Accuracy of a single position estimate for k NN-based fingerprinting indoor positioning applying error propagation theory

Indoor Positioning Systems usually consider the average positioning error over a set of evaluation samples, or a quartile of that value, as the global error. However, they do not provide a metric for the uncertainty for each individual position estimation. In this paper, we apply the error propagati...

Full description

Saved in:
Bibliographic Details
Published in:IEEE sensors journal 2023, Vol.23 (16), p.18765-18775
Main Authors: Perez-Navarro, Antoni, Montoliu, Raul, Sansano-Sansano, Emilio, Martinez-Garcia, Marina, Femenia, Ruben, Torres-Sospedra, Joaquín
Format: Article
Language:English
Subjects:
Algorithms
Ciências da Computação e da Informação
Ciências Naturais
Error propagation
Errors
Fingerprinting
Fingerprinting methods
Indoor positioning
Position measurement
Uncertainty
Citations: Items that this one cites
Items that cite this one
Online Access:Get full text
Tags: Add Tag
No Tags, Be the first to tag this record!
Description
Summary:Indoor Positioning Systems usually consider the average positioning error over a set of evaluation samples, or a quartile of that value, as the global error. However, they do not provide a metric for the uncertainty for each individual position estimation. In this paper, we apply the error propagation theory to the kNN algorithm in Wi-Fi fingerprint-based indoor positioning. Our proposed method does not only retrieve the position estimate but also describes how the uncertainties of the RSSI measurements propagate through the calculations. We have validated our proposed method with two open-access datasets. This work was supported in part by projects Grant PID2021-1226420B-C44 funded AEI/10.13039/501100011033/FEDER,UE, Grant PID2021-1226420B-C42 funded AEI/10.13039/501100011033/FEDER,UE, Grant TED2021-199866B–I00 funded AEI/10.13039/501100011033/ European Union NextGenerationEU/PRTR , UJI-A2022-12, CYTED Network “GeoLibero” and H2020-MSCA-IF 101023072.
ISSN:1530-437X
1558-1748
DOI:10.1109/JSEN.2023.3287856