Method for Mitigation of NLOS Error based on SVM using Geometry Information and Training data

DOI

10.2991/icismme-15.2015.2How to use a DOI?

Keywords

Time of arrival; Mobile location; NLOS error; LS-SVM; Kernel function

Abstract

In this paper, a novel least square support vector machines (LS-SVM) based on geometry information and training data is proposed to improve the performance of mobile localization in the non-line-of-sight (NLOS) environments. Simulations show that the performance of the proposed method is better than the geometry method and the learning method based RBF kernel function in difference channel environments.

Copyright

© 2015, the Authors. Published by Atlantis Press.

Open Access

This is an open access article distributed under the CC BY-NC license (http://creativecommons.org/licenses/by-nc/4.0/).

Download article (PDF)

TY  - CONF
AU  - Jiyan Huang
AU  - Peng Liu
AU  - Mingquan Lu
AU  - Baogen Xu
AU  - Zhongchu Rao
AU  - Yihe Wan
AU  - Chuan Lu
AU  - Hongyan Zhang
PY  - 2015/07
DA  - 2015/07
TI  - Method for Mitigation of NLOS Error based on SVM using Geometry Information and Training data
BT  - Proceedings of the First International Conference on Information Sciences, Machinery, Materials and Energy
PB  - Atlantis Press
SP  - 7
EP  - 11
SN  - 1951-6851
UR  - https://doi.org/10.2991/icismme-15.2015.2
DO  - 10.2991/icismme-15.2015.2
ID  - Huang2015/07
ER  -