Employing Ray-tracing and Least-Squares Support Vector Machines for Localisation

Research output: Contribution to journalArticle (Academic Journal)

214 Downloads (Pure)

Abstract

This article evaluates the use of least-squares support vector machines, with ray-traced data, to solve the problem of localisation in multipath environments. The schemes discussed concern 2-D localisation, but could easily be extended to 3-D. It does not require NLOS identification and mitigation, hence, it can be applied in any environment. Some background details and a detailed experimental setup is provided. Comparisons with schemes that require NLOS identification and mitigation, from earlier work, are also presented. The results demonstrate that the direct localisation scheme using least-squares support vector machine (the Direct method) achieves superior outage to TDOA and TOA/AOA for NLOS environments. TDOA has better outage in LOS environments. TOA/AOA performs better for an accepted outage probability of 20 percent or greater but as the outage probability lowers, the Direct method becomes better
Original languageEnglish
JournalSensors
Volume18
Issue number11
Early online date20 Nov 2018
DOIs
Publication statusPublished - Nov 2018

Keywords

  • localisation
  • support vector machine
  • ray-tracing
  • positioning

Fingerprint Dive into the research topics of 'Employing Ray-tracing and Least-Squares Support Vector Machines for Localisation'. Together they form a unique fingerprint.

  • Cite this