A Self-Attention Mechanism based NLOS Discrimination Method for B5G network

In urban areas, signal reception conditions are often poor due to reflections from buildings, resulting in inaccurate global navigation satellite system (GNSS)-based positioning. Various 3D-mapping-aided (3DMA) GNSS techniques, including shadow matching, have been proposed to address this issue. However, conventional shadow matching estimates positions in a discretized manner. The accuracy of this approach is limited by the resolution of the grid points representing the candidate receiver positions, making it difficult to achieve robust urban positioning and to ensure that the position estimate satisfies user-specified protection levels or safety bounds. To overcome these limitations, zonotope shadow matching (ZSM) has been proposed, which utilizes a set-based position estimate rather than grid-based estimates. ZSM calculates the GNSS shadow—an area on the ground where the line-of-sight (LOS) is blocked and only non-line-of-sight (NLOS) signals can be received—to estimate the receiver’s position set. ZSM distinguishes between LOS and NLOS satellites, determining that the receiver is inside the GNSS shadow if the satellite is NLOS and outside if the satellite is LOS. However, relying solely on GNSS shadows limits the ability to sufficiently reduce the size of the receiver position set and to precisely estimate the receiver’s location. To address this, we propose zonotope shadow and reflection matching (ZSRM) to enhance positioning accuracy in urban areas. ZSRM incorporates both GNSS shadows and GNSS reflections to estimate the receiver’s position. A GNSS reflection is defined as an area on the ground where both LOS and NLOS signals are received simultaneously. Unlike ZSM, ZSRM classifies satellites into three types: LOS-only, LOS + NLOS, and NLOS-only. Based on this classification, the receiver’s position is determined in one of three ways: inside the GNSS shadow (if NLOS-only), inside the GNSS reflection (if LOS + NLOS), or outside both areas (if LOS-only). Using this framework, ZSRM can estimate the receiver’s position more precisely than ZSM. The proposed ZSRM technique is validated through field tests using GNSS signals collected in an urban environment. Consequently, the RMS horizontal position error of ZSRM improved by 10.0% to 53.6% compared with ZSM, while the RMS cross-street and along-street position bounds improved by 18.0% to 50.1% and 30.7% to 59.3%, respectively.

Urban environments present major challenges to the global navigation satellite system (GNSS) positioning to estimate the position of a self-driving vehicle. GNSS signals are often obstructed by buildings and other obstacles, leading to reflected and diffracted signals, which cause major positioning errors and known as line-of-sight (LOS) and non-line-of-sight (NLOS) multipath errors. Particularly, real-time kinematic (RTK)-GNSS, which can estimate the position in the centimeter-level accuracy, cannot estimate the precise position when there exist NLOS multipath errors. If we use NLOS GNSS code and carrier phase multipath measurements into the RTK-GNSS algorithm, carrier phase integer ambiguity cannot be solved, or wrong integer ambiguities are estimated. As a result, integer ambiguity resolved to fix solutions cannot be estimated, or wrong fix solutions which have large position error are estimated. That is a major barrier to using RTK-GNSS in autonomous driving. In this paper, we propose a novel NLOS detection and exclusion technique to enhance existing RTK-GNSS positioning in urban areas using only GNSS measurements alone. The key idea behind the proposed technique is that the NLOS pseudorange error will always be a positive value. NLOS pseudorange is longer than the true range, which is the distance between the GNSS antenna and satellite, due to the time delay caused by reflection and diffraction. The distribution of the NLOS error is not along with a Gaussian distribution. We use this phenomenon to detect the NLOS signals. We propose a technique to detect and eliminate the NLOS multipath using double-differenced pseudorange residuals (DD-PR). In the RTK-GNSS, DD GNSS measurement between the rover and base station is typically used. Here, we compute the DD-PR to detect the NLOS signals. In order to compute the DD-PR, the true position of the vehicle must be determined in advance. To solve this contradiction, we use a particle filter. The particle filter generates the position hypotheses, which is called as “particle”. These particles are used as the position candidate for estimating the DD-PR. When the DD-PR can be calculated at each particle position, we detect the large positive errors in DD-PR as NLOS signals. Then we compute the integer ambiguity of only the LOS DD carrier phase to estimate the precise vehicle position. The flow of the proposed technique is as follows: (1) The hypothetical user positions are created as particles, where the state vectors of these particles are 3D positions, x, y, and z. The initial particles are distributed based on the solution of the normal GNSS point positioning and its variance. (2) In the prediction step of the particle filter, the particle state in the next time step is estimated using the velocity of each particle computed from GNSS Doppler measurements. (3) Next, we compute the DD-PR at each particle location. The receiver clock bias, satellite clock bias, ionosphere error, and troposphere error in GNSS pseudorange are canceled through DD computation. As a result, DD geometrical range between receiver and satellite and DD multipath errors remain in the DD measurement. We compute DD-PR using the particle position. As a result, the only multipath error remains if the particle is close to the true position. NLOS multipath error is always positive value; we generate the subset of the LOS measurement hypothesis at each particle using a simple threshold test. (4) Next, we compute the RTK-GNSS position solution using the generated subset of the LOS measurement hypothesis at each particle location. It is expected that the RTK-GNSS fix solution can be calculated if the particle location is close to the true position because the NLOS signal has been eliminated. By contrast, if the particle is far from true position, the integer ambiguity cannot be solved because of using the incorrect subset of LOS measurements. The likelihood of each particle is computed from a distance between the particle location and the RTK-GNSS fix solution. The particle that is closest to the true position has a higher likelihood than the other particles. The probabilistic weight of each particle is then updated based on its likelihood. (5) Finally, all the particles are resampled based on their new weights. Particles that are sufficiently close to the true position survive this resampling step, and the average position of the remaining particles are employed as the final estimated user position. To confirm the effectiveness of the proposed technique, a kinematic positioning test was performed in Shinjuku, Tokyo, Japan. From the several positioning tests, the proposed technique could dramatically improve the availability and accuracy of RTK-GNSS fix solutions in the dense urban canyon where there exist a lot of NLOS multipath signals.

Infants and children with respiratory conditions are often prescribed bronchodilators. Face masks are used to facilitate the administration of nebulized therapy in patients unable to use a mouthpiece. Masks incorporate holes into their design, and their occlusion during aerosol delivery has been a common practice. Masks are available in different sizes and different dead volumes. The aim of this study was to compare the effect of different degrees of occlusion of the mask holes and different mask dead space on the amount of nebulized albuterol available at the mouth opening in a model of a spontaneously breathing child. A breathing simulator mimicking infant (tidal volume [VT] = 50 mL, breathing frequency = 30 breaths/min, inspiratory-expiratory ratio [I:E] = 1:3), child (VT = 155 mL, breathing frequency = 25 breaths/min, I:E = 1:2), and adult (VT = 500 mL, breathing frequency = 15 breaths/min, I:E = 1:2) breathing patterns was connected to a collection filter hidden behind a face plate. A pediatric size mask and an adult size mask connected to a continuous output jet nebulizer were sealed to the face plate. Three nebulizers were loaded with albuterol sulfate (2.5 mg/3 mL) and operated with 6 L/min compressed air for 5 min. Experiments were repeated with different degrees of occlusion (0%, 50%, and 90%). Albuterol was extracted from the filter and measured with a spectrophotometer at 276 nm. Occlusion of the holes in the large mask did not increase the amount of albuterol in any of the breathing patterns. The amount of albuterol captured at the mouth opening did not change when the small mask was switched to the large mask, except with the breathing pattern of a child, and when the holes in the mask were 50% occluded (P = .02). Neither decreasing the dead space of the mask nor occluding the mask holes increased the amount of nebulized albuterol captured at the mouth opening.

Abstract. Ultra-wideband (UWB) technology stands out among numerous indoor positioning techniques due to its high operating frequency, low interception capability, resistance to multipath effects, and strong penetration. The UWB uses the time-of-arrival (TOA) to estimate the distance between the transmitter and receiver anchors in centimeter accuracy. However, in complex indoor positioning environments, obstacles such as walls, glass windows, metal plates, and wooden doors may block and reflect signals, inevitably causing non-line-of-sight (NLOS) errors that significantly affect positioning accuracy. The NLOS signal has lower signal energy due to the reflections. Thus, the channel impulse responses (CIR) from NLOS and LOS are different. To address the NLOS signal identification issue in UWB positioning, we utilize UWB CIR data collected from various positioning scenarios as the data source. CIR waveform input features are provided for the NLOS signal recognition model, and four machine learning models—Support Vector Machine (SVM), Multi-Layer Perceptron (MLP), K-Nearest Neighbors (KNN), and XGBoost—are trained and optimized for NLOS signal recognition. The aim of the study is to analyze the performance of different machine learning algorithms for NLOS signal recognition in UWB indoor localization using these features. Experimental results indicate that machine learning-based NLOS signal recognition algorithms can achieve an accuracy of approximately 77.46%, precision of 80.46%, and an F1 score of 0.81. Among the four models, the XGBoost model demonstrates generally better recognition performance.

At present, the satellite navigation and positioning system can provide a high precision positioning service to end users in outdoor environments. But in urban canyons, high-rise buildings, urban tunnels, tree canopy covered areas, and other environments with weak signal such as military base and other special places with signal disturbance or spoofery, effective positioning or positioning results cannot to be trusted. Hence, it is very important and meaningful to use the existing radio signals ("signal of opportunity") in the environment for positioning. Among the existing types of signals, mobile communication signals have more obvious characteristics for signal of opportunity navigation and thus has received more attention. This paper aims to solve the problem of signal selection in the application of mobile communication signals to navigation and positioning. This done by using characteristics such as signal carrier frequency, received signal strength and geometric position distribution to model, evaluate and systematically analyze the influence of each factor on positioning performance. Finally, based on a comprehensive evaluation method, a signal selection algorithm is designed while putting the signal type, signal carrier frequency, received signal strength, geometric position of the signal source and other factors into consideration. GSM and LTE signals are used in an actual environment to analyze, verify and extract the parameters required for the selection algorithm, also a comparative verification analysis was carried out with cluster and sub-optimal selection algorithm. The positioning accuracy of the proposed model proves both the reliability and the effectiveness of the proposed algorithm for comprehensive evaluation of signal source selection.

Non-Line-of-Sight (NLoS) propagation condition is a crucial factor affecting the precision of the localization in the Ultra-Wideband (UWB) Indoor Positioning System (IPS). Numerous supervised Machine Learning (ML) approaches have been applied for NLoS identification to improve the accuracy of the IPS. However, it is difficult for existing ML approaches to maintain a high classification accuracy when the database contains a small number of NLoS signals and a large number of Line-of-Sight (LoS) signals. The inaccurate localization of the target node caused by this small number of NLoS signals can still be problematic. To solve this issue, we propose feature-based Gaussian Distribution (GD) and Generalized Gaussian Distribution (GGD) NLoS detection algorithms. By employing our detection algorithm for the imbalanced dataset, a classification accuracy of $96.7\%$ and $98.0\%$ can be achieved. We also compared the proposed algorithm with the existing cutting-edge such as Support-Vector-Machine (SVM), Decision Tree (DT), Naive Bayes (NB), and Neural Network (NN), which can achieve an accuracy of $92.6\%$, $92.8\%$, $93.2\%$, and $95.5\%$, respectively. The results demonstrate that the GGD algorithm can achieve high classification accuracy with the imbalanced dataset. Finally, the proposed algorithm can also achieve a higher classification accuracy for different ratios of LoS and NLoS signals which proves the robustness and effectiveness of the proposed method.

Observational ergonomic postural assessment methods have been used to evaluate the risks of musculoskeletal disorders. Recently, researchers have actively proposed semiautomatic approaches using motion capture data. This study compared joint angle measurements from optical, inertial, and depth-based motion capture systems, especially for cases with occlusions. Participants performed 6 static postures with different degrees of occlusion while capturing motion data by three motion capture systems. Results showed that the joint angle difference between the three systems was acceptably low in general, but the difference between Kinect and the other two systems was larger, especially in cases with occlusions. The findings indicate that the Kinect-based system is less stable than optical and inertial-based motion capture systems, but it can be used for ergonomic postural assessments in the environment without severe occlusions.

To solve object detection issues in the field of surveillance video, including a low recognition rate and a high false alarm rate caused by the great change of scale and different degrees of occlusion, we propose a multiscale pedestrian detection method. A Res-spp module based on residual structure is proposed to fuse the local and global features of objects after the backbone network. Besides, the CIOU_LOSS is employed as an object box position loss to promote the stability of the object’s bounding boxes regression. In addition, we make a neck structure that involves Weight_Conat mechanism designed for cross-layer multiscale feature fusion connection, which is based on learnable weights. It aims to strengthen the capability of network multiscale feature integration. Experimental results on VOC pedestrian dataset and widerperson dataset not only show the accuracy of the proposed method, 87.9% and 86.69% respectively, but also demonstrates a noticeable effect on the improvement of transformation of different scale and the occlusion problem of pedestrians.

In complicated urban environments, Global Navigation Satellite System (GNSS) signals are frequently affected by building reflection or refraction, resulting in Non-Line-of-Sight (NLOS) errors. In severe cases, NLOS errors can cause a ranging error of hundreds of meters, which has a substantial impact on the precision and dependability of GNSS positioning. To address this problem, we propose a reliable NLOS error identification method based on the Light Gradient Boosting Machine (LightGBM), which is driven by multiple features of GNSS signals. The sample data are first labeled using a fisheye camera to classify the signals from visible satellites as Line-of-Sight (LOS) or NLOS signals. We then analyzed the sample data to determine the correlation among multiple features, such as the signal-to-noise ratio, elevation angle, pseudorange consistency, phase consistency, Code Minus Carrier, and Multi-Path combined observations. Finally, we introduce the LightGBM model to establish an effective correlation between signal features and satellite visibility and adopt a multifeature-driven scheme to achieve reliable identification of NLOSs. The test results show that the proposed method is superior to other methods such as Extreme Gradient Boosting (XGBoost), in terms of accuracy and usability. The model demonstrates a potential classification accuracy of approximately 90% with minimal time consumption. Furthermore, the Standard Point Positioning results after excluding NLOSs show the Root Mean Squares are improved by 47.82%, 56.68%, and 36.68% in the east, north, and up directions, respectively, and the overall positioning performance is significantly improved.

For an indoor localization system based on visible light communication (VLC) by using received signal strength technique, visible light signals used for estimating the distances between each localization target and reference nodes suffer from non-line-of-sight (NLoS) signal propagation, which could introduce large errors in estimating their locations. Both line-of-sight (LoS) link and NLoS link are taken into account in a noisy VLC channel, and thus the NLoS signal and ambient noise are the sources of localization error. Ricean K factor is introduced to evaluate the relation between the value of NLoS signal and the quality of localization in the proposed system. Analytical expressions for the distance measurement error and the upper bound of localization error are derived by using the least squares method. The simulation results show that the estimation of localization error matches the distribution of Ricean K factor in the noisy overall link. The environmental parameters that can be used to decrease the value of Ricean K factor are also discussed in the simulations, which provide the reference of parameters for building an experimental demonstration of a VLC indoor localization system. A comparison is conducted with the previous works to demonstrate the good performance of our scheme.

At present, people spend most of their time indoors, so it is necessary to study high-precision positioning. Ultra wide band (UWB) can obtain the ranging accuracy with centimeter-level error. However, since the indoor environment is more complex than the outdoor environment, positioning errors tend to be generated during the UWB positioning due to the influence of non-line of sight (NLOS). Therefore, this paper investigates how to identify the NLOS environment and reduce the NLOS error. This paper proposes a method to determine the line of sight (LOS) environment credibility and uses it to determine the NLOS environment. The data with NLOS error is determined according to the standard deviation of the residual between the square of the predicted ranging value and the square of the measured ranging value. Then the data with NLOS error is compensated by complementary filtering. Finally, the compensated measurement data and the optimal estimation of the state at the previous moment are imported into the Kalman filter (KF) to determine the optimal estimation at the current moment.

With the rise of the Internet of Things and smart cities, indoor positioning technology becomes more and more important. Among the existing network technologies, ultra-wide band (UWB) has the advantages of high transmission rate, and strong penetration ability. However, its signal propagation is susceptible to N on- Line-of-Sight (NLOS) effects. Therefore, this paper focuses on indoor positioning in NLOS environments, and studies the Chan-Taylor co-weighted positioning algorithm improved by machine learning. The main research contents include: 1. A machine learning method is proposed to identify and classify NLOS signals. Using a sliding window to dynamically calculate the variance and mean of multiple groups of TDOA measurements in a short period of time as the input to the recognition algorithm, and classify them into three categories: Line-of-Sight (LOS), low NLOS error, and high NLOS error. 2. Based on the Chan- Taylor co-location algorithm, the algorithm introduces the concept of weighting coefficient, optimizes the observation data, and finally obtains the target position coordinates. The simulation results show that the positioning accuracy and system stability of the algorithm are improved compared with the Chan algorithm and the Chan-Taylor co-location algorithm.

Previous work shows that Average Bit Error Probability (ABEP) of SM systems under Non Line of Sight (NLOS) scenario is lower than that under Line of Sight (LOS) scenario because of a lower spatial correlation with a given Signal to Noise Ratio (SNR). However, when transmit power is constrained as a constant, the SNR under LOS scenario is larger than that under NLOS scenario benefiting from the strong LOS ray. Spatial correlation and SNR are two contradictory factors which both impact the performance of SM systems. In order to analyze performances of SM systems with a constant power under LOS and NLOS indoor scenarios, 15150 complex MIMO channel matrices are measured in a typical building of Shenzhen Graduate School, Harbin Institute of Technology. Based on measured data and motivated by the Minimum Distance Lower Bound (MDLB) approach, Euclid distances between received symbols of SM systems, as a monotonic function of ABEP, is analyzed. It is found that the effect of the SNR is much more important than the spatial correlation in the indoor environment so that SM system under LOS scenario shows a better performance than NLOS when the transmitting power is a constant. Furthermore, it is observed that bottlenecks of ABEP under LOS and NLOS scenarios are different. Under the LOS scenario, the bottleneck of ABEP is the antenna index error. On the contrary, under the NLOS scenario, the bottleneck of ABEP is the joint error. Using two extreme cases, such phenomena is analytically explained in the paper.

The indoor positioning technology is based on the hotpots of location based services (LBS). However, most indoor positioning systems are two-dimensional and couldn’t meet the requirements of today’s LBS. The complex indoor structures and environment determine the floor positioning rather than the altitude positioning in the vertical direction, so the floor identification is the key to three-dimensional indoor positioning systems. There are many restrictions for the existing floor identification methods based on barometer or inertial sensor. They need to get the comparable data in advance, or detect the test data changes in a certain period of time for accurate identification. The current floor identification methods based on ordinary Wi-Fi fingerprints are less effective in the complex environment. Therefore, a new floor identification method based on confidence interval of Wi-Fi signals was developed in this paper, which was divided into the offline stage and the online stage. In the offline stage, the dynamic Wi-Fi signal sequences were collected fast. Then, the adaptive partitioning of Wi-Fi signal intervals was carried out according to RSSI distribution characteristics in the multi-floor environment. Finally, the confidence levels were calculated and the database of fingerprints was constructed. In the online stage, the matching between the test fingerprints and those in the database was applied to obtain the confidence of APs on each floor monitored by the test fingerprints. The sums of the confidence of APs on each floor were calculated, and the floor corresponding to the maximum value was judged as the target floor. To verify the performance of the proposed method, it was compared with the majority voting committees, K-means, Naive Bayes and KNN methods. The results indicate that it was better than other methods in large complex indoor scenes. Its identification accuracy rate was 92.2% and the error rate was 7.8% only one floor away. Moreover, it also could significantly reduce the size of the fingerprint database and further improve the efficiency of algorithm.

Non-line-of-sight (NLOS) propagation poses a significant challenge to achieving high-accuracy ultra-wideband (UWB) indoor positioning. To address this issue, this study investigates solutions from two complementary perspectives: NLOS identification and error mitigation. First, an NLOS signal classification model is proposed based on multidimensional statistics of the channel impulse response (CIR). The model incorporates an attention mechanism and an improved snake optimization (ISO) algorithm, achieving significantly enhanced classification accuracy and robustness. Building on this foundation, a UKF–BiLSTM dual-directional mutual calibration framework is proposed to compensate for NLOS errors dynamically. The framework embeds the constant turn rate and velocity (CTRV) motion model within an unscented Kalman filter (UKF) to enhance trajectory modeling. It establishes a bidirectional correction loop with a bidirectional long short-term memory (BiLSTM) network. Through the synergy of physical constraints and data-driven learning, the framework adaptively suppresses NLOS errors. Experimental results demonstrate that the proposed classification model and positioning framework significantly outperform state-of-the-art methods, thereby providing a systematic solution for high-precision and robust UWB positioning in complex indoor environments.