With the increasing demand of location-based services, channel state information (CSI) has attracted great interest because of the fine-grained information it provides. In this paper, we propose an original network structure, which exploits both the local information and global information in CSI amplitude for fingerprint localization. First, we validate the correlation between adjacent subcarriers and introduce the position-dependent local feature (PDL-feature). Next, local connection based deep neural network (LC-DNN) is designed to improve positioning performance by extracting and exploiting the correlation between adjacent subcarriers for indoor localization. LC-DNN consists of locally-connected layer and fully-connected layer. In the locally-connected layer, the variation of CSI amplitude in local frequency range is extracted and spliced for rich information. The frequency range and the times of extraction are determined by receptive field length and step size respectively. In the fully-connected layer, not only global features of CSI amplitude are further extracted, but also the function between features and position coordinates is obtained. Experiments are conducted to validate the effectiveness of LC-DNN and investigate the influence of hyper parameters on localization. Moreover, the positioning performance of LC-DNN is compared with four methods based on deep neural networks (DNNs). Results show that LC-DNN performs well in positioning accuracy and stability, with the mean error of 0.78m.

Indoor positioning and navigation is an essential field of location-based service. Non-line of sight (NLOS) error restricts the accuracy of indoor positioning. Many researchers have studied the localization problem in indoor NLOS environments, but there is still a problem that NLOS error cannot be mitigated in unknown areas. To solve the above problems, this paper proposes a method of constructing virtual base stations in unknown areas (UA-VBS), and presents the corresponding positioning algorithm to calculate the location of the user equipment. Firstly, the base stations are selected and the initial positioning is carried out. Then, multiple virtual base stations are constructed according to the user equipment positions in the first three steps. The LOS base stations and virtual base stations participate in the TDOA calculation together, and calculate the base stations’ combination with the minimum residual and the corresponding positioning result. Finally, the pedestrian dead reckoning fusion weight is updated by the residual value, and the accurate positioning result in NLOS environment is obtained. Simulation and experimental results show that the proposed algorithm has high positioning accuracy and stability in NLOS environment.

The fingerprint positioning has achieved remarkable results in indoor localization tasks, but the method usually relies on a large amount of fingerprint data to build a fingerprint database, and the amount and diversity of fingerprint data will directly affect the effectiveness of fingerprint positioning. Since fingerprint acquisition is limited and disturbed by space and time, it consumes a lot of labor and time costs to collect fingerprint data in the localization environment, and wireless fingerprint data is time-sensitive and environment-dependent, and changes in the localization environment will reduce the usability of the existing fingerprint database. The complex and repetitive fingerprint acquisition work seriously affects the feasibility of practical deployment of fingerprint positioning systems in the positioning environment. Therefore, the study of low-cost wireless fingerprint database construction methods has become an inevitable part of promoting the widespread deployment of indoor fingerprint positioning systems. In this paper, we introduce the traditional data augmentation-based approach and the advanced machine learning model-based approach, systematically presenting the underlying models and algorithms of both. The former reviews the application of two traditional data enhancement methods, namely channel propagation models and interpolation or regression, to the construction of low-cost wireless fingerprint databases, while the latter taps into techniques for reducing the cost of fingerprint database construction by combining generative adversarial networks and small-sample learning models with the indoor localization domain. Finally, we discuss the current challenges and future research directions for achieving high-performance indoor localization based on low-cost wireless fingerprint databases, and suggest some useful research guidelines.

Channel state information (CSI) provides a fine-grained description of the signal propagation process, which has attracted extensive attention in the field of indoor positioning. The CSI signals collected by different fingerprint points have a high degree of discrimination due to the influence of multi-path effects. This multi-path effect is reflected in the correlation between subcarriers and antennas. However, in mining such correlations, previous methods are difficult to aggregate non-adjacent features, resulting in insufficient multi-path information extraction. In addition, the existence of the multi-path effect makes the relationship between the original CSI signal and the distance not obvious, and it is easy to cause mismatching of long-distance points. Therefore, this paper proposes an indoor localization algorithm that combines the multi-head self-attention mechanism and effective CSI (MHSA-EC). This algorithm is used to solve the problem where it is difficult for traditional algorithms to effectively aggregate long-distance CSI features and mismatches of long-distance points. This paper verifies the stability and accuracy of MHSA-EC positioning through a large number of experiments. The average positioning error of MHSA-EC is 0.71 m in the comprehensive office and 0.64 m in the laboratory.

Vehicle positioning with 5G can effectively compensate for the lack of vehicle positioning based on GNSS (Global Navigation Satellite System) in urban canyons. However, there is also a large ranging error in the non-line of sight (NLOS) propagation of 5G. Aiming to solve this problem, we consider a new time delay estimation algorithm called non-line of sight cancellation multiple signal classification (NC-MUSIC). This algorithm uses cross-correlation to identify and cancel the NLOS signal. Then, an unsupervised multipath estimation method is used to estimate the number of multipaths and extract the noise subspace. The MUSIC spectral function can be calculated by the noise subspace. Finally, the time delay of the direct path is estimated by searching the peak of MUSIC spectral function. This paper adopts the 5G channel model developed by 3GPP TR38.901 for simulation experiments. The experiment results demonstrated that the proposed algorithm has obvious advantages in terms of NLOS propagation for urban canyon environments. It provided a high-precision time delay estimation algorithm for observed time difference of arrival (OTDOA), joint angle of arrival (AOA) ranging, and other positioning methods in the 5G vehicle positioning method, which can effectively improve the positioning accuracy of 5G vehicle positioning in urban canyon environments.

Indoor positioning technologies has boomed recently because of the growing commercial interest in indoor location-based service (ILBS). Due to the absence of satellite signal in Global Navigation Satellite System (GNSS), various technologies have been proposed for indoor applications. Among them, Wi-Fi fingerprinting has been attracting much interest from researchers because of its pervasive deployment, flexibility and robustness to dense cluttered indoor environments. One challenge, however, is the deployment of Access Points (AP), which would bring a significant influence on the system positioning accuracy. This paper concentrates on WLAN based fingerprinting indoor location by analyzing the AP deployment influence, and studying the advantages of coordinate-based clustering compared to traditional RSS-based clustering. A coordinate-based clustering method for indoor fingerprinting location, named Smallest-Enclosing-Circle-based (SEC), is then proposed aiming at reducing the positioning error lying in the AP deployment and improving robustness to dense cluttered environments. All measurements are conducted in indoor public areas, such as the National Center For the Performing Arts (as Test-bed 1) and the XiDan Joy City (Floors 1 and 2, as Test-bed 2), and results show that SEC clustering algorithm can improve system positioning accuracy by about 32.7% for Test-bed 1, 71.7% for Test-bed 2 Floor 1 and 73.7% for Test-bed 2 Floor 2 compared with traditional RSS-based clustering algorithms such as K-means.