Received-Signal-Strength (RSS) Based 3D Visible-Light-Positioning (VLP) System Using Kernel Ridge Regression Machine Learning Algorithm With Sigmoid Function Data Preprocessing Method

Yu-Chun Wu; Chi-Wai Chow; Yang Liu; Yun-Shen Lin; Chong-You Hong; Dong-Chang Lin; Shao-Hua Song; Chien-Hung Yeh

doi:10.1109/ACCESS.2020.3041192

IEEE Access (Jan 2020)

Received-Signal-Strength (RSS) Based 3D Visible-Light-Positioning (VLP) System Using Kernel Ridge Regression Machine Learning Algorithm With Sigmoid Function Data Preprocessing Method

Yu-Chun Wu,
Chi-Wai Chow,
Yang Liu,
Yun-Shen Lin,
Chong-You Hong,
Dong-Chang Lin,
Shao-Hua Song,
Chien-Hung Yeh

Affiliations

Yu-Chun Wu: ORCiD; Department of Photonics, College of Electrical and Computer Engineering, National Chiao Tung University, Hsinchu, Taiwan
Chi-Wai Chow: ORCiD; Department of Photonics, College of Electrical and Computer Engineering, National Chiao Tung University, Hsinchu, Taiwan
Yang Liu: ORCiD; Philips Electronics Ltd., Shatin, Hong Kong
Yun-Shen Lin: ORCiD; Department of Photonics, College of Electrical and Computer Engineering, National Chiao Tung University, Hsinchu, Taiwan
Chong-You Hong: ORCiD; Department of Photonics, College of Electrical and Computer Engineering, National Chiao Tung University, Hsinchu, Taiwan
Dong-Chang Lin: ORCiD; Department of Photonics, College of Electrical and Computer Engineering, National Chiao Tung University, Hsinchu, Taiwan
Shao-Hua Song: ORCiD; Department of Photonics, College of Electrical and Computer Engineering, National Chiao Tung University, Hsinchu, Taiwan
Chien-Hung Yeh: ORCiD; Department of Photonics, Feng Chia University, Taichung, Taiwan

DOI: https://doi.org/10.1109/ACCESS.2020.3041192
Journal volume & issue: Vol. 8
pp. 214269 – 214281

Abstract

Read online

In this work, we propose and demonstrate a received-signal-strength (RSS) based visible-light-positioning (VLP) system using sigmoid function data preprocessing (SFDP) method; and apply it to two types of regression based machine learning algorithms; including the second-order linear regression machine learning (LRML) algorithm, and the kernel ridge regression machine learning (KRRML) algorithm. Experimental results indicate that the use of SFDP method can significantly improve the positioning accuracies in both the LRML and KRRML algorithms. Besides, the SFDP with KRRML scheme outperforms the other three schemes in terms of position accuracy, with the experimental average positioning error of about 2 cm in both horizontal and vertical directions.

Published in IEEE Access

ISSN: 2169-3536 (Online)
Publisher: IEEE
Country of publisher: United States
LCC subjects: Technology: Electrical engineering. Electronics. Nuclear engineering
Website: https://ieeexplore.ieee.org/xpl/RecentIssue.jsp?punumber=6287639

About the journal

Abstract

Keywords