Indoor high-precision three-dimensional positioning algorithm based on visible light communication and fingerprinting using K-means and random forest

Jiajia Jiang; Weipeng Guan; Zhounan Chen; Yirong Chen

doi:10.1117/1.OE.58.1.016102

5 January 2019 Indoor high-precision three-dimensional positioning algorithm based on visible light communication and fingerprinting using K-means and random forest

Jiajia Jiang, Weipeng Guan, Zhounan Chen, Yirong Chen

Author Affiliations +

Optical Engineering, Vol. 58, Issue 1, 016102 (January 2019). https://doi.org/10.1117/1.OE.58.1.016102

Abstract

Recently, visible light communication (VLC) has been widely used in indoor positioning. Considering that conventional VLC-based positioning (VLP) algorithms are susceptible to interference and cannot adapt well to the complex indoor location environment, we propose a high-precision indoor three-dimensional positioning algorithm based on VLC and fingerprinting using fusion of K-means and random forest algorithms. Unlike the trilateration techniques based on received signal strength, the mentioned system does not depend on the model parameters and is robust to external interference. Besides, the proposed system introduces the concept of VLP kernel to compress the fingerprint database and shorten the training time. And we have validated the feasibility of our proposed VLC-based positioning system using fingerprinting in the real indoor VLP environment. Both simulation and experiment results verify that our proposed algorithm delivers satisfactory performance in terms of real-time ability and positioning accuracy, both of which are crucial for the performance of an indoor positioning system. Therefore, our proposed positioning system with strong interference immunity is a promising candidate for future indoor positioning applications.

Citation Download Citation

Jiajia Jiang, Weipeng Guan, Zhounan Chen, and Yirong Chen "Indoor high-precision three-dimensional positioning algorithm based on visible light communication and fingerprinting using K-means and random forest," Optical Engineering 58(1), 016102 (5 January 2019). https://doi.org/10.1117/1.OE.58.1.016102

Received: 23 September 2018; Accepted: 5 December 2018; Published: 5 January 2019

ACCESS THE FULL ARTICLE

INSTITUTIONAL
Select your institution to access the SPIE Digital Library.

SELECT YOUR INSTITUTION

PERSONAL
Sign in with your SPIE account to access your personal subscriptions or to use specific features such as save to my library, sign up for alerts, save searches, etc.

PERSONAL SIGN IN

No SPIE Account? Create one

;

PURCHASE THIS CONTENT

SUBSCRIBE TO DIGITAL LIBRARY

50 downloads per 1-year subscription

Members: $195

Non-members: $335 ADD TO CART

25 downloads per 1 - year subscription

Members: $145

Non-members: $250 ADD TO CART

PURCHASE SINGLE ARTICLE