Improving Proximity Classification for Contact Tracing using a Multi-channel Approach

Eric Lanfer; Thomas Hänel; Roland Martijn van Rijswijk - Deij; Nils Aschenbruck

doi:10.48550/arXiv.2201.10401

Improving Proximity Classification for Contact Tracing using a Multi-channel Approach

Eric Lanfer^*, Thomas Hänel, Roland Martijn van Rijswijk - Deij, Nils Aschenbruck

^*Corresponding author for this work

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

85 Downloads (Pure)

Abstract

Due to the COVID-19 pandemic, smartphone-based proximity tracing systems became of utmost interest. Many of these systems use Bluetooth Low Energy (BLE) signal strength data to estimate the distance between two persons. The quality of this method depends on many factors and, therefore, does hardly deliver accurate results. We present a multi-channel approach to improve proximity classification, and a novel, publicly available data set that contains matched IEEE 802.11 (2.4 & 5 GHz) and BLE signal strength data, measured in four different environments. We utilize these data to train machine learning models. The evaluation showed significant improvements in the distance classification and consequently also the contact tracing accuracy. However, we also encountered privacy problems and limitations due to the consistency and interval at which such probes are sent. We discuss these limitations and sketch how our approach could be improved to make it suitable for real-world deployment.

Original language	English
Title of host publication	Proceedings of the 47th Conference on Local Computer Networks (LCN)
Place of Publication	Piscataway, NJ
Publisher	IEEE
Pages	64-72
ISBN (Electronic)	978-1-6654-8001-7
ISBN (Print)	978-1-6654-8002-4
DOIs	https://doi.org/10.48550/arXiv.2201.10401 https://doi.org/10.1109/LCN53696.2022.9843531
Publication status	Published - 26 Sept 2022
Event	47th Conference on Local Computer Networks, LCN 2022 - Edmonton, Canada Duration: 26 Sept 2022 → 29 Sept 2022 Conference number: 47

Conference

Conference	47th Conference on Local Computer Networks, LCN 2022
Abbreviated title	LCN 2022
Country/Territory	Canada
City	Edmonton
Period	26/09/22 → 29/09/22

Keywords

Privacy
Proximity
Contact tracing app
Security
Cybersecurity
2023 OA procedure

Access to Document

ArticleFinal published version, 1.99 MBLicence: Taverne

Cite this

@inproceedings{ca8b6111283a4f8488bb59b40e9b8876,

title = "Improving Proximity Classification for Contact Tracing using a Multi-channel Approach",

abstract = "Due to the COVID-19 pandemic, smartphone-based proximity tracing systems became of utmost interest. Many of these systems use Bluetooth Low Energy (BLE) signal strength data to estimate the distance between two persons. The quality of this method depends on many factors and, therefore, does hardly deliver accurate results. We present a multi-channel approach to improve proximity classification, and a novel, publicly available data set that contains matched IEEE 802.11 (2.4 \& 5 GHz) and BLE signal strength data, measured in four different environments. We utilize these data to train machine learning models. The evaluation showed significant improvements in the distance classification and consequently also the contact tracing accuracy. However, we also encountered privacy problems and limitations due to the consistency and interval at which such probes are sent. We discuss these limitations and sketch how our approach could be improved to make it suitable for real-world deployment.",

keywords = "Privacy, Proximity, Contact tracing app, Security, Cybersecurity, 2023 OA procedure",

author = "Eric Lanfer and Thomas H{\"a}nel and \{van Rijswijk - Deij\}, \{Roland Martijn\} and Nils Aschenbruck",

year = "2022",

month = sep,

day = "26",

doi = "10.48550/arXiv.2201.10401",

language = "English",

isbn = "978-1-6654-8002-4",

pages = "64--72",

booktitle = "Proceedings of the 47th Conference on Local Computer Networks (LCN)",

publisher = "IEEE",

address = "United States",

note = "47th Conference on Local Computer Networks, LCN 2022, LCN 2022 ; Conference date: 26-09-2022 Through 29-09-2022",

}

Lanfer, E, Hänel, T, van Rijswijk - Deij, RM & Aschenbruck, N 2022, Improving Proximity Classification for Contact Tracing using a Multi-channel Approach. in Proceedings of the 47th Conference on Local Computer Networks (LCN). IEEE, Piscataway, NJ, pp. 64-72, 47th Conference on Local Computer Networks, LCN 2022, Edmonton, Alberta, Canada, 26/09/22. https://doi.org/10.48550/arXiv.2201.10401, https://doi.org/10.1109/LCN53696.2022.9843531

Improving Proximity Classification for Contact Tracing using a Multi-channel Approach. / Lanfer, Eric; Hänel, Thomas; van Rijswijk - Deij, Roland Martijn et al.
Proceedings of the 47th Conference on Local Computer Networks (LCN). Piscataway, NJ: IEEE, 2022. p. 64-72.

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

TY - GEN

T1 - Improving Proximity Classification for Contact Tracing using a Multi-channel Approach

AU - Lanfer, Eric

AU - Hänel, Thomas

AU - van Rijswijk - Deij, Roland Martijn

AU - Aschenbruck, Nils

N1 - Conference code: 47

PY - 2022/9/26

Y1 - 2022/9/26

N2 - Due to the COVID-19 pandemic, smartphone-based proximity tracing systems became of utmost interest. Many of these systems use Bluetooth Low Energy (BLE) signal strength data to estimate the distance between two persons. The quality of this method depends on many factors and, therefore, does hardly deliver accurate results. We present a multi-channel approach to improve proximity classification, and a novel, publicly available data set that contains matched IEEE 802.11 (2.4 & 5 GHz) and BLE signal strength data, measured in four different environments. We utilize these data to train machine learning models. The evaluation showed significant improvements in the distance classification and consequently also the contact tracing accuracy. However, we also encountered privacy problems and limitations due to the consistency and interval at which such probes are sent. We discuss these limitations and sketch how our approach could be improved to make it suitable for real-world deployment.

AB - Due to the COVID-19 pandemic, smartphone-based proximity tracing systems became of utmost interest. Many of these systems use Bluetooth Low Energy (BLE) signal strength data to estimate the distance between two persons. The quality of this method depends on many factors and, therefore, does hardly deliver accurate results. We present a multi-channel approach to improve proximity classification, and a novel, publicly available data set that contains matched IEEE 802.11 (2.4 & 5 GHz) and BLE signal strength data, measured in four different environments. We utilize these data to train machine learning models. The evaluation showed significant improvements in the distance classification and consequently also the contact tracing accuracy. However, we also encountered privacy problems and limitations due to the consistency and interval at which such probes are sent. We discuss these limitations and sketch how our approach could be improved to make it suitable for real-world deployment.

KW - Privacy

KW - Proximity

KW - Contact tracing app

KW - Security

KW - Cybersecurity

KW - 2023 OA procedure

U2 - 10.48550/arXiv.2201.10401

DO - 10.48550/arXiv.2201.10401

M3 - Conference contribution

SN - 978-1-6654-8002-4

SP - 64

EP - 72

BT - Proceedings of the 47th Conference on Local Computer Networks (LCN)

PB - IEEE

CY - Piscataway, NJ

T2 - 47th Conference on Local Computer Networks, LCN 2022

Y2 - 26 September 2022 through 29 September 2022

ER -

Improving Proximity Classification for Contact Tracing using a Multi-channel Approach

Abstract

Conference

Keywords

Access to Document

Fingerprint

Cite this