.contributor.committeeRoppel, Thaddeus
dc.contributor.committeeGong, Xiaowen


Files in this item

Show simple item record