A decision tree-based NLOS detection method for the UWB indoor location tracking accuracy improvement

Among existing wireless technologies, ultra-wideband (UWB) is the most promising solution for indoor location tracking. UWB has a great multipath fading immunity; however, great multipath resolvability alone does not eliminate the effect of non-line-of-sight (NLOS) and multipath propagation. NLOS and multipath propagation in indoor environments can easily produce meters of UWB ranging error. This condition gives an enormous impact on the accuracy of indoor location tracking data. To address this problem, we propose an NLOS detection method using recursive decision tree learning. Using the UWB channel quality indicators information, we develop our model with the Gini index and altered priors splitting criteria. We then validate the constructed model using the 10-fold cross-validation method. Our experiment shows that the constructed model has correctly detected 90% of both line-of-sight (LOS) and NLOS cases on the seven different indoor environments. The result of this work can be used for the UWB indoor location tracking accuracy improvement.