Robust kernel-based machine learning localization using NLOS TOAs or TDOAs

Jun Li, I. Tai Lu, Jonathan S. Lu, Lingwen Zhang

Research output: Chapter in Book/Report/Conference proceedingConference contribution

Abstract

A robust kernel-based machine learning localization scheme using time of arrival (TOA) or time difference of arrival (TDOA) in none-line-of-sight (NLOS) environments is proposed. The scheme can provide accurate position estimation while the reference nodes are coarsely and randomly distributed in the area of interests. Moreover, the scheme is insensitive with respect to random TOA synchronization and measurement errors.

Original languageEnglish (US)
Title of host publication2017 IEEE Long Island Systems, Applications and Technology Conference, LISAT 2017
PublisherInstitute of Electrical and Electronics Engineers Inc.
ISBN (Electronic)9781538638873
DOIs
StatePublished - Aug 3 2017
Event2017 IEEE Long Island Systems, Applications and Technology Conference, LISAT 2017 - Farmingdale, United States
Duration: May 5 2017 → …

Publication series

Name2017 IEEE Long Island Systems, Applications and Technology Conference, LISAT 2017

Other

Other2017 IEEE Long Island Systems, Applications and Technology Conference, LISAT 2017
CountryUnited States
CityFarmingdale
Period5/5/17 → …

Keywords

  • Kernel-based Machine Learning
  • Localization
  • NLOS
  • TDOA
  • TOA
  • fingerprinting

ASJC Scopus subject areas

  • Artificial Intelligence
  • Instrumentation
  • Software
  • Computer Science Applications
  • Renewable Energy, Sustainability and the Environment

Fingerprint Dive into the research topics of 'Robust kernel-based machine learning localization using NLOS TOAs or TDOAs'. Together they form a unique fingerprint.

Cite this