Support Vector Regression for Mobile Target Localization in Indoor Environments

[EN] Trilateration-based target localization using received signal strength (RSS) in a wireless sensor network (WSN) generally yields inaccurate location estimates due to high fluctuations in RSS measurements in indoor environments. Improving the localization accuracy in RSS-based systems has long b...

Descripción completa

Detalles Bibliográficos
Autores: Jondhale, Satish R., Mohan, Vijay, Sharma, Bharat Bhushan, Athawale, Shashikant V., Lloret, Jaime|||0000-0002-0862-0533
Tipo de recurso: artículo
Fecha de publicación:2022
País:España
Institución:Universitat Politècnica de València (UPV)
Repositorio:RiuNet. Repositorio Institucional de la Universitat Politécnica de Valéncia
Idioma:inglés
OAI Identifier:oai:riunet.upv.es:10251/201813
Acceso en línea:https://riunet.upv.es/handle/10251/201813
Access Level:acceso abierto
Palabra clave:Trilateration
Received signal strength (RSS)
Wireless sensor network (WSN)
Localization and tracking (L&amp
T)
Support vector regression (SVR)
Kalman filter (KF)
Generalized regression neural network (GRNN)
INGENIERÍA TELEMÁTICA
Descripción
Sumario:[EN] Trilateration-based target localization using received signal strength (RSS) in a wireless sensor network (WSN) generally yields inaccurate location estimates due to high fluctuations in RSS measurements in indoor environments. Improving the localization accuracy in RSS-based systems has long been the focus of a substantial amount of research. This paper proposes two range-free algorithms based on RSS measurements, namely support vector regression (SVR) and SVR + Kalman filter (KF). Unlike trilateration, the proposed SVR-based localization scheme can directly estimate target locations using field measurements without relying on the computation of distances. Unlike other state-of-the-art localization and tracking (L&T) schemes such as the generalized regression neural network (GRNN), SVR localization architecture needs only three RSS measurements to locate a mobile target. Furthermore, the SVR based localization scheme was fused with a KF in order to gain further refinement in target location estimates. Rigorous simulations were carried out to test the localization efficacy of the proposed algorithms for noisy radio frequency (RF) channels and a dynamic target motion model. Benefiting from the good generalization ability of SVR, simulation results showed that the presented SVR-based localization algorithms demonstrate superior performance compared to trilateration- and GRNN-based localization schemes in terms of indoor localization performance.