Radio maps can enhance the capability of wireless sensor networks and improve the efficiency of spectrum utilization. However, the construction of an accurate radio map in the urban environment is a challenging task, since the dense buildings lead to a non-line-of-sight (NLOS) transmission environment. With this focus, we first transform the spatial sparse measurement points into a graph structure and extract the connected relation through the building map. Then, we propose a graph neural network (GNN) scheme to recover the complete radio map from sparse measurements. Numerical results show that our algorithm outperforms the benchmark methods in accuracy and is robust to noise.

This paper proposes a restricted weighted k-nearest neighbor algorithm (RWKNN) specific for indoor environments. The traditional WKNN method determines the locations by calculating the difference between the current received signal strength (RSS) and fingerprint RSS. However, the limitations of the traditional WKNN positioning method include RSS instability and spatial ambiguity. With this focus, the proposed RWKNN considers indoor moving constraints and uses searching rectangular and trajectory restriction to reduce spatial ambiguity. In addition, to mitigate the effects of RSS instability on the iteration-based method, a confidence number is introduced. Through simulation of office environments, field experiments, and verification based on public datasets, numerical results show the superiority and effectiveness of the proposed RWKNN over other constraint-based algorithms in terms of robustness and accuracy. Specifically, RWKNN outperformed the traditional WKNN method by 43% and 20% in the simulation and field experiment tests respectively, and by 22% on the Tampere open dataset.

Accurate radio environment maps (REMs) can enhance the performance of wireless networks and optimize spectrum utilization efficiency. However, in rugged terrain environments, radio propagation is significantly affected by terrain variations, resulting in spatial heterogeneity in received signal strength (RSS) and impairing the accuracy of REM construction. To address these challenges, a Gaussian Process Regression method incorporating terrain (GPRT) is proposed to exploit both spatial and terrain correlation properties. In GPRT, a specialized kernel function is designed to integrate digital elevation data into the Gaussian process framework, capturing anisotropic spatial correlation and terrain effects. In addition, an Adaptive Moment Estimation (Adam) optimization algorithm is utilized for efficient hyperparameter tuning, enhancing convergence speed and parameter accuracy. Simulations with varying numbers of emitters and field experiments in real-world terrain demonstrate the superiority and effectiveness of the proposed GPRT over competing methods in terms of robustness and accuracy. Specifically, GPRT outperformed the best comparative approaches by 20% to 33% in simulations and by up to 20% in the field experiment.

Accurate context awareness of land vehicles can assist integrated navigation systems. Motion behavior recognition is one context awareness of vehicles, based on which constraint information helps reduce the impact of short-term blockage of navigation signals on radio-frequency-based positioning systems. To improve the reliability of behavior recognition, we proposed a machine learning-based vehicle motion behavior recognition and constraint method (MLMRC). The machine learning-based recognition process is directly driven by raw data from low-cost MEMS-IMU, while the traditional threshold-based method relies on previous experience. Four categories of constraint information—sensor error calibration, velocity constraint, angle constraint, and position constraint—were constructed from the recognition results. Both the simulated vehicle experiment and real vehicle experiment demonstrate the performance of the MLMRC method. When there is a short-term blockage, the MLMRC method can reduce the positioning error from 17.2% to 38.3% compared with the traditional method, which effectively improves positioning accuracy and provides support for autonomous vehicles in complex urban environments.