We put forward and demonstrate a angle-of-arrival (AOA) based visible-lightpositioning (VLP) system using quadrant-solar-cell (QSC) and third-order ridge regression machine learning (RRML) to improve the positioning accuracy.

In this work, we propose and demonstrate a received-signal-strength (RSS) based visiblelight-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. INDEX TERMS Visible light communication (VLC), visible light positioning (VLP), light-emitting-diode (LED), machine learning.

We propose and demonstrate using the DIALux software with our proposed linear-regression 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.

No abstract

We propose and demonstrate using DIALux software with regression-machine-learning for designing visible-light-positioning (VLP) systems. Besides, the proposed scheme can also reduce the burden of training data collection in VLP systems.