Applying t-Distributed Stochastic Neighbor Embedding for Improving Fingerprinting-Based Localization System

Getaneh Berie Tarekegn; Li Chia Tai; Hsin Piao Lin; Belayneh Abebe Tesfaw; Rong Terng Juang; Huan Chia Hsu; Kai Lun Huang; Kanishk Singh

doi:10.1109/LSENS.2023.3301838

Applying t-Distributed Stochastic Neighbor Embedding for Improving Fingerprinting-Based Localization System

Getaneh Berie Tarekegn, Li Chia Tai^*, Hsin Piao Lin, Belayneh Abebe Tesfaw, Rong Terng Juang, Huan Chia Hsu, Kai Lun Huang, Kanishk Singh

^*Corresponding author for this work

Institute of Electrical and Control Engineering

Research output: Contribution to journal › Article › peer-review

2 Scopus citations

Abstract

Large-scale location estimation is crucial for many artificial intelligence Internet of Things (IoT) applications in the era of smart cities. This letter proposes a deep learning-based outdoor positioning scheme for large-scale wireless settings using fingerprinting techniques. We first developed a feature extraction technique using t-distributed stochastic neighbor embedding (t-SNE) to extract dominant and distinguishable features while eliminating noises from the radio fingerprints. Afterward, we developed a deep learning-based coarse-fine localization framework to improve positioning performance significantly. Based on our numerical analysis, the proposed scheme reduces computation time by 64.41%, and the average positioning error is 38 cm. Therefore, the proposed approach significantly improved positioning accuracy and reduced computation time.

Original language	English
Article number	6005004
Journal	IEEE Sensors Letters
Volume	7
Issue number	9
DOIs	https://doi.org/10.1109/LSENS.2023.3301838
State	Published - 1 Sep 2023

Keywords

Feature extraction technique
fingerprinting method
location estimation
long short-term memory (LSTM)
signal fingerprints
support vector machine (SVM)

UN SDGs

This output contributes to the following UN Sustainable Development Goals (SDGs)

Access to Document

10.1109/LSENS.2023.3301838

Cite this

@article{2b693bd7a72b475587b8bf210d3f4e8c,

title = "Applying t-Distributed Stochastic Neighbor Embedding for Improving Fingerprinting-Based Localization System",

abstract = "Large-scale location estimation is crucial for many artificial intelligence Internet of Things (IoT) applications in the era of smart cities. This letter proposes a deep learning-based outdoor positioning scheme for large-scale wireless settings using fingerprinting techniques. We first developed a feature extraction technique using t-distributed stochastic neighbor embedding (t-SNE) to extract dominant and distinguishable features while eliminating noises from the radio fingerprints. Afterward, we developed a deep learning-based coarse-fine localization framework to improve positioning performance significantly. Based on our numerical analysis, the proposed scheme reduces computation time by 64.41%, and the average positioning error is 38 cm. Therefore, the proposed approach significantly improved positioning accuracy and reduced computation time.",

keywords = "Feature extraction technique, fingerprinting method, location estimation, long short-term memory (LSTM), signal fingerprints, support vector machine (SVM)",

author = "Tarekegn, {Getaneh Berie} and Tai, {Li Chia} and Lin, {Hsin Piao} and Tesfaw, {Belayneh Abebe} and Juang, {Rong Terng} and Hsu, {Huan Chia} and Huang, {Kai Lun} and Kanishk Singh",

note = "Publisher Copyright: {\textcopyright} 2017 IEEE.",

year = "2023",

month = sep,

day = "1",

doi = "10.1109/LSENS.2023.3301838",

language = "English",

volume = "7",

journal = "IEEE Sensors Letters",

issn = "2475-1472",

publisher = "Institute of Electrical and Electronics Engineers Inc.",

number = "9",

}

TY - JOUR

T1 - Applying t-Distributed Stochastic Neighbor Embedding for Improving Fingerprinting-Based Localization System

AU - Tarekegn, Getaneh Berie

AU - Tai, Li Chia

AU - Lin, Hsin Piao

AU - Tesfaw, Belayneh Abebe

AU - Juang, Rong Terng

AU - Hsu, Huan Chia

AU - Huang, Kai Lun

AU - Singh, Kanishk

PY - 2023/9/1

Y1 - 2023/9/1

N2 - Large-scale location estimation is crucial for many artificial intelligence Internet of Things (IoT) applications in the era of smart cities. This letter proposes a deep learning-based outdoor positioning scheme for large-scale wireless settings using fingerprinting techniques. We first developed a feature extraction technique using t-distributed stochastic neighbor embedding (t-SNE) to extract dominant and distinguishable features while eliminating noises from the radio fingerprints. Afterward, we developed a deep learning-based coarse-fine localization framework to improve positioning performance significantly. Based on our numerical analysis, the proposed scheme reduces computation time by 64.41%, and the average positioning error is 38 cm. Therefore, the proposed approach significantly improved positioning accuracy and reduced computation time.

AB - Large-scale location estimation is crucial for many artificial intelligence Internet of Things (IoT) applications in the era of smart cities. This letter proposes a deep learning-based outdoor positioning scheme for large-scale wireless settings using fingerprinting techniques. We first developed a feature extraction technique using t-distributed stochastic neighbor embedding (t-SNE) to extract dominant and distinguishable features while eliminating noises from the radio fingerprints. Afterward, we developed a deep learning-based coarse-fine localization framework to improve positioning performance significantly. Based on our numerical analysis, the proposed scheme reduces computation time by 64.41%, and the average positioning error is 38 cm. Therefore, the proposed approach significantly improved positioning accuracy and reduced computation time.

KW - Feature extraction technique

KW - fingerprinting method

KW - location estimation

KW - long short-term memory (LSTM)

KW - signal fingerprints

KW - support vector machine (SVM)

UR - http://www.scopus.com/inward/record.url?scp=85166769808&partnerID=8YFLogxK

U2 - 10.1109/LSENS.2023.3301838

DO - 10.1109/LSENS.2023.3301838

M3 - Article

AN - SCOPUS:85166769808

SN - 2475-1472

VL - 7

JO - IEEE Sensors Letters

JF - IEEE Sensors Letters

IS - 9

M1 - 6005004

ER -

Applying t-Distributed Stochastic Neighbor Embedding for Improving Fingerprinting-Based Localization System

Abstract

Keywords

UN SDGs

Access to Document

Other files and links

Fingerprint

Cite this