Analysis of Machine Learning-Based NLOS Signal Identification Algorithm for UWB Indoor Localization Using CIR Waveform Features

In Ultra-Wide Band (UWB) positioning, wireless signals are subject to non-line-of-sight (NLOS) propagation due to obstruction by obstacles, which leads to ranging and positioning estimation errors. How to accurately and efficiently identify line-of-sight (LOS) and NLOS propagation paths is a key research task in UWB positioning systems. By effectively integrating the characteristics of global channel impulse response (CIR) sequence features and statistical time-domain features, a dual-branch feature fusion Transformer (DBFF-Transformer) is proposed for NLOS path identification. Firstly, the original CIR sequence data is processed using the Transformer to learn the global feature relationships within the data. Secondly, four key time-domain features are extracted from the CIR sequence: the first-path energy ratio, the root-mean-square time delay spread, the kurtosis and the phase difference. Finally, by integrating the sequence features and the time-domain features, the two features’ branches are fused through a fully connected network. The proposed method is evaluated in two typical indoor scenarios from the latest open-source datasets of the eWINE project. The ablation experiment proves that the fusion of the sequence features and time-domain features of the CIR sequence can effectively improve NLOS identification accuracy. The identification accuracy in the two experimental scenarios is 95.9% and 95.7%, with F1 scores of 97.2% and 97.1% and Recall of 97.4% and 96.4%, respectively. The comparative analysis of the DBFF-Transformer with the state-of-the-art baseline models demonstrates superior accuracy and robustness, which can provide a novel solution for NLOS identification in UWB indoor positioning.

The error compensation and suppression effects of traditional ultrawideband (UWB) ranging in non Line of Sight (NLOS) environments are limited. The contribution of specific occlusions to UWB spatial perception in NLOS is ignored. To achieve comprehensive sensing of spatial information by UWB, we initially analyze the channel impulse response (CIR) and the underlying parameters of registers during UWB communication. By comparing the difference between NLOS and line-of-sight (LOS) environments for each parameter on a continuous time series, a fast discriminative method for UWB environment conversion is proposed. Further, combining the ensemble learning XGBoost classifier, an efficient NLOS occlusion recognition method is proposed. At the same time, an algorithm optimization based on a discrete degree threshold is designed. It is based on loss function probability matrix-weighted predictive labeling. The prediction matrix of the loss function of the XGBoost algorithm is used as label weights. The UWB prediction labels of continuous time series are weighted, which mitigates the effect of low-probability data on the overall prediction results. Finally, UWB spatial sensing experiments are carried out to verify the reliability of the proposed method. The experimental results show that the mutation in the parameter profile can effectively perceive the LOS/NLOS transition. The recognition accuracy of the proposed occlusion recognition method in conditions of human, metal, and wall occlusion is 94.44%, 92.00%, and 95.87%, respectively. In contrast to the origin method, the suggested algorithm’s average recognition accuracy has increased by 16.71%. Its precise recognition accuracy makes UWB spatial sensing more effective.

With the booming demand of indoor position information, Wireless signals (Wi-Fi, Bluetooth, Ultra-Wide-Band etc.) are investigated to construct Indoor Positioning System (IPS). Among these wireless signals, UWB (Ultra-Wide-Band) is recognized as the most promising technology to construct IPS with decimeter-level positioning accuracy. However, there are various objects in indoor environments, UWB signals might be reflected by these surrounding objects. These None-Line-Of-Sight (NLOS) signals will induce additional errors to the distance measurements between the anchor and agent. Therefore, NLOS/LOS (Line-Of-Sight) signals classification should be carried out for identifying the NLOS reception. In UWB based IPS, the distance information is extracted through the Channel Impulse Response (CIR) waveforms. NLOS reception will lead to different CIR waveforms compared with that from the LOS signal, this difference could be characterized for NLOS/LOS signals classification. However, the hardware circuits, signal transmitting path and the NLOS reception will bring about noises to the CIR waveforms, which might influence the signal type identification. Motivated by this problem, in this letter, a reversible transformation method was proposed for de-nosing the CIR data, and a Conventional Neural Network (CNN) was employed to identify the NLOS signal. Raw and de-noised CIR dataset were both input to the CNN for assessing the effect of the de-noising method. With dataset collected from seven different sites, the results showed that the reversible transformation method was able to increase the Signal Noise Ratio (SNR) values of these CIR datasets. After the de-noising, the CNN performed higher classification accuracy with less convolutional layers. Moreover, the de-noising operation brought about higher NLOS signal identification accuracy increase than that of LOS signals.

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.

Ultra-wideband (UWB) and WiFi technologies have been widely proposed for the implementation of accurate and scalable indoor positioning systems (IPSs). Among different approaches, fingerprinting appears particularly suitable for WiFi IPSs and was also proposed for UWB IPSs, in order to cope with the decrease in accuracy of time of arrival (ToA)-based lateration schemes in the case of severe multipath and non-line-of-sight (NLoS) environments. However, so far, the two technologies have been analyzed under very different assumptions, and no fair performance comparison has been carried out. This paper fills this gap by comparing UWB- and WiFi-based fingerprinting under similar settings and scenarios by computer simulations. Two different k-nearest neighbor (kNN) algorithms are considered in the comparison: a traditional fixed k algorithm, and a novel dynamic k algorithm capable of operating on fingerprints composed of multiple location-dependent features extracted from the channel impulse response (CIR), typically made available by UWB hardware. The results show that UWB and WiFi technologies lead to a similar accuracy when a traditional algorithm using a single feature is adopted; when used in combination with the proposed dynamic k algorithm operating on channel energy and delay spread, UWB outperforms WiFi, providing higher accuracy and more degrees of freedom in the design of the system architecture.

This work proposes channel impulse response (CIR) prediction for time-varying ultra-wideband (UWB) channels by exploiting the fast movement of channel taps within delay bins. Considering the sparsity of UWB channels, we introduce a window-based CIR (WB-CIR) to approximate the high temporal resolutions of UWB channels. A recursive least square (RLS) algorithm is adopted to predict the time evolution of the WB-CIR. For predicting the future WB-CIR tap of window wk, three RLS filter coefficients are computed from the observed WB-CIRs of the left wk−1, the current wk and the right wk+1 windows. The filter coefficient with the lowest RLS error is used to predict the future WB-CIR tap. To evaluate our proposed prediction method, UWB CIRs are collected through measurement campaigns in outdoor environments considering line-of-sight (LOS) and non-line-of-sight (NLOS) scenarios. Under similar computational complexity, our proposed method provides an improvement in prediction errors of approximately 80% for LOS and 63% for NLOS scenarios compared with a conventional method.

Ultrawideband (UWB) radio frequency positioning technology has found extensive applications in indoor and outdoor localization due to its strong anti-interference capabilities, high penetration power, and precise measurement accuracy. However, its positioning accuracy significantly decreases under nonline-of-sight (NLOS) conditions, particularly in dynamic NLOS environments. Therefore, it is essential to identify NLOS propagation and mitigate its associated errors. To overcome these issues, this study proposes a novel enhanced domain-adversarial neural network for UWB signal occlusion recognition (EDANN-SOR). EDANN-SOR integrates hybrid manually extracted channel impulse response (CIR) features, effectively aligning the source and target domains and extracting discriminative and domain-invariant UWB CIR features in dynamic NLOS environments. Through adversarial learning, our method achieves high generalization with minimal CIR sample requirements, reducing the need for extensive data collection and significantly enhancing robustness in distance measurement and positioning under dynamic NLOS conditions. In contrast to state-of-the-art NLOS identification and transfer learning (TL) techniques, our method excels in both binary and multiclass NLOS classification. Specifically, it achieves an accuracy of over 97.36% in conventional LOS/NLOS binary classification across scenarios and 97.07% in multiclass classification. The integration of manually extracted features has been proved effective in improving the EDANN-SOR model’s ability to distinguish among LOS, human, and glass obstacles.

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.

In the rapidly evolving Internet of Things (IoT) landscape, accurate indoor positioning is increasingly vital. The proposed algorithm synergizes an ultrawideband (UWB) sensor with an inertial measurement unit (IMU) and artificial intelligence to obtain precise positioning in nonline-of-sight (NLOS) scenarios. In the proposed UWB module, a large language model (LLM) such as bidirectional encoder representations from transformers (BERT) algorithm is designed to utilize the channel impulse response (CIR) for effective NLOS identification and UWB ranging trustworthiness evaluation. Concurrently, the IMU module is also designed with BERT to recognize various pedestrian activity states, thereby optimizing positioning. BERT’s self-attention mechanism and deep learning (DL) bidirectional training efficiently extract essential features from sequential data, capturing both local and global information. The integration of both UWB and IMU through a proposed tightly coupled algorithm significantly boosts positioning performance. Experimental campaigns demonstrate an average NLOS identification accuracy, line-of-sight (LOS), and <inline-formula xmlns:mml="http://www.w3.org/1998/Math/MathML" xmlns:xlink="http://www.w3.org/1999/xlink"> <tex-math notation="LaTeX">${F}2$ </tex-math></inline-formula> of 98.8%, 99.4%, and 0.9926, respectively. These performances surpass the state-of-the-art least-squares support vector machine (LS-SVM), convolutional neural network (CNN), and CNN with long short-term memory (CNN-LSTM) up to 17.66% in NLOS identification. In terms of pedestrian activity recognition using BERT, the BERT algorithm achieves a precision (recall) of 99.3% (99.4%), notably outperforming the CNN and CNN-LSTM by 17.9% (16.2%) and 11.9% (10.9%), respectively. Finally, the UWB-IMU algorithm significantly enhances positioning accuracy by 80.5%, outperforming Kalman, LSTM-EKF, and particle filter (PF) methods by 68.1%, 48.3%, and 45.0%, respectively. The proposed approach presents a robust solution for indoor positioning for IoT applications, particularly in challenging NLOS environments.

At present, location technology divides into outdoor location technology and indoor location technology. Comparing with other indoor location methods, ultra-wide band (UWB)indoor location technology has the advantages of strong anti-multipath interference ability and signal penetration ability. But, when this method faces large obstacles or metal obstacles, non line of sight (NLOS) will still occur. Indoor location system is a part of our project Home Care System for The Elderly. The NLOS of Indoor location system reduces the reliability of Home Care System for The Elderly. In order to improve the accuracy of location and efficiency of operation, an NLOS detection method based on k-nearest neighbors (KNN) algorithm is proposed. This algorithm modeled the training samples to find the K value with the highest recognition accuracy. The experimental results show that The NLOS detection accuracy of this method is 78% in the simulated apartment scene. With the same number of samples, the accuracy of the widely used Convolutional Neural Networks (CNN) algorithm is 67%. The experimental results show that KNN algorithm is more suitable for Home Care System for The Elderly for it can keep high accuracy with less requirement for the number of samples than CNN.

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.

This paper considers the global localization of a pedestrian via an ultra-wideband (UWB) ranging aided inertial navigation system (INS) and aims to address the challenges involved in proper processing of UWB range measurements. Even though UWB offers a decimeter level accuracy in line-of-sight (LoS) ranging, its accuracy degrades significantly in non-line-of-sight (NLoS). This drop in accuracy is due to a significant unknown positive bias in the NLOS range measurements. Therefore, the measurement models used in UWB LoS and NLoS ranging conditions are different, and proper processing of NLoS measurements requires a bias compensation measure. Previous work on bias compensation for UWB ranging that is used to aid an INS based localization assumes that the LoS and NLoS measurements are identified and distinguished from each other with absolute certainty. However, in practice, this assumption is hard to satisfy, and identifiers that determine the type of UWB range measurements deliver their results with only some level of certainty. To take into account the probabilistic nature of the NLoS identifiers, in this paper, we propose an adaptive localization based on the first-order generalized pseudo Bayesian (GPB) method to seamlessly handle the measurement model switching between LoS and NLoS UWB range measurements. The effectiveness of our proposed method is demonstrated via an experiment for pedestrian geolocation using a shoe-mounted INS system aided by UWB range measurements with respect to beacons with known locations.

Forestry work involves scientific management and the effective utilization of forest land resources, and finding economical, efficient and accurate acquisition methods for forest land resource information. In previous land-use classification research, machine learning algorithms have achieved good results, and Sentinel public data have been used in various remote sensing applications. However, there is a paucity of research using these data to evaluate the performance of machine learning algorithms in the extracting of complex forest land resource information. Using the Sentinel-2 satellite multispectral image data, the spectral reflectance, vegetation index characteristics and image texture characteristics of different forest land resources in the study area were calculated and compared. Then, based on three groups of features, the performances of the Support Vector Machine (SVM), K-Nearest Neighbor (KNN), Random Forest (RF), decision trees (DT) and Multi-layer Perceptron (MLP) were examined and compared to identify and classify forest land resource types. The research indicates the following: (1) The SVM algorithm achieved the highest OA (95.8%). The average accuracy of the SVM algorithm was much higher than other algorithms (SVM 88.3%, KNN 87.5, RF 85.3%, MLP 85.00% and DT 77.5%). (2) The classification accuracies of each algorithm for coniferous forests were relatively high, and the recognition accuracy was above 95%, whereas the classification accuracies of the other categories varied greatly. (3) Adding texture features can improve the accuracy of the five algorithms. This study reports new references for the qualitative methods of forest land resource distribution. It has also produced more efficient and accurate acquisitions of forest land resource information, scientific management and effective use of forest land resources.

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.

Ultra-Wide-Band (UWB) ranging sensors have been widely adopted for robotic navigation thanks to their extremely high bandwidth and hence high resolution. However, off-the-shelf devices may output ranges with significant errors in cluttered, severe non-line-of-sight (NLOS) environments. Recently, neural networks have been actively studied to improve the ranging accuracy of UWB sensors using the channel-impulse-response (CIR) as input. However, previous works have not systematically evaluated the efficacy of various packet types and their possible combinations in a two-way-ranging transaction, including poll, response and final packets. In this paper, we firstly investigate the utility of different packet types and their combinations when used as input for a neural network. Secondly, we propose two novel data-driven approaches, namely FMCIR and WMCIR, that leverage two-sided CIRs for efficient UWB error mitigation. Our approaches outperform state-of-the-art by a significant margin, further reducing range errors up to 45%. Finally, we create and release a dataset of transaction-level synchronized CIRs (each sample consists of the CIR of the poll, response and final packets), which will enable further studies in this area.