Enabling Dynamic Indoor Localization by Employing Intersection over Union as a Metric

Lucie Klus; Roman Klus; Joaquín Torres-Sospedra; Elena Simona Lohan; Ivo Silva; Cristiano Pendão; Mikko Valkama

doi:10.1109/VTC2024-Fall63153.2024.10758013

Enabling Dynamic Indoor Localization by Employing Intersection over Union as a Metric

Lucie Klus^*
, Roman Klus
, Joaquín Torres-Sospedra
, Elena Simona Lohan
, Ivo Silva
, Cristiano Pendão
, Mikko Valkama

^*Corresponding author for this work

Research output: Chapter in Book/Report/Conference proceeding › Conference contribution › Scientific › peer-review

1 Citation (Scopus)

48 Downloads (Pure)

Abstract

In modern wireless networks evolving towards 6^th generation, localization, and sensing in indoor environments play an increasingly critical role in ensuring reliability, security, and control over network users, including vehicular assets. Despite recent advancements in deep learning, using k-Nearest Neighbors (k-NN) as a positioning algorithm in Received Signal Strength Indicator (RSSI) fingerprinting-based localization still provides numerous advantages, including localization accuracy, reliability, and interpretability. In this work, we introduce Intersection over Union (IoU) as a novel similarity metric and introduce κ-enhanced k-NN, which enables dynamic neighbor selection leading to improved performance and generalization capabilities of the positioning algorithm. In the evaluation using 26 publicly available indoor positioning datasets, we clearly show the improvements in localization accuracy of the combined IoU with κ-enhanced k-NN over the relevant baselines.

Original language	English
Title of host publication	2024 IEEE 100th Vehicular Technology Conference, VTC 2024-Fall - Proceedings
Publisher	IEEE
Number of pages	7
ISBN (Electronic)	979-8-3315-1778-6
ISBN (Print)	979-8-3315-1779-3
DOIs	https://doi.org/10.1109/VTC2024-Fall63153.2024.10758013
Publication status	Published - 2024
Publication type	A4 Article in conference proceedings
Event	IEEE Vehicular Technology Conference - Washington, United States Duration: 7 Oct 2024 → 10 Oct 2024

Publication series

Name	IEEE Vehicular Technology Conference
ISSN (Print)	1090-3038
ISSN (Electronic)	2577-2465

Conference

Conference	IEEE Vehicular Technology Conference
Country/Territory	United States
City	Washington
Period	7/10/24 → 10/10/24

Funding

This work was supported by the Research Council of Finland (grants #357730, #359095) and the European Union's Horizon 2020 Research and Innovation programme under the Marie Sklodowska Curie grant agreement No. 813278 (A-WEAR: A network for dynamic wearable applications with privacy constraints, http://www.a-wear.eu/); L. Klus acknowledges funding from Nokia Foundation, grant number 20231420; J. Torres-Sospedra acknowledges funding from Generalitat Valenciana (CIDEXG/2023/17, Conselleria d'Educaci\u00F3, Universitats i Ocupaci\u00F3); C. Pend\u00E3o and I. Silva acknowledge funding by FCT - Funda\u00E7\u00E3o para a Ci\u00EAncia e Tecnologia within the R&D Units Project Scope: UIDB/00319/2020.

Funders	Funder number
Fundação para a Ciência e a Tecnologia	UIDB/00319/2020
Horizon 2020	813278
Nokia Foundation	20231420
Research Council of Finland	357730, 359095
Generalitat Valenciana	CIDEXG/2023/17

Keywords

Fingerprinting
Indoor Positioning
Intersection over Union
IoU
k-Nearest Neighbors
Localization

Publication forum classification

Publication forum level 1

ASJC Scopus subject areas

Computer Science Applications
Electrical and Electronic Engineering
Applied Mathematics

Access to Document

10.1109/VTC2024-Fall63153.2024.10758013

VTC_Fall_2024_IoU_indoor_localization
This publication is copyrighted. You may download, display and print it for Your own personal use. Commercial use is prohibited.
Accepted author manuscript, 283 KBLicence: Unspecified

https://urn.fi/URN:NBN:fi:tuni-202501021043Licence: Unspecified

Supplementary material for "Enabling Dynamic Indoor Localization by Employing Intersection over Union as a Metric"
Klus, L. (Creator), Klus, R. (Creator), Joaquín, T.-S. (Creator), Elena Simona, L. (Creator), Silva, I. (Creator), Pendão, C. (Creator) & Valkama, M. (Creator), Zenodo, 30 Jan 2025
DOI: 10.5281/zenodo.11016090
Dataset: Software

Cite this

@inproceedings{3ccd466efb60490e9737aca540f9c44b,

title = "Enabling Dynamic Indoor Localization by Employing Intersection over Union as a Metric",

abstract = "In modern wireless networks evolving towards 6th generation, localization, and sensing in indoor environments play an increasingly critical role in ensuring reliability, security, and control over network users, including vehicular assets. Despite recent advancements in deep learning, using k-Nearest Neighbors (k-NN) as a positioning algorithm in Received Signal Strength Indicator (RSSI) fingerprinting-based localization still provides numerous advantages, including localization accuracy, reliability, and interpretability. In this work, we introduce Intersection over Union (IoU) as a novel similarity metric and introduce κ-enhanced k-NN, which enables dynamic neighbor selection leading to improved performance and generalization capabilities of the positioning algorithm. In the evaluation using 26 publicly available indoor positioning datasets, we clearly show the improvements in localization accuracy of the combined IoU with κ-enhanced k-NN over the relevant baselines.",

keywords = "Fingerprinting, Indoor Positioning, Intersection over Union, IoU, k-Nearest Neighbors, Localization",

author = "Lucie Klus and Roman Klus and Joaqu{\'i}n Torres-Sospedra and Lohan, \{Elena Simona\} and Ivo Silva and Cristiano Pend{\~a}o and Mikko Valkama",

note = "Publisher Copyright: {\textcopyright} 2024 IEEE.; IEEE Vehicular Technology Conference ; Conference date: 07-10-2024 Through 10-10-2024",

year = "2024",

doi = "10.1109/VTC2024-Fall63153.2024.10758013",

language = "English",

isbn = "979-8-3315-1779-3",

series = "IEEE Vehicular Technology Conference",

publisher = "IEEE",

booktitle = "2024 IEEE 100th Vehicular Technology Conference, VTC 2024-Fall - Proceedings",

address = "United States",

}

Klus, L , Klus, R, Torres-Sospedra, J, Lohan, ES, Silva, I, Pendão, C & Valkama, M 2024, Enabling Dynamic Indoor Localization by Employing Intersection over Union as a Metric. in 2024 IEEE 100th Vehicular Technology Conference, VTC 2024-Fall - Proceedings. IEEE Vehicular Technology Conference, IEEE, IEEE Vehicular Technology Conference, Washington, United States, 7/10/24. https://doi.org/10.1109/VTC2024-Fall63153.2024.10758013

Enabling Dynamic Indoor Localization by Employing Intersection over Union as a Metric. / Klus, Lucie ; Klus, Roman; Torres-Sospedra, Joaquín et al.
2024 IEEE 100th Vehicular Technology Conference, VTC 2024-Fall - Proceedings. IEEE, 2024. (IEEE Vehicular Technology Conference).

Research output: Chapter in Book/Report/Conference proceeding › Conference contribution › Scientific › peer-review

TY - GEN

T1 - Enabling Dynamic Indoor Localization by Employing Intersection over Union as a Metric

AU - Klus, Lucie

AU - Klus, Roman

AU - Torres-Sospedra, Joaquín

AU - Lohan, Elena Simona

AU - Silva, Ivo

AU - Pendão, Cristiano

AU - Valkama, Mikko

PY - 2024

Y1 - 2024

N2 - In modern wireless networks evolving towards 6th generation, localization, and sensing in indoor environments play an increasingly critical role in ensuring reliability, security, and control over network users, including vehicular assets. Despite recent advancements in deep learning, using k-Nearest Neighbors (k-NN) as a positioning algorithm in Received Signal Strength Indicator (RSSI) fingerprinting-based localization still provides numerous advantages, including localization accuracy, reliability, and interpretability. In this work, we introduce Intersection over Union (IoU) as a novel similarity metric and introduce κ-enhanced k-NN, which enables dynamic neighbor selection leading to improved performance and generalization capabilities of the positioning algorithm. In the evaluation using 26 publicly available indoor positioning datasets, we clearly show the improvements in localization accuracy of the combined IoU with κ-enhanced k-NN over the relevant baselines.

AB - In modern wireless networks evolving towards 6th generation, localization, and sensing in indoor environments play an increasingly critical role in ensuring reliability, security, and control over network users, including vehicular assets. Despite recent advancements in deep learning, using k-Nearest Neighbors (k-NN) as a positioning algorithm in Received Signal Strength Indicator (RSSI) fingerprinting-based localization still provides numerous advantages, including localization accuracy, reliability, and interpretability. In this work, we introduce Intersection over Union (IoU) as a novel similarity metric and introduce κ-enhanced k-NN, which enables dynamic neighbor selection leading to improved performance and generalization capabilities of the positioning algorithm. In the evaluation using 26 publicly available indoor positioning datasets, we clearly show the improvements in localization accuracy of the combined IoU with κ-enhanced k-NN over the relevant baselines.

KW - Fingerprinting

KW - Indoor Positioning

KW - Intersection over Union

KW - IoU

KW - k-Nearest Neighbors

KW - Localization

U2 - 10.1109/VTC2024-Fall63153.2024.10758013

DO - 10.1109/VTC2024-Fall63153.2024.10758013

M3 - Conference contribution

AN - SCOPUS:85213009365

SN - 979-8-3315-1779-3

T3 - IEEE Vehicular Technology Conference

BT - 2024 IEEE 100th Vehicular Technology Conference, VTC 2024-Fall - Proceedings

PB - IEEE

T2 - IEEE Vehicular Technology Conference

Y2 - 7 October 2024 through 10 October 2024

ER -

Enabling Dynamic Indoor Localization by Employing Intersection over Union as a Metric

Abstract

Publication series

Conference

Funding

Keywords

Publication forum classification

ASJC Scopus subject areas

Access to Document

Fingerprint

Datasets

Supplementary material for "Enabling Dynamic Indoor Localization by Employing Intersection over Union as a Metric"

Cite this