Robust Received Signal Strength Indicator (RSSI)-Based Multitarget Localization via Gaussian Process Regression

We consider the robust localization, via Gaussian process regression (GPR), of multiple transmitters/targets based on received signal strength indicator (RSSI) data collected by fixed sensors distributed in the environment. For such a scenario and approach, we contribute both with a novel noise robu...

Full description

Saved in:
Bibliographic Details
Main Authors: Niclas Fuhrling, Hyeon Seok Rou, Giuseppe Thadeu Freitas de Abreu, David Gonzalez G., Osvaldo Gonsa
Format: Article
Language:English
Published: IEEE 2023-01-01
Series:IEEE Journal of Indoor and Seamless Positioning and Navigation
Subjects:
Online Access:https://ieeexplore.ieee.org/document/10314734/
Tags: Add Tag
No Tags, Be the first to tag this record!
_version_ 1850036181511700480
author Niclas Fuhrling
Hyeon Seok Rou
Giuseppe Thadeu Freitas de Abreu
David Gonzalez G.
Osvaldo Gonsa
author_facet Niclas Fuhrling
Hyeon Seok Rou
Giuseppe Thadeu Freitas de Abreu
David Gonzalez G.
Osvaldo Gonsa
author_sort Niclas Fuhrling
collection DOAJ
description We consider the robust localization, via Gaussian process regression (GPR), of multiple transmitters/targets based on received signal strength indicator (RSSI) data collected by fixed sensors distributed in the environment. For such a scenario and approach, we contribute both with a novel noise robust procedure to train the parameters of the GPR model, which is achieved via a mini-batch stochastic gradient descent (SGD) scheme with gradients given in closed form, and with a pair of corresponding robust marginalization procedures for the estimation of target locations. Simulation results validate the contributions by showing that the proposed methods significantly outperform the best related state-of-the-art (SotA) alternative and approach the performance of a genie-aided (GA) scheme.
format Article
id doaj-art-9daaaea8ae4d4e2e9536879ad701bc5e
institution DOAJ
issn 2832-7322
language English
publishDate 2023-01-01
publisher IEEE
record_format Article
series IEEE Journal of Indoor and Seamless Positioning and Navigation
spelling doaj-art-9daaaea8ae4d4e2e9536879ad701bc5e2025-08-20T02:57:17ZengIEEEIEEE Journal of Indoor and Seamless Positioning and Navigation2832-73222023-01-01110411410.1109/JISPIN.2023.333203310314734Robust Received Signal Strength Indicator (RSSI)-Based Multitarget Localization via Gaussian Process RegressionNiclas Fuhrling0https://orcid.org/0000-0003-1942-8691Hyeon Seok Rou1https://orcid.org/0000-0003-3483-7629Giuseppe Thadeu Freitas de Abreu2https://orcid.org/0000-0002-5018-8174David Gonzalez G.3https://orcid.org/0000-0003-2090-8481Osvaldo Gonsa4https://orcid.org/0000-0001-5452-8159School of Computer Science and Engineering, Constructor University (previously Jacobs University Bremen), Bremen, GermanySchool of Computer Science and Engineering, Constructor University (previously Jacobs University Bremen), Bremen, GermanySchool of Computer Science and Engineering, Constructor University (previously Jacobs University Bremen), Bremen, GermanyWireless Communications Technologies Group, Continental AG, Hannover, GermanyWireless Communications Technologies Group, Continental AG, Hannover, GermanyWe consider the robust localization, via Gaussian process regression (GPR), of multiple transmitters/targets based on received signal strength indicator (RSSI) data collected by fixed sensors distributed in the environment. For such a scenario and approach, we contribute both with a novel noise robust procedure to train the parameters of the GPR model, which is achieved via a mini-batch stochastic gradient descent (SGD) scheme with gradients given in closed form, and with a pair of corresponding robust marginalization procedures for the estimation of target locations. Simulation results validate the contributions by showing that the proposed methods significantly outperform the best related state-of-the-art (SotA) alternative and approach the performance of a genie-aided (GA) scheme.https://ieeexplore.ieee.org/document/10314734/Gaussian process regression (GPR)machine learningmultitarget localizationnoise robustnessreceived signal strength indicator (RSSI)
spellingShingle Niclas Fuhrling
Hyeon Seok Rou
Giuseppe Thadeu Freitas de Abreu
David Gonzalez G.
Osvaldo Gonsa
Robust Received Signal Strength Indicator (RSSI)-Based Multitarget Localization via Gaussian Process Regression
IEEE Journal of Indoor and Seamless Positioning and Navigation
Gaussian process regression (GPR)
machine learning
multitarget localization
noise robustness
received signal strength indicator (RSSI)
title Robust Received Signal Strength Indicator (RSSI)-Based Multitarget Localization via Gaussian Process Regression
title_full Robust Received Signal Strength Indicator (RSSI)-Based Multitarget Localization via Gaussian Process Regression
title_fullStr Robust Received Signal Strength Indicator (RSSI)-Based Multitarget Localization via Gaussian Process Regression
title_full_unstemmed Robust Received Signal Strength Indicator (RSSI)-Based Multitarget Localization via Gaussian Process Regression
title_short Robust Received Signal Strength Indicator (RSSI)-Based Multitarget Localization via Gaussian Process Regression
title_sort robust received signal strength indicator rssi based multitarget localization via gaussian process regression
topic Gaussian process regression (GPR)
machine learning
multitarget localization
noise robustness
received signal strength indicator (RSSI)
url https://ieeexplore.ieee.org/document/10314734/
work_keys_str_mv AT niclasfuhrling robustreceivedsignalstrengthindicatorrssibasedmultitargetlocalizationviagaussianprocessregression
AT hyeonseokrou robustreceivedsignalstrengthindicatorrssibasedmultitargetlocalizationviagaussianprocessregression
AT giuseppethadeufreitasdeabreu robustreceivedsignalstrengthindicatorrssibasedmultitargetlocalizationviagaussianprocessregression
AT davidgonzalezg robustreceivedsignalstrengthindicatorrssibasedmultitargetlocalizationviagaussianprocessregression
AT osvaldogonsa robustreceivedsignalstrengthindicatorrssibasedmultitargetlocalizationviagaussianprocessregression