In recent times, several applications requiring highly accurate indoor positioning systems have been developed. Since global positioning system (GPS) is unavailable/less accurate in the indoor environment, alternative techniques such as… Click to show full abstract
In recent times, several applications requiring highly accurate indoor positioning systems have been developed. Since global positioning system (GPS) is unavailable/less accurate in the indoor environment, alternative techniques such as visible light positioning (VLP) is considered. The VLP system benefts from wide availability of illumination infrastructure, energy effciency and absence of electromagnetic interference. However, there is a limited number of studies on three dimensional (3-D) VLP and the effect of multipath propagation on the accuracy of the 3-D VLP. This paper proposes a supervised artifcial neural network (ANN) to provide accurate 3-D VLP whilst considering multipath propagation using receiver diversity. The results show that the proposed system can accurately estimate the 3-D position with an average RMS error of 0.0198m and 0.021m for line-of-sight (LOS) and non-line-of-sight (nLOS) link respectively. For 2-D localisation, the average RMS errors are 0.0103m and 0.0133m, respectively.
               
Click one of the above tabs to view related content.