Visible light communication and positioning using positioning cells and machine learning algorithms

Abstract

We propose and experimentally demonstrate a practical visible light position (VLP) system using repeated unit cells and machine learning (ML) algorithms. ML is employed to increase the positioning accuracy. Algorithms of the 2nd-order regression ML model and the polynomial trilateral ML model are discussed. More than 80% of the measurement data have position error within 4 cm when using the 2nd-order regression ML model, while the position error is within 5 cm when using the polynomial trilateral ML model. (C) 2019 Optical Society of America under the terms of the OSA Open Access Publishing Agreement