Adaptive Weighted K-Nearest Neighbor Trilateration Algorithm for Visible Light Positioning

An adaptive weighted K-nearest neighbor (AWKNN) trilateration positioning algorithm fused with the channel state information (CSI) is proposed to optimize accuracy of visible light positioning. The core concept behind this combine WKNN ranging based on CSI. direct path distance estimated by CSI utilized construct a position set consisting multiple positions and corresponding database containing vectors. error parameters combinations different vectors are calculated iteratively evaluate impact K-values weights accuracy. can achieve high-precision adaptively selecting K-value weight. A typical 4 m × 3 indoor multipath scene four LEDs established simulate performance. simulation results reveal that mean CSI-based AWKNN achieves 1.84 cm, root square (RMSE) 2.13 cm. Compared least squares (LS) method, nonlinear LS average method decreased 29%, 16%, 17%, whereas RMSE reduced 35%, 14%, 19%.