A Multi-Scale Feature Selection Framework for WiFi Access Points Line-of-sight Identification

Xu Feng; Khuong An Nguyen; Zhiyuan Luo

doi:10.1109/WCNC55385.2023.10118876

A Multi-Scale Feature Selection Framework for WiFi Access Points Line-of-sight Identification

Xu Feng
, Khuong An Nguyen
, Zhiyuan Luo

Research output: Contribution to conference › Paper › peer-review

Abstract

Despite its high accuracy in the ideal condition where there is a direct line-of-sight between the Access Points and the user, most WiFi indoor positioning systems struggle under the non-line-of-sight scenario. Thus, we propose a novel feature selection algorithm leveraging Machine Learning based weighting methods and multi-scale selection, with WiFi RTT and RSS as the input signals. We evaluate the algorithm performance on a campus building floor. The results indicated an accuracy of 93% line-of-sight detection success with 13 Access Points, using only 3 seconds of test samples at any moment; and an accuracy of 98% for individual AP line-of-sight detection.

Original language	English
DOIs	https://doi.org/10.1109/WCNC55385.2023.10118876
Publication status	Published - 26 Mar 2023
Event	IEEE Wireless Communications and Networking Conference (WCNC) 2023 - Glasgow, United Kingdom Duration: 26 Mar 2023 → 29 Mar 2023 https://wcnc2023.ieee-wcnc.org/

Conference

Conference	IEEE Wireless Communications and Networking Conference (WCNC) 2023
Abbreviated title	IEEE WCNC 2023
Country/Territory	United Kingdom
City	Glasgow
Period	26/03/23 → 29/03/23
Internet address	https://wcnc2023.ieee-wcnc.org/

Keywords

WiFi Round-Trip Time
feature selection
indoor positioning

Access to Document

10.1109/WCNC55385.2023.10118876

A_Multi_Scale_Feature_Selection_FrameworkAccepted author manuscript, 3.05 MBLicence: Other

Cite this

@conference{8edccd016ede4bc28ef08d458dcc7ff6,

title = "A Multi-Scale Feature Selection Framework for WiFi Access Points Line-of-sight Identification",

abstract = "Despite its high accuracy in the ideal condition where there is a direct line-of-sight between the Access Points and the user, most WiFi indoor positioning systems struggle under the non-line-of-sight scenario. Thus, we propose a novel feature selection algorithm leveraging Machine Learning based weighting methods and multi-scale selection, with WiFi RTT and RSS as the input signals. We evaluate the algorithm performance on a campus building floor. The results indicated an accuracy of 93\% line-of-sight detection success with 13 Access Points, using only 3 seconds of test samples at any moment; and an accuracy of 98\% for individual AP line-of-sight detection.",

keywords = "WiFi Round-Trip Time, feature selection, indoor positioning",

author = "Xu Feng and Nguyen, \{Khuong An\} and Zhiyuan Luo",

year = "2023",

month = mar,

day = "26",

doi = "10.1109/WCNC55385.2023.10118876",

language = "English",

note = "IEEE Wireless Communications and Networking Conference (WCNC) 2023, IEEE WCNC 2023 ; Conference date: 26-03-2023 Through 29-03-2023",

url = "https://wcnc2023.ieee-wcnc.org/",

}

TY - CONF

T1 - A Multi-Scale Feature Selection Framework for WiFi Access Points Line-of-sight Identification

AU - Feng, Xu

AU - Nguyen, Khuong An

AU - Luo, Zhiyuan

PY - 2023/3/26

Y1 - 2023/3/26

N2 - Despite its high accuracy in the ideal condition where there is a direct line-of-sight between the Access Points and the user, most WiFi indoor positioning systems struggle under the non-line-of-sight scenario. Thus, we propose a novel feature selection algorithm leveraging Machine Learning based weighting methods and multi-scale selection, with WiFi RTT and RSS as the input signals. We evaluate the algorithm performance on a campus building floor. The results indicated an accuracy of 93% line-of-sight detection success with 13 Access Points, using only 3 seconds of test samples at any moment; and an accuracy of 98% for individual AP line-of-sight detection.

AB - Despite its high accuracy in the ideal condition where there is a direct line-of-sight between the Access Points and the user, most WiFi indoor positioning systems struggle under the non-line-of-sight scenario. Thus, we propose a novel feature selection algorithm leveraging Machine Learning based weighting methods and multi-scale selection, with WiFi RTT and RSS as the input signals. We evaluate the algorithm performance on a campus building floor. The results indicated an accuracy of 93% line-of-sight detection success with 13 Access Points, using only 3 seconds of test samples at any moment; and an accuracy of 98% for individual AP line-of-sight detection.

KW - WiFi Round-Trip Time

KW - feature selection

KW - indoor positioning

UR - https://ieeexplore.ieee.org/document/10118876

U2 - 10.1109/WCNC55385.2023.10118876

DO - 10.1109/WCNC55385.2023.10118876

M3 - Paper

T2 - IEEE Wireless Communications and Networking Conference (WCNC) 2023

Y2 - 26 March 2023 through 29 March 2023

ER -

A Multi-Scale Feature Selection Framework for WiFi Access Points Line-of-sight Identification

Abstract

Conference

Keywords

Access to Document

Other files and links

Fingerprint

Cite this