IoT-Aided Fingerprint Indoor Positioning Using Support Vector Classification

Yiqiao Wei, Seung Hoon Hwang, Sang Moon Lee

Research output: Chapter in Book/Report/Conference proceedingConference contributionpeer-review

7 Scopus citations

Abstract

Wi-Fi based fingerprint indoor positioning technology is known as one of the most popular indoor positioning technologies. In this work, an internet of things (IoT) aided fingerprint indoor positioning system using support vector machine classifier has been proposed. The support vector classification with kernel tricks is introduced to accomplish multi-classes classification problem in fingerprint indoor positioning. Three kinds of kernel functions are investigated and compared based on results of the experiment performed in a real indoor environment. The results show support vector classifier with Gaussian RBF kernel function has highest positioning accuracy.

Original languageEnglish
Title of host publication9th International Conference on Information and Communication Technology Convergence
Subtitle of host publicationICT Convergence Powered by Smart Intelligence, ICTC 2018
PublisherInstitute of Electrical and Electronics Engineers Inc.
Pages973-975
Number of pages3
ISBN (Electronic)9781538650400
DOIs
StatePublished - 16 Nov 2018
Event9th International Conference on Information and Communication Technology Convergence, ICTC 2018 - Jeju Island, Korea, Republic of
Duration: 17 Oct 201819 Oct 2018

Publication series

Name9th International Conference on Information and Communication Technology Convergence: ICT Convergence Powered by Smart Intelligence, ICTC 2018

Conference

Conference9th International Conference on Information and Communication Technology Convergence, ICTC 2018
Country/TerritoryKorea, Republic of
CityJeju Island
Period17/10/1819/10/18

Keywords

  • Fingerprint
  • Indoor positioning
  • IoT
  • Received Signal Strength
  • Support vector machine

Fingerprint

Dive into the research topics of 'IoT-Aided Fingerprint Indoor Positioning Using Support Vector Classification'. Together they form a unique fingerprint.

Cite this