Cited time in webofscience Cited time in scopus

Full metadata record

DC Field Value Language
dc.contributor.author Jin, Feiyu -
dc.contributor.author Liu, Kai -
dc.contributor.author Zhang, Hao -
dc.contributor.author Ng, Joseph Kee-Yin -
dc.contributor.author Guo, Songtao -
dc.contributor.author Lee, Victor C. S. -
dc.contributor.author Son, Sang Hyuk -
dc.date.accessioned 2020-04-16T10:06:16Z -
dc.date.available 2020-04-16T10:06:16Z -
dc.date.created 2020-03-05 -
dc.date.issued 2020-02 -
dc.identifier.citation IEEE Internet of Things Journal, v.7, no.2, pp.1192 - 1204 -
dc.identifier.issn 2327-4662 -
dc.identifier.uri http://hdl.handle.net/20.500.11750/11674 -
dc.description.abstract Although indoor localization has been studied over a decade, it is still challenging to enable many IoT applications, such as activity tracking and monitoring in smart home and customer navigation and trajectory mining in smart shopping mall, which typically require meter-level localization accuracy in a highly dynamic and large-scale indoor environment. Therefore, this article aims at designing and implementing an adaptive and scalable indoor tracking system in a cost-effective way. First, we propose a zero site-survey overhead (ZSSO) algorithm to enhance the system scalability. It integrates the step information and map constraints to infer user's positions based on the particle filter and supports the auto labeling of scanned Wi-Fi signal for constructing the fingerprint database without the extra site-survey overhead. Further, we propose an iterative-weight-update (IWU) strategy for ZSSO to enhance system robustness and make it more adaptive to the dynamic changing of environments. Specifically, a two-step clustering mechanism is proposed to delete outliers in the fingerprint database and alleviate the mismatch between the auto-tagged coordinates and the corresponding signal features. Then, an iterative fingerprint update mechanism is designed to continuously evaluate the Wi-Fi fingerprint localization results during online tracking, which will further refine the fingerprint database. Finally, we implement the indoor tracking system in real-world environments and conduct a comprehensive performance evaluation. The field testing results conclusively demonstrate the scalability and effectiveness of the proposed algorithms. -
dc.language English -
dc.publisher Institute of Electrical and Electronics Engineers Inc. -
dc.title Toward Scalable and Robust Indoor Tracking: Design, Implementation, and Evaluation -
dc.type Article -
dc.identifier.doi 10.1109/JIOT.2019.2953376 -
dc.identifier.wosid 000521981800031 -
dc.identifier.scopusid 2-s2.0-85079739632 -
dc.type.local Article(Overseas) -
dc.type.rims ART -
dc.description.journalClass 1 -
dc.citation.publicationname IEEE Internet of Things Journal -
dc.contributor.nonIdAuthor Jin, Feiyu -
dc.contributor.nonIdAuthor Liu, Kai -
dc.contributor.nonIdAuthor Zhang, Hao -
dc.contributor.nonIdAuthor Ng, Joseph Kee-Yin -
dc.contributor.nonIdAuthor Guo, Songtao -
dc.contributor.nonIdAuthor Lee, Victor C. S. -
dc.contributor.nonIdAuthor Son, Sang Hyuk -
dc.identifier.citationVolume 7 -
dc.identifier.citationNumber 2 -
dc.identifier.citationStartPage 1192 -
dc.identifier.citationEndPage 1204 -
dc.identifier.citationTitle IEEE Internet of Things Journal -
dc.type.journalArticle Article -
dc.description.isOpenAccess N -
dc.subject.keywordAuthor Algorithm design -
dc.subject.keywordAuthor indoor localization -
dc.subject.keywordAuthor performance evaluation -
dc.subject.keywordAuthor trajectory tracking -
dc.subject.keywordAuthor Wi-Fi fingerprint -
dc.subject.keywordPlus POSITIONING SYSTEMS -
dc.subject.keywordPlus LOCALIZATION -
dc.contributor.affiliatedAuthor Jin, Feiyu -
dc.contributor.affiliatedAuthor Liu, Kai -
dc.contributor.affiliatedAuthor Zhang, Hao -
dc.contributor.affiliatedAuthor Ng, Joseph Kee-Yin -
dc.contributor.affiliatedAuthor Guo, Songtao -
dc.contributor.affiliatedAuthor Lee, Victor C. S. -
dc.contributor.affiliatedAuthor Son, Sang Hyuk -
Files in This Item:

There are no files associated with this item.

Appears in Collections:
ETC 1. Journal Articles

qrcode

  • twitter
  • facebook
  • mendeley

Items in Repository are protected by copyright, with all rights reserved, unless otherwise indicated.

BROWSE