Employing DIALux to relieve machine-learning training data collection when designing indoor positioning systems

Shao Hua Song; Dong Chang Lin; Yang Liu; Chi Wai Chow; Yun Han Chang; Kun Hsien Lin; Yi Chang Wang; Yi Yuan Chen

doi:10.1364/OE.422851

Employing DIALux to relieve machine-learning training data collection when designing indoor positioning systems

Shao Hua Song, Dong Chang Lin, Yang Liu, Chi Wai Chow^*, Yun Han Chang, Kun Hsien Lin, Yi Chang Wang, Yi Yuan Chen

^*Corresponding author for this work

Department of Photonics

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

21 Scopus citations

Abstract

We propose and demonstrate using the DIALux software with our proposed linearregression machine-learning (LRML) algorithm for designing a practical indoor visible light positioning (VLP) system. Experimental results reveal that the average position errors and error distributions of the model trained via the DIALux simulation and trained via the experimental data match with each other. This implies that the training data can be generated in DIALux if the room dimensions and LED luminary parameters are available. The proposed scheme could relieve the burden of training data collection in VLP systems.

Original language	English
Pages (from-to)	16887-16892
Number of pages	6
Journal	Optics Express
Volume	29
Issue number	11
DOIs	https://doi.org/10.1364/OE.422851
State	Published - 24 May 2021

Access to Document

10.1364/OE.422851

Cite this

@article{0ad48d3d78eb4d29875fbe62b8ed3275,

title = "Employing DIALux to relieve machine-learning training data collection when designing indoor positioning systems",

abstract = "We propose and demonstrate using the DIALux software with our proposed linearregression machine-learning (LRML) algorithm for designing a practical indoor visible light positioning (VLP) system. Experimental results reveal that the average position errors and error distributions of the model trained via the DIALux simulation and trained via the experimental data match with each other. This implies that the training data can be generated in DIALux if the room dimensions and LED luminary parameters are available. The proposed scheme could relieve the burden of training data collection in VLP systems. ",

author = "Song, {Shao Hua} and Lin, {Dong Chang} and Yang Liu and Chow, {Chi Wai} and Chang, {Yun Han} and Lin, {Kun Hsien} and Wang, {Yi Chang} and Chen, {Yi Yuan}",

note = "Publisher Copyright: {\textcopyright} 2021 Optical Society of America.",

year = "2021",

month = may,

day = "24",

doi = "10.1364/OE.422851",

language = "English",

volume = "29",

pages = "16887--16892",

journal = "Optics Express",

issn = "1094-4087",

publisher = "Optica Publishing Group",

number = "11",

}

TY - JOUR

T1 - Employing DIALux to relieve machine-learning training data collection when designing indoor positioning systems

AU - Song, Shao Hua

AU - Lin, Dong Chang

AU - Liu, Yang

AU - Chow, Chi Wai

AU - Chang, Yun Han

AU - Lin, Kun Hsien

AU - Wang, Yi Chang

AU - Chen, Yi Yuan

PY - 2021/5/24

Y1 - 2021/5/24

N2 - We propose and demonstrate using the DIALux software with our proposed linearregression machine-learning (LRML) algorithm for designing a practical indoor visible light positioning (VLP) system. Experimental results reveal that the average position errors and error distributions of the model trained via the DIALux simulation and trained via the experimental data match with each other. This implies that the training data can be generated in DIALux if the room dimensions and LED luminary parameters are available. The proposed scheme could relieve the burden of training data collection in VLP systems.

AB - We propose and demonstrate using the DIALux software with our proposed linearregression machine-learning (LRML) algorithm for designing a practical indoor visible light positioning (VLP) system. Experimental results reveal that the average position errors and error distributions of the model trained via the DIALux simulation and trained via the experimental data match with each other. This implies that the training data can be generated in DIALux if the room dimensions and LED luminary parameters are available. The proposed scheme could relieve the burden of training data collection in VLP systems.

UR - http://www.scopus.com/inward/record.url?scp=85106210307&partnerID=8YFLogxK

U2 - 10.1364/OE.422851

DO - 10.1364/OE.422851

M3 - Article

C2 - 34154241

AN - SCOPUS:85106210307

SN - 1094-4087

VL - 29

SP - 16887

EP - 16892

JO - Optics Express

JF - Optics Express

IS - 11

ER -

Employing DIALux to relieve machine-learning training data collection when designing indoor positioning systems

Abstract

Access to Document

Other files and links

Fingerprint

Cite this