Search

In ultra-wideband (UWB) positioning systems, positioning accuracy can be improved by determining the conditions of line-of-sight (LOS) and non-line-of-sight (NLOS) propagation and taking appropriate measures. The machine learning-based LOS/NLOS identification methods have been widely used due to its advantages of eliminating the need for prior knowledge. Unfortunately, traditional identification methods, such as LS-SVM, DT, and KTT, decrease significantly in other scenarios. Fortunately, Capsule Networks (CapsNet) showed its advantages of high accuracy and robustness in image classification as one of the latest machine learning achievements. Recently, some researchers noticed CapsNet and extended its application to LOS/NLOS identification. However, the generation ability and robustness of the capsule network needs to be further studied. In this paper, we verify the generalization ability and robustness of CapsNet based on the IEEE 802.15.4a channel model and experimental data. Experimental results show that the generation ability and robustness of the CapsNet-based method is better than the benchmark methods.

Non-line-of-sight (NLOS) propagation is one of the key challenges in radio positioning. Significant attentions have been drawn to the identification and mitigation of the NLOS in recent years. This paper focuses on the identification of NLOS signals based on the feature attached to the signals themselves. We propose a novel NLOS identification technique employing K-Means Clustering (KMC) and kernel KMC methods, which are two of the most popular techniques in the field of data mining. Our work is based on the fact that the features used, i.e., the kurtosis, the mean excess delay spread, and the root-mean-square delay spread are well modeled by log-normal random variables. Numerical simulations are performed to demonstrate the validity of the methodology.

For a wireless location network using ultra-wideband signals, the positioning accuracy of the network is affected by the transmission power of the anchors when the power resources are limited. The square position error bound is introduced as the standard of the positioning accuracy of the network, and a functional model of the square position error bound of the network and the transmission power of the anchors is established. Based on this model, a power optimization allocation algorithm based on cooperative game was proposed to achieve the goal of improving positioning accuracy. Simulation results show that the algorithm reduces the square position error bound of the network, which effectively improves the positioning accuracy.