Indoor localization using unsupervised manifold alignment with geometry perturbation

Handle URI:
http://hdl.handle.net/10754/564902
Title:
Indoor localization using unsupervised manifold alignment with geometry perturbation
Authors:
Majeed, Khaqan; Sorour, Sameh; Al-Naffouri, Tareq Y.; Valaee, Shahrokh
Abstract:
The main limitation of deploying/updating Received Signal Strength (RSS) based indoor localization is the construction of fingerprinted radio map, which is quite a hectic and time-consuming process especially when the indoor area is enormous and/or dynamic. Different approaches have been undertaken to reduce such deployment/update efforts, but the performance degrades when the fingerprinting load is reduced below a certain level. In this paper, we propose an indoor localization scheme that requires as low as 1% fingerprinting load. This scheme employs unsupervised manifold alignment that takes crowd sourced RSS readings and localization requests as source data set and the environment's plan coordinates as destination data set. The 1% fingerprinting load is only used to perturb the local geometries in the destination data set. Our proposed algorithm was shown to achieve less than 5 m mean localization error with 1% fingerprinting load and a limited number of crowd sourced readings, when other learning based localization schemes pass the 10 m mean error with the same information.
KAUST Department:
Computer, Electrical and Mathematical Sciences and Engineering (CEMSE) Division; Electrical Engineering Program
Publisher:
Institute of Electrical and Electronics Engineers (IEEE)
Journal:
2014 IEEE Wireless Communications and Networking Conference (WCNC)
Conference/Event name:
2014 IEEE Wireless Communications and Networking Conference, WCNC 2014
Issue Date:
Apr-2014
DOI:
10.1109/WCNC.2014.6952925
Type:
Conference Paper
ISSN:
15253511
ISBN:
9781479930838
Appears in Collections:
Conference Papers; Electrical Engineering Program; Computer, Electrical and Mathematical Sciences and Engineering (CEMSE) Division

Full metadata record

DC FieldValue Language
dc.contributor.authorMajeed, Khaqanen
dc.contributor.authorSorour, Samehen
dc.contributor.authorAl-Naffouri, Tareq Y.en
dc.contributor.authorValaee, Shahrokhen
dc.date.accessioned2015-08-04T07:24:37Zen
dc.date.available2015-08-04T07:24:37Zen
dc.date.issued2014-04en
dc.identifier.isbn9781479930838en
dc.identifier.issn15253511en
dc.identifier.doi10.1109/WCNC.2014.6952925en
dc.identifier.urihttp://hdl.handle.net/10754/564902en
dc.description.abstractThe main limitation of deploying/updating Received Signal Strength (RSS) based indoor localization is the construction of fingerprinted radio map, which is quite a hectic and time-consuming process especially when the indoor area is enormous and/or dynamic. Different approaches have been undertaken to reduce such deployment/update efforts, but the performance degrades when the fingerprinting load is reduced below a certain level. In this paper, we propose an indoor localization scheme that requires as low as 1% fingerprinting load. This scheme employs unsupervised manifold alignment that takes crowd sourced RSS readings and localization requests as source data set and the environment's plan coordinates as destination data set. The 1% fingerprinting load is only used to perturb the local geometries in the destination data set. Our proposed algorithm was shown to achieve less than 5 m mean localization error with 1% fingerprinting load and a limited number of crowd sourced readings, when other learning based localization schemes pass the 10 m mean error with the same information.en
dc.publisherInstitute of Electrical and Electronics Engineers (IEEE)en
dc.titleIndoor localization using unsupervised manifold alignment with geometry perturbationen
dc.typeConference Paperen
dc.contributor.departmentComputer, Electrical and Mathematical Sciences and Engineering (CEMSE) Divisionen
dc.contributor.departmentElectrical Engineering Programen
dc.identifier.journal2014 IEEE Wireless Communications and Networking Conference (WCNC)en
dc.conference.date6 April 2014 through 9 April 2014en
dc.conference.name2014 IEEE Wireless Communications and Networking Conference, WCNC 2014en
dc.contributor.institutionElectrical Engineering Department, King Fahd University of Petroleum and Minerals (KFUPM)Dhahran, Saudi Arabiaen
dc.contributor.institutionDepartment of Electrical and Computer Engineering, University of TorontoToronto, ON, Canadaen
kaust.authorAl-Naffouri, Tareq Y.en
All Items in KAUST are protected by copyright, with all rights reserved, unless otherwise indicated.