Novel range-free localization based on multidimensional support vector regression trained in the primal space

Jaehun Lee, Baehoon Choi, Euntai Kim

Research output: Contribution to journalArticle

39 Citations (Scopus)

Abstract

A novel range-free localization algorithm based on the multidimensional support vector regression (MSVR) is proposed in this paper. The range-free localization problem is formulated as a multidimensional regression problem, and a new MSVR training method is proposed to solve the regression problem. Unlike standard support vector regression, the proposed MSVR allows multiple outputs and localizes the sensors without resorting to multilateration. The training of the MSVR is formulated directly in primal space and it can be solved in two ways. First, it is formulated as a second-order cone programming and trained by convex optimization. Second, its own training method is developed based on the Newton-Raphson method. A simulation is conducted for both isotropic and anisotropic networks, and the proposed method exhibits excellent and robust performance in both isotropic and anisotropic networks.

Original languageEnglish
Article number6488858
Pages (from-to)1099-1113
Number of pages15
JournalIEEE Transactions on Neural Networks and Learning Systems
Volume24
Issue number7
DOIs
Publication statusPublished - 2013 Apr 1

Fingerprint

Convex optimization
Newton-Raphson method
Cones
Sensors
Time difference of arrival

All Science Journal Classification (ASJC) codes

  • Software
  • Computer Science Applications
  • Computer Networks and Communications
  • Artificial Intelligence

Cite this

@article{4de6364decb24364b288662ed7fae04b,
title = "Novel range-free localization based on multidimensional support vector regression trained in the primal space",
abstract = "A novel range-free localization algorithm based on the multidimensional support vector regression (MSVR) is proposed in this paper. The range-free localization problem is formulated as a multidimensional regression problem, and a new MSVR training method is proposed to solve the regression problem. Unlike standard support vector regression, the proposed MSVR allows multiple outputs and localizes the sensors without resorting to multilateration. The training of the MSVR is formulated directly in primal space and it can be solved in two ways. First, it is formulated as a second-order cone programming and trained by convex optimization. Second, its own training method is developed based on the Newton-Raphson method. A simulation is conducted for both isotropic and anisotropic networks, and the proposed method exhibits excellent and robust performance in both isotropic and anisotropic networks.",
author = "Jaehun Lee and Baehoon Choi and Euntai Kim",
year = "2013",
month = "4",
day = "1",
doi = "10.1109/TNNLS.2013.2250996",
language = "English",
volume = "24",
pages = "1099--1113",
journal = "IEEE Transactions on Neural Networks and Learning Systems",
issn = "2162-237X",
publisher = "IEEE Computational Intelligence Society",
number = "7",

}

Novel range-free localization based on multidimensional support vector regression trained in the primal space. / Lee, Jaehun; Choi, Baehoon; Kim, Euntai.

In: IEEE Transactions on Neural Networks and Learning Systems, Vol. 24, No. 7, 6488858, 01.04.2013, p. 1099-1113.

Research output: Contribution to journalArticle

TY - JOUR

T1 - Novel range-free localization based on multidimensional support vector regression trained in the primal space

AU - Lee, Jaehun

AU - Choi, Baehoon

AU - Kim, Euntai

PY - 2013/4/1

Y1 - 2013/4/1

N2 - A novel range-free localization algorithm based on the multidimensional support vector regression (MSVR) is proposed in this paper. The range-free localization problem is formulated as a multidimensional regression problem, and a new MSVR training method is proposed to solve the regression problem. Unlike standard support vector regression, the proposed MSVR allows multiple outputs and localizes the sensors without resorting to multilateration. The training of the MSVR is formulated directly in primal space and it can be solved in two ways. First, it is formulated as a second-order cone programming and trained by convex optimization. Second, its own training method is developed based on the Newton-Raphson method. A simulation is conducted for both isotropic and anisotropic networks, and the proposed method exhibits excellent and robust performance in both isotropic and anisotropic networks.

AB - A novel range-free localization algorithm based on the multidimensional support vector regression (MSVR) is proposed in this paper. The range-free localization problem is formulated as a multidimensional regression problem, and a new MSVR training method is proposed to solve the regression problem. Unlike standard support vector regression, the proposed MSVR allows multiple outputs and localizes the sensors without resorting to multilateration. The training of the MSVR is formulated directly in primal space and it can be solved in two ways. First, it is formulated as a second-order cone programming and trained by convex optimization. Second, its own training method is developed based on the Newton-Raphson method. A simulation is conducted for both isotropic and anisotropic networks, and the proposed method exhibits excellent and robust performance in both isotropic and anisotropic networks.

UR - http://www.scopus.com/inward/record.url?scp=84877925125&partnerID=8YFLogxK

UR - http://www.scopus.com/inward/citedby.url?scp=84877925125&partnerID=8YFLogxK

U2 - 10.1109/TNNLS.2013.2250996

DO - 10.1109/TNNLS.2013.2250996

M3 - Article

AN - SCOPUS:84877925125

VL - 24

SP - 1099

EP - 1113

JO - IEEE Transactions on Neural Networks and Learning Systems

JF - IEEE Transactions on Neural Networks and Learning Systems

SN - 2162-237X

IS - 7

M1 - 6488858

ER -