Investigation on indoor visible light positioning systems

• Main Author: Lei, Lei
• Other Authors: Arokiaswami Alphones
• Format: Thesis-Master by Coursework
• Language: English
• Published: Nanyang Technological University 2020
• Subjects: Engineering::Electrical and electronic engineering::Optics, optoelectronics, photonics; Engineering::Electrical and electronic engineering::Wireless communication systems
• Online Access: https://hdl.handle.net/10356/142933
• Institution: Nanyang Technological University

With the development of communication technology, there are some shortcomings been found in wireless communication in terms of radio waves. For example, the limitation of the available spectrums. In order to tackle the bandwidth problem, the Light Fidelity (LiFi) technology is hence produced which is a new kind of communication method to transmit data using visible light proposed by a team from the University of Edinburgh [1]. Under the condition of the fast developing of LED based communication and positioning, plenty of new technologies have been invented based on the visible light communication theory, which include visible light positioning (VLP) application. VLP system is invented to offer a fast, safe and accurate indoor positioning method for company or personal using. To be specific, VLP system can be used in airport, office building or in a single house. And this project aims to find out a kind of neural network solution for the indoor VLP system to fix the error caused by the changing of different environments. Firstly, a static neural network based solver is constructed to perform indoor positioning functions with pre-training techniques. Then, to improve the robustness of the positioning system under environmental changes (e.g. dimming, reflections, temperature/humidity variations), a dynamic neural network with online updateable schematic is hence proposed. Moreover, the neural network based scheme can correct the error caused by the non-ideal irradiation patters in both intensity and time of the lamps to improve the accuracy of the VLP system.