A dynamic model switching algorithm for WiFi fingerprinting indoor positioning

Xu Feng; Khuong An Nguyen; Zhiyuan Luo

A dynamic model switching algorithm for WiFi fingerprinting indoor positioning

Xu Feng, Khuong An Nguyen, Zhiyuan Luo

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

Abstract

In 2023, there are various WiFi technologies and algorithms for an indoor positioning system. However, each technology and algorithm comes with their own strengths and weaknesses that may not universally benefit all building locations. Therefore, we propose a novel algorithm to dynamically switch to the most optimal positioning model at any given location, by utilising a Machine Learning based weighted model selection algorithm, with WiFi RSS and RTT signal measures as the input features. We evaluated our algorithm in three real-world indoor scenarios to demonstrate an improvement of up to 1.8 metres, compared to standard WiFi fingerprinting algorithm.

Original language	English
Number of pages	6
Publication status	Published - 25 Sept 2023
Event	13th International Conference on Indoor Positioning and Indoor Navigation (IPIN) - Nuremberg, Nuremberg, Germany Duration: 25 Sept 2023 → 28 Sept 2023 https://ipin-conference.org/2023/

Conference

Conference	13th International Conference on Indoor Positioning and Indoor Navigation (IPIN)
Country/Territory	Germany
City	Nuremberg
Period	25/09/23 → 28/09/23
Internet address	https://ipin-conference.org/2023/

Keywords

WiFi fingerprinting
Model Switching
Feature Selection

Cite this

@conference{c802b4634b3b4548bd4e3612b824bb76,

title = "A dynamic model switching algorithm for WiFi fingerprinting indoor positioning",

abstract = "In 2023, there are various WiFi technologies and algorithms for an indoor positioning system. However, each technology and algorithm comes with their own strengths and weaknesses that may not universally benefit all building locations. Therefore, we propose a novel algorithm to dynamically switch to the most optimal positioning model at any given location, by utilising a Machine Learning based weighted model selection algorithm, with WiFi RSS and RTT signal measures as the input features. We evaluated our algorithm in three real-world indoor scenarios to demonstrate an improvement of up to 1.8 metres, compared to standard WiFi fingerprinting algorithm.",

keywords = "WiFi fingerprinting, Model Switching, Feature Selection",

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

year = "2023",

month = sep,

day = "25",

language = "English",

note = "13th International Conference on Indoor Positioning and Indoor Navigation (IPIN) ; Conference date: 25-09-2023 Through 28-09-2023",

url = "https://ipin-conference.org/2023/",

}

TY - CONF

T1 - A dynamic model switching algorithm for WiFi fingerprinting indoor positioning

AU - Feng, Xu

AU - Nguyen, Khuong An

AU - Luo, Zhiyuan

PY - 2023/9/25

Y1 - 2023/9/25

N2 - In 2023, there are various WiFi technologies and algorithms for an indoor positioning system. However, each technology and algorithm comes with their own strengths and weaknesses that may not universally benefit all building locations. Therefore, we propose a novel algorithm to dynamically switch to the most optimal positioning model at any given location, by utilising a Machine Learning based weighted model selection algorithm, with WiFi RSS and RTT signal measures as the input features. We evaluated our algorithm in three real-world indoor scenarios to demonstrate an improvement of up to 1.8 metres, compared to standard WiFi fingerprinting algorithm.

AB - In 2023, there are various WiFi technologies and algorithms for an indoor positioning system. However, each technology and algorithm comes with their own strengths and weaknesses that may not universally benefit all building locations. Therefore, we propose a novel algorithm to dynamically switch to the most optimal positioning model at any given location, by utilising a Machine Learning based weighted model selection algorithm, with WiFi RSS and RTT signal measures as the input features. We evaluated our algorithm in three real-world indoor scenarios to demonstrate an improvement of up to 1.8 metres, compared to standard WiFi fingerprinting algorithm.

KW - WiFi fingerprinting

KW - Model Switching

KW - Feature Selection

M3 - Paper

T2 - 13th International Conference on Indoor Positioning and Indoor Navigation (IPIN)

Y2 - 25 September 2023 through 28 September 2023

ER -

A dynamic model switching algorithm for WiFi fingerprinting indoor positioning

Abstract

Conference

Keywords

Fingerprint

Cite this