Average Localization Error Research Articles

Optimizing federated learning approaches with hybrid Convolutional Neural Networks ‐ Bidirectional Encoder Representations from Transformers for precise estimation of average localization errors in wireless sensor networks

SummaryWireless sensor networks (WSNs) require precise node location in order to function properly, and they are essential in many different applications. In this research, we propose a unique method to maximize the accurate estimate of average localization errors (ALEs) in WSNs by utilizing federated learning (FL) approaches. The suggested approach combines the extraction of spatial features with collection of contextual data through integration of hybrid convolutional neural network–bidirectional encoder representations from transformers (CNN‐BERT) model. Effectively applying min–max normalization to input features minimizes data from flowing into test, validation, and training sets. The technique is centered around a collaborative learning architecture, wherein the weights of the model are iteratively assessed and modified on centralized server. The suggested methodology's effectiveness in an array of settings is illustrated by mean absolute error (MAE), mean squared error (MSE), and root mean square error (RMSE) values for node localization in WSN. Network B demonstrated accuracy with an MAE of 0.05, MSE of 0.03, and RMSE of 0.10; Network C demonstrated strong accuracy with an MAE of 0.09, MSE of 0.08, and RMSE of 0.12; and Network A generated an MAE of 0.04, MSE of 0.06, and RMSE of 0.08. Furthermore, the centralized server, which is crucial for collaborative learning, obtained exceptional MAE of 0.01, MSE of 0.02, and RMSE of 0.99 demonstrating the superiority of the FL‐optimized method in improving localization accuracy. The outcomes demonstrate the FL‐optimized hybrid model's superiority over conventional methods in providing accurate node localization in a variety of WSN settings.

Accurate digitization of EEG electrode locations by electromagnetic tracking system: The proposed head rotation method and comparison against optical system

Electroencephalogram (EEG) electrode digitization is crucial for accurate EEG source estimation, and several commercial systems are available for this purpose. The present study aimed to evaluate the digitizing accuracy of electromagnetic and optical systems. Additionally, we introduced a novel rotation method for the electromagnetic system and compared its accuracy with the conventional method of electromagnetic and optical systems. In the conventional method, the operator moves around a stationary participant to digitize, while the participant does not move their head or body. In contrast, in our proposed rotation method with an electromagnetic system, the operator rotates the participant sitting on a swivel chair to digitize in a consistent position. We showed high localization accuracy in both the optical and electromagnetic systems, with an average localization error of less than 3.6 mm. Comparisons of the digitization methods revealed that the electromagnetic system demonstrates superior digitizing accuracy compared to the optical system. Notably, the proposed rotational method is the most accurate among the three methods, which can be attributed to the consistent positioning of EEG electrode digitization within the electromagnetic field. Considering the affordability of the electromagnetic system, our findings provide valuable insights for researchers aiming for precise EEG source estimation.•The study compares the accuracy of electromagnetic and optical systems for EEG electrode digitization, introducing a novel rotation method for improved consistency and precision.•The electromagnetic system, especially with the proposed rotation method, achieves superior digitizing accuracy over the optical system.•Highlighting the cost-effectiveness and precision of the electromagnetic system with the rotation method, this research offers significant insights for achieving precise EEG source estimation.

Cooperative Localization under Ionospheric Scintillation Events

Ionospheric scintillation causes major impairments to Global Navigation Satellite System (GNSS) in low-latitude regions. In severe scenarios, this event can lead to complete loss of lock, thus making GNSS measurements unusable for navigation. In this paper, we derive a cooperative localization algorithm where a set of partially connected aircraft exchange messages with neighboring nodes on the network to improve their own position estimates. We consider the scintillation events as abrupt changes in the measurement variance, which are modeled by a discrete-valued Markov process at the nodes which have access to GNSS measurements. Simulation results show that Markovian modeling and cooperation via factor graph message passing reduce the average 3D root mean square localization error and yield an average vertical position error that meets civil aviation standards for approach and landing.

Determine the location of acoustic emission source on wood surface by using a wavelet-energy attenuation method

ABSTRACT To determine the location of wood damage and fracture, an acoustic emission source localization method based on wavelet-energy attenuation law was proposed. High-speed acquisition equipment and LabVIEW software were used to design a three-channel AE signal acquisition system. The wavelet transform is used to decompose the original signals into five frequency levels, and the second, third, and fourth level were selected for reconstruction of the acoustic emission signal. Finally, the reconstructed signals was used to determine the location of the acoustic emission source in accordance with the energy attenuation law. The results indicated that when the distance between the three sensors were 100 and 200 mm, the average location error obtained using the original signals in accordance with the energy attenuation law was 12.6 and 18.4 mm, respectively. However, the average location error obtained using the reconstructed signals in accordance with the energy attenuation law was 2.2 and 6.9 mm, respectively. These results reveal that the proposed method can achieve high-precision localization of acoustic emission source. This research enrich and expand the content of AE technology and wooden building research, provide new ideas and methods for non-destructive testing of similar structures, and promote research progress in related fields..

Side Collision Detection Model for Visually Impaired Using Monocular Object-specific Distance Estimation and Multimodal Real-World Location Calculation

Targeting the potential risk of side-vehicle collisions when the visually impaired crosses roads, this study proposed a side collision detection model, including monocular distance estimation, multimodal real-world location estimation, future location prediction and collision warning strategies tailored for visually impaired pedestrians. The proposed model employs YOLOv8 and DeepSort for vehicle detection and tracking, utilizing shallow neural networks for distance estimation based on image information and vehicle position data. Predicted vehicle distances are combined with magnetic field sensor and GPS data to compute and store real-world vehicle locations, and these location data will be used for linear regression to forecast future locations. A warning strategy is then implemented to alert users. Experimental validation shows that the monocular distance estimation network has an Absolute Relative Error of 0.043 and an ALE (Average Localization Error) of 1.249m. In real-world location estimation, the view angle ALE is 0.019, and the location ALE is 1.778m. Regarding location prediction, the accuracy in distinguishing stationary and moving vehicles reaches 0.962, and the predicted curve, based on ground truth and predicted locations, exhibits good alignment. The proposed warning strategy, evaluated on Kitti Tracking Dataset and a self-created dataset, accurately detects the majority of potential collision risks.

Metric localization for lunar rovers via cross-view image matching

Accurate localization is critical for lunar rovers exploring lunar terrain features. Traditionally, lunar rover localization relies on sensor data from odometers, inertial measurement units and stereo cameras. However, localization errors accumulate over long traverses, limiting the rover’s localization accuracy. This paper presents a metric localization framework based on cross-view images (ground view from a rover and air view from an orbiter) to eliminate accumulated localization errors. First, we employ perspective projection to reduce the geometric differences in cross-view images. Then, we propose an image-based metric localization network to extract image features and generate a location heatmap. This heatmap serves as the basis for accurate estimation of query locations. We also create the first large-area lunar cross-view image (Lunar-CV) dataset to evaluate the localization performance. This dataset consists of 30 digital orthophoto maps (DOMs) with a resolution of 7 m/pix, collected by the Chang’e-2 lunar orbiter, along with 8100 simulated rover panoramas. Experimental results on the Lunar-CV dataset demonstrate the superior performance of our proposed framework. Compared to the second best method, our method significantly reduces the average localization error by 26% and the median localization error by 22%.

A novel meta‐learning network for partial discharge source localization in gas‐insulated switchgear via digital twin

AbstractDue to the requirement for highly precise synchronous sampling and the substantial reliance on time difference calculations, the current partial discharge (PD) localization based on the time difference of arrival is only applicable in certain situations. As digital twin technology has advanced, it is possible to employ virtual models to support gas‐insulated switchgear (GIS) PD localization. To do this, we propose a meta‐learning (ML) network with the aid of digital twin for actual GIS PD localization. Firstly, a GIS digital twin model was established to acquire an auxiliary simulated sample library. Then, a temporal convolutional network is established to extract the discriminable features, effectively obtain the time dependence between features, and improve the accuracy of localization. Next, ML is adopted to quickly learn meta‐knowledge that can be applied across tasks, and the model's sensitivity to task changes is improved. Finally, the model is fine‐tuned through a limited number of samples from the target task, and high precise PD localization is achieved. The experimental results demonstrate that the ML has an average localization error of only 9.25 cm and a probability density rose to 93% within 20 cm, which is clearly superior to previous methods.

Sparse reconstruction of ultrasonic guided wave signals of fluid-filled pipes by multistrategy hybrid DBO-OMP using dispersive Hanning-windowed chirplet model

Ultrasonic guided waves (UGWs) in fluid-filled pipes are subject to more severe dispersion and coherent noise than those of vacant pipes, posing significant challenges for defect identification and localization. To this end, a novel sparse signal decomposition method called multistrategy hybrid dung beetle optimization based orthogonal matching pursuit (MHDBO-OMP) using dispersive Hanning-windowed chirplet model was proposed, of which the model not only represents the nonlinear frequency and asymmetric envelope of the dispersive UGW, but also contains the mode and propagation distance information, and this model exhibits better matching and interpretability than the other UGW models. For dispersive perturbed UGW signals with multiple modes and features, MHDBO-OMP achieves high reconstruction accuracy in both signal reconstruction (RES < 0.3) and propagation distance estimation (RES < 3 cm). When applied to experimental UGW signals obtained from water/oil-filled pipes containing cracks and corrosion pits, MHDBO-OMP successfully reconstructs dispersion-compensated signals that solely contain feature signals, and the minimum location error is 0.72 cm while the average location error is 2.65 cm. © 2001 Elsevier Science. All rights reserved.

Positioning algorithm based on space constraint of the PD array in VLP system

Due to factors such as indoor multipath effects and noise, the positioning signal becomes unstable, posing a challenge for visible light positioning systems relying on a single photodetector (PD) to achieve accurate position estimation. To enhance localization precision and ranging accuracy, a positioning algorithm based on spatial constraints of the PD array is introduced in this paper. By leveraging spatial information from the PD array and the channel state information (CSI) from multiple PDs, cross-matching among multiple PDs is performed to alleviate the limitation of unstable positioning information of a single PD during the positioning process. Moreover, the distances obtained through cross-matching are fused with those based on CSI, and the measured distance is iteratively updated to reduce the interference of reflection paths on ranging. This algorithm utilizes the spatial arrangement of the PD array to constrain positioning information received by multiple PDs, rather than relying on a single PD for positioning. This method can achieve joint optimization of positioning accuracy and ranging accuracy without requiring additional equipment or modifying the transceiver structure. Simulation results within a 4 m × 4 m × 3 m indoor space showcase the proposed method's effectiveness. The average positioning error has been reduced to 1.28 cm, and the root mean square error has been reduced to 1.51 cm. In comparison to the least squares (LS) algorithm based on CSI and the nonlinear LS algorithm based on CSI, the new approach reduces average localization errors by approximately 50.4% and 41.3%, respectively. Additionally, the algorithm attains a ranging accuracy of 3.86 cm, outperforming CSI-based distance estimation accuracy by 41.9%.

Multi-Constellation-Inspired Single-Shot Global LiDAR Localization

Global localization is a challenging task for intelligent robots, as its accuracy directly contributes to the performance of downstream navigation and planning tasks. However, existing literature focus more on the place retrieval and the success rate of localization, with limited attention given to the metrics of position estimation. In this paper, a single-shot global LiDAR localization method is proposed with the ultimate goal of achieving high position accuracy, inspired by the positioning approach of multi-constellation localization systems. Initially, we perform coarse localization using global descriptors and select observation points along with their corresponding coordinates based on the obtained coarse localization results. Coordinates can be acquired from a pre-built map, GNSS, or other devices. Then, a lightweight LiDAR odometry method is designed to estimate the distance between the retrieved data and the observation points. Ultimately, the localization problem is transformed into an optimization problem of solving a system of multiple sphere equations. The experimental results on the KITTI dataset and the self-collected dataset demonstrate that our method achieves an average localization error (including errors in the z-axis) of 0.89 meters. In addition, it achieves retrieval efficiency of 0.357 s per frame on the former dataset and 0.214 s per frame on the latter one. Code and data are available at https://github.com/jlurobot/multi-constellation-localization.

A Long-Range Signal-Based Target Localization Algorithm

Indoor target localization is pivotal across various applications, encompassing security monitoring, behavioral analysis, and elderly care. This work proposes an advanced target localization algorithm that harnesses antennas endowed with sensing capabilities to capture the phase change in the signal ratio, derived from the signal amplitude. This phase change, indicative of the target’s movement direction, is analyzed alongside the front and rear arrival angle information and signal amplitude characteristics obtained from LoRa signals. The algorithm, through a comprehensive examination of the phase change patterns, amalgamated with arrival angle data and signal amplitude characteristics, effectively estimates the precise location of the target. Experimental validations underscore the algorithm’s efficacy in determining the target’s location during continuous walking activity. Conducted within a 6 m × 12 m open platform, the algorithm achieves an average localization error of 48.5 cm, underscoring its superior performance compared to existing methodologies.

Improving the Detection Effect of Long-Baseline Lightning Location Networks Using PCA and Waveform Cross-Correlation Methods

Ultra-long-distance and high-precision lightning location technology is an important means to realize low-cost and wide-area lightning detection. This paper carried out research on the high-precision location technology of very-low-frequency (VLF) lightning electromagnetic pulse based on the Asia-Pacific Lightning Location Network (APLLN) deployed in 2018. Two key technologies are proposed in this paper: one is the calculation method of signal arrival time using very-low-frequency lightning electromagnetic pulse waveform, and the other is the compression transmission technology of lightning electromagnetic pulse waveform based on a signal principal component analysis. The results of a comparison and evaluation of the improved APLLN with the ADTD system show that the APLLN has a relative location efficiency of 69.1% and an average location error within the network of 4.5 km.

Development of an indoor corridor localization system based on a WCL method with corridor area selection and distance compensation

SummaryIn this paper, a received signal strength indicator (RSSI)‐based weighted centroid localization (WCL) method for indoor corridor scenarios is developed and tested. The contribution of the proposed system is that, to scope the area of an unknown target position, the possible corridor area where the target node should be located is automatically selected, and only reference nodes deployed in such an area are applied for position estimation. Additionally, to improve the estimation precision, distance values converted from measured RSSIs and used for the WCL are also compensated to alleviate the RSSI variation problem caused by physical environments. Therefore, our methods can save a number of reference nodes to be used, while localization accuracy can also be achieved. Experiments in the corridor environment using a 2.4 GHz IEEE 802.15.4 wireless sensor network with four reference nodes deployed in the test field dimension of 22 m × 9.3 m have been performed. Experimental results demonstrate that the proposed method, which requires only two reference nodes, outperforms the original WCL method with four reference nodes by 53.053%, as indicated by average localization errors. The results also reveal that the proposed method provides error distances lower than the WCL method for all test target positions, while all estimated positions fall within the corridor areas by 100%.

Mechanical Fault Sound Source Localization Estimation in a Multisource Strong Reverberation Environment

Aiming at the sound source localization of mechanical faults in a strong reverberation scenario with multiple sound sources, this paper investigates a mechanical fault source localization method using the U-net deep convolutional neural network. The method utilizes the SRP-PHAT algorithm to calculate the response power spectra of the collected multichannel fault signals. Through the utilization of the U-net neural network, the response power spectra containing spurious peaks are transformed into “clean” estimated source distribution maps. By employing interpolation search, the estimated source distribution maps are processed to obtain location estimations for multiple fault sources. To validate the effectiveness of the proposed method, this paper constructs an experimental dataset using mechanical fault data from electromechanical equipment relays and conducts sound source localization experiments. The experimental results show that the U-net network under 0.2 s/0.5 s/0.7 s reverberation time can effectively eliminate spurious peak interference in the response power spectrum. As the signal-to-noise ratio decreases, it can still distinguish the sound sources with a distance of 0.2 m. In the context of multifault source localization, the method is capable of simultaneously locating the positions of four fault sources, with an average localization error of less than 0.02 m. The method in this paper effectively eliminates spurious peaks in the response power spectra under conditions of multisource strong reverberation. It accurately locates multiple mechanical fault sources, thereby significantly enhancing the efficiency of mechanical fault detection.

Automatic Tracking of Hyoid Bone Displacement and Rotation Relative to Cervical Vertebrae in Videofluoroscopic Swallow Studies Using Deep Learning.

The hyoid bone displacement and rotation are critical kinematic events of the swallowing process in the assessment of videofluoroscopic swallow studies (VFSS). However, the quantitative analysis of such events requires frame-by-frame manual annotation, which is labor-intensive and time-consuming. Our work aims to develop a method of automatically tracking hyoid bone displacement and rotation in VFSS. We proposed a full high-resolution network, a deep learning architecture, to detect the anterior and posterior of the hyoid bone to identify its location and rotation. Meanwhile, the anterior-inferior corners of the C2 and C4 vertebrae were detected simultaneously to automatically establish a new coordinate system and eliminate the effect of posture change. The proposed model was developed by 59,468 VFSS frames collected from 1488 swallowing samples, and it achieved an average landmark localization error of 2.38 pixels (around 0.5% of the image with 448 × 448 pixels) and an average angle prediction error of 0.065 radians in predicting C2-C4 and hyoid bone angles. In addition, the displacement of the hyoid bone center was automatically tracked on a frame-by-frame analysis, achieving an average mean absolute error of 2.22 pixels and 2.78 pixels in the x-axis and y-axis, respectively. The results of this study support the effectiveness and accuracy of the proposed method in detecting hyoid bone displacement and rotation. Our study provided an automatic method of analyzing hyoid bone kinematics during VFSS, which could contribute to early diagnosis and effective disease management.

Attention Mechanism and LSTM Network for Fingerprint-Based Indoor Location System.

The demand for precise indoor localization services is steadily increasing. Among various methods, fingerprint-based indoor localization has become a popular choice due to its exceptional accuracy, cost-effectiveness, and ease of implementation. However, its performance degrades significantly as a result of multipath signal attenuation and environmental changes. In this paper, we propose an indoor localization method based on fingerprints using self-attention and long short-term memory (LSTM). By integrating a self-attention mechanism and LSTM network, the proposed method exhibits outstanding positioning accuracy and robustness in diverse experimental environments. The performance of the proposed method is evaluated under two different experimental scenarios, which involve 2D and 3D moving trajectories, respectively. The experimental results demonstrate that our approach achieves an average localization error of 1.76 m and 2.83 m in the respective scenarios, outperforming the existing state-of-the-art methods by 42.67% and 31.64%.

Low Velocity Impact Monitoring of Composite Tubes Based on FBG Sensors.

Carbon fiber reinforced composites (CFRP) are susceptible to hidden damage from low velocity external impacts during their service life. To ensure the proper monitoring of the state of the composites, it is crucial to predict the location of an impact event. In this paper, fiber Bragg grating (FBG) sensors are affixed to the surface of a carbon fiber composite tube, and an optical sensing interrogator is used to capture the central wavelength shift of the FBG sensors due to low-velocity impacts. A discrete wavelet transform is used for noise reduction in the response signals. Then, the differences in the captured response signals of the FBG sensors at different locations of the impact were analyzed. Moreover, two methods were implemented to predict the location of low-velocity impacts, according to the differences in the captured response signals. The BP neural network-based method utilized three data sets to train the neural network, resulting in an average localization error of 20.68 mm. In contrast, the method based on error outliers selected a specific data set as the reference dataset, achieving an average localization error of 13.98 mm. The comparison of the predicted results shows that the latter approach has a higher predictive accuracy and does not require a significant amount of data.

Fusion of Time-of-Flight Based Sensors with Monocular Cameras for a Robotic Person Follower

Human-robot collaboration (HRC) is becoming increasingly important in advanced production systems, such as those used in industries and agriculture. This type of collaboration can contribute to productivity increase by reducing physical strain on humans, which can lead to reduced injuries and improved morale. One crucial aspect of HRC is the ability of the robot to follow a specific human operator safely. To address this challenge, a novel methodology is proposed that employs monocular vision and ultra-wideband (UWB) transceivers to determine the relative position of a human target with respect to the robot. UWB transceivers are capable of tracking humans with UWB transceivers but exhibit a significant angular error. To reduce this error, monocular cameras with Deep Learning object detection are used to detect humans. The reduction in angular error is achieved through sensor fusion, combining the outputs of both sensors using a histogram-based filter. This filter projects and intersects the measurements from both sources onto a 2D grid. By combining UWB and monocular vision, a remarkable 66.67% reduction in angular error compared to UWB localization alone is achieved. This approach demonstrates an average processing time of 0.0183s and an average localization error of 0.14 meters when tracking a person walking at an average speed of 0.21 m/s. This novel algorithm holds promise for enabling efficient and safe human-robot collaboration, providing a valuable contribution to the field of robotics.

Localization in 3D Wireless Sensor Networks with Obstacle Consideration

Wireless sensor network (WSN) refers to the network formed by sensor nodes for communicating sensed data over the wireless medium. These sensor nodes are mostly deployed randomly in the target area, and hence estimating the coordinates of these sensor nodes through the localization process is an important activity. Majority of the localization algorithms existing in the literature assume the target area to be an obstacle-free 2D terrain. However, such algorithms are not suitable for real-life scenarios where WSNs are actually deployed on 3D terrains that may also have obstacles that hinder the radio signals from the deployed sensor nodes. Hence, factors such as the height of the terrain, the presence of obstacles, etc., require significant considerations while designing algorithms for WSN. The proposed research presents a localization scheme for 3D WSN where the sensor nodes are randomly deployed in a 3D area having large obstacles. The proposed scheme adopts a distributed approach for calculating the virtual coordinates of the sensors using four beacon nodes. The deployment area is divided into regions, and each node computes its virtual coordinates with respect to the obstacle. Simulation results indicate an average localization error of 6.93 m. The proposed scheme requires very less computational effort and can be easily adapted in different scenarios.

Improved Pedestrian Location Method for the Indoor Environment Based on MIMU and sEMG Sensors

In order to guarantee the pedestrian location accuracy for the indoor environment, an improved pedestrian location method based on the improved Mahony complementary filter algorithm is proposed by the data fusion of microinertial measurement unit (MIMU) and sEMG sensors, which are installed on the lower limbs. First, the pedestrian location method for the indoor environment is introduced by the data fusion of MIMU and surface electromyography; and then, BP neural network is applied to adjust the parameters in real time for PI controller of Mahony complementary filter algorithm, which can obtain the current heading angle for the location. Finally, the indoor environment experiments for pedestrian location are carried out. The heading angle estimating experiment result shows that the indoor heading angle for the pedestrian can be exactly calculated by the improved Mahony complementary filter algorithm. The indoor location experiment shows that the average relative location error is 2.34 m, and the average relative location error rate is 2.27%.