Search Results (251)

Populus euphratica is a key constructive species in desert ecosystems and plays a vital role in maintaining their stability. However, effective automated methods for accurately delineating its distribution outlines are currently lacking. This study used the mainstream area of the Tarim River as a case study and proposed a technical solution for identifying the distribution outline of Populus euphratica using multi-source thematic classification data. First, cropland thematic data were used to optimize the accuracy of the Populus euphratica classification raster data. Discrete points were removed based on density to reduce their impact on boundary identification. Then, a hierarchical identification scheme was constructed using the alpha-shape algorithm to identify the boundaries of high- and low-density Populus euphratica distribution areas separately. Finally, the outlines of the Populus euphratica distribution polygons were smoothed, and the final distribution outline data were obtained after spatial merging. The results showed the following: (1) Applying a closing operation to the cropland thematic classification data to obtain the distribution range of shelterbelts effectively eliminated misclassified pixels. Using the kd-tree algorithm to remove sparse discrete points based on density, with a removal ratio of 5%, helped suppress the interference of outlier point sets on the Populus euphratica outline identification. (2) Constructing a hierarchical identification scheme based on differences in Populus euphratica density is critical for accurately delineating its distribution contours. Using the alpha-shape algorithm with parameters set to α = 0.02 and α = 0.006, the reconstructed geometries effectively covered both densely and sparsely distributed Populus euphratica areas. (3) In the morphological processing stage, a combination of three methods—Gaussian filtering, equidistant expansion, and gap filling—effectively ensured the accuracy of the Populus euphratica outline. Among the various smoothing algorithms, Gaussian filtering yielded the best results. The equidistant expansion method reduced the impact of elongated cavities, thereby contributing to boundary accuracy. This study enhances the automation of Populus euphratica vector data mapping and holds significant value for the scientific management and research of desert vegetation. Full article

Unmanned aerial vehicles (UAVs) are increasingly used indoors for inspection, security, and emergency tasks. Achieving accurate and robust localization under Global Navigation Satellite System (GNSS) unavailability and obstacle occlusions is therefore a critical challenge. Due to their inherent physical limitations, Inertial Measurement Unit (IMU)–based localization errors accumulate over time, Ultra-Wideband (UWB) measurements suffer from systematic biases in Non-Line-of-Sight (NLOS) environments and Visual–Inertial Odometry (VIO) depends heavily on environmental features, making it susceptible to long-term drift. We propose a tightly coupled fusion framework based on the Error-State Kalman Filter (ESKF). Using an IMU motion model for prediction, the method incorporates raw UWB ranges, VIO relative poses, and TFmini altitude in the update step. To suppress abnormal UWB measurements, a multi-epoch outlier rejection method constrained by VIO is developed, which can robustly eliminate NLOS range measurements and effectively mitigate the influence of outliers on observation updates. This framework improves both observation quality and fusion stability. We validate the proposed method on a real-world platform in an underground parking garage. Experimental results demonstrate that, in complex indoor environments, the proposed approach exhibits significant advantages over existing algorithms, achieving higher localization accuracy and robustness while effectively suppressing UWB NLOS errors as well as IMU and VIO drift. Full article

In indoor environments, fusion localization methods that combine Wi-Fi fingerprinting and Pedestrian Dead Reckoning (PDR) are constrained by the high sensitivity of traditional filters, such as the Extended Kalman Filter (EKF), to initial states and by their susceptibility to nonlinear drift. This study presents a Wi-Fi/PDR fusion localization approach based on global geometric alignment optimized via a Genetic Algorithm (GA). The proposed method models the PDR trajectory as an integrated geometric entity and performs a global search for the optimal two-dimensional similarity transformation that aligns it with discrete Wi-Fi observations, thereby eliminating dependence on precise initial conditions and mitigating multipath noise. Experiments conducted in a real office environment (14 × 9 m, eight dual-band APs) with a double-L trajectory demonstrate that the proposed GA fusion achieves the lowest mean error of 0.878 m (compared to 2.890 m, 1.277 m, and 1.193 m for Wi-Fi, PDR, and EKF fusion, respectively) and an RMSE of 0.978 m. It also attains the best trajectory fidelity (DTW = 0.390 m, improving by 71.0%, 14.7%, and 27.8%) and the smallest maximum deviation (Hausdorff = 1.904 m, 52.4% lower than Wi-Fi). The cumulative error distribution shows that 90% of GA fusion errors are within 1.5 m, outperforming EKF and PDR. Additional experiments that compare the proposed GA optimizer with Levenberg–Marquardt (LM), particle swarm optimization (PSO), and Procrustes alignment, as well as tests with 30% artificial Wi-Fi outliers, further confirm the robustness of the Huber-based cost and the effectiveness of the global optimization framework. These results indicate that the proposed GA-based fusion method achieves high robustness and accuracy in the tested office-scale scenario and demonstrate its potential as a practical multi-sensor fusion approach for indoor localization. Full article

Dam displacement monitoring is crucial for assessing structural safety; however, conventional models often prioritize single-task prediction, leading to an inherent difficulty in balancing monitoring data quality with model performance. To bridge this gap, this study proposes a novel two-stage analytical framework that synergistically integrates an improved isolation forest (iForest) with a metaheuristic-optimized random forest (RF). The first stage focuses on data cleaning, where Kalman filtering is applied for denoising, and a newly developed Dynamic Threshold Isolation Forest (DTIF) algorithm is introduced to effectively isolate noise and outliers amidst complex environmental loads. In the second stage, the model’s predictive capability is enhanced by first employing the LASSO algorithm for feature importance analysis and optimal subset selection, followed by an Improved Reptile Search Algorithm (IRSA) for fine-tuning RF hyperparameters, thereby significantly boosting the model’s robustness. The IRSA incorporates several key improvements: Tent chaotic mapping during initialization to ensure population diversity, an adaptive parameter adjustment mechanism combined with a Lévy flight strategy in the encircling phase to dynamically balance global exploration and convergence, and the integration of elite opposition-based learning with Gaussian perturbation in the hunting phase to refine local exploitation. Validated against field data from a concrete hyperbolic arch dam, the proposed DTIF algorithm demonstrates superior anomaly detection accuracy across nine distinct outlier distribution scenarios. Moreover, for long-term displacement prediction tasks, the IRSA-RF model substantially outperforms traditional benchmark models in both predictive accuracy and generalization capability, providing a reliable early risk warning and decision-support tool for engineering practice. Full article

Realizing real-time dense 3D reconstruction on resource-limited mobile platforms remains a significant challenge, particularly in low-texture environments that demand robust multi-frame fusion to resolve matching ambiguities. However, the inherent tight coupling of pose estimation and mapping in traditional monolithic SLAM architectures imposes a severe restriction on integrating high-complexity fusion algorithms without compromising tracking stability. To overcome these limitations, this paper proposes MDR–SLAM, a modular and fully decoupled stereo framework. The system features a novel keyframe-driven temporal filter that synergizes efficient ELAS stereo matching with Kalman filtering to effectively accumulate geometric constraints, thereby enhancing reconstruction density in textureless areas. Furthermore, a confidence-based fusion backend is employed to incrementally maintain global map consistency and filter outliers. Quantitative evaluation on the NUFR-M3F indoor dataset demonstrates the effectiveness of the proposed method: compared to the standard single-frame baseline, MDR–SLAM reduces map RMSE by 83.3% (to 0.012 m) and global trajectory drift by 55.6%, while significantly improving map completeness. The system operates entirely on CPU resources with a stable 4.7 Hz mapping frequency, verifying its suitability for embedded mobile robotics. Full article

Global Navigation Satellite System (GNSS)/Inertial Navigation System (INS) integrated navigation is one of the key methods for achieving precise positioning in complex urban environments. However, in some scenarios such as urban canyons, overpasses, and foliage occlusion, GNSS signals are frequently attenuated or interrupted, leading to degraded positioning accuracy when relying solely on INSs. To address this limitation, this study developed an improved GNSS/INS-integrated navigation algorithm based on a hybrid framework that combines a Robust Adaptive Kalman Filter (RAKF) with a Radial Basis Function (RBF) neural network. The RAKF allows a multi-criterion optimization strategy to be created to adaptively adjust the measurement noise covariance matrix according to GNSS data quality indicators such as PDOP, the number of satellites, and signal quality factors. This enhances the filter’s robustness and outlier detection capability under degraded GNSS conditions. Meanwhile, the RBF network is trained to predict pseudo-position increments, which substitute missing GNSS measurements during signal outages to maintain continuous navigation. Real-world vehicular experiments were conducted to evaluate the proposed RBF-aided RAKF (RBF-RAKF) against three other methods: the Extended Kalman Filter (EKF), standard RAKF, and RBF-aided Kalman Filter (RBF-KF). The experimental results demonstrate that during GNSS outages the proposed method achieved root mean square (RMS) positioning errors of 0.94, 1.02, and 0.21 m in the north, east, and down directions, respectively, representing improvements of over 90% compared with conventional filters. Moreover, the algorithm maintained meter-level horizontal accuracy and sub-meter vertical precision under severe GNSS signal degradation. These results confirm that the proposed RBF-RAKF algorithm provides stable and high-precision navigation performance in challenging urban environments. Full article

Bone drilling is a widely encountered process in orthopedic surgeries and keyhole neuro surgeries. We are developing a sensor-integrated smart end-effector for drilling for robotic surgical applications. In manual surgeries, surgeons assess tool wear based on experience and force perception. In this work, we propose a machine-learning (ML)-based tool condition monitoring system based on multi-sensor data to preempt excessive tool wear during drilling in robotic surgery. Real-time data is acquired from the six-component force sensor of a collaborative arm along with the data from the temperature and multi-axis vibration sensor mounted on the bone specimen being drilled upon. Raw data from the sensors may have noises and outliers. Signal processing in the time- and frequency-domain are used for denoising as well as to obtain additional features to be derived from the raw sensory data. This paper addresses the challenging problem of identification of the most suitable ML algorithm and the most suitable features to be used as inputs to the algorithm. While dozens of features and innumerable machine learning and deep learning models are available, this paper addresses the problem of selecting the most relevant features, the most relevant AI models, and the optimal hyperparameters to be used in the AI model to provide accurate prediction on the tool condition. A unique framework is proposed for classifying tool wear that combines machine learning-based modeling with multi-sensor data. From the raw sensory data that contains only a handful of features, a number of additional features are derived using frequency-domain techniques and statistical measures. Using feature engineering, we arrived at a total of 60 features from time-domain, frequency-domain, and interaction-based metrics. Such additional features help in improving its predictive capabilities but make the training and prediction complicated and time-consuming. Using a sequence of techniques such as variance thresholding, correlation filtering, ANOVA F-test, and SHAP analysis, the number of features was reduced from 60 to the 4 features that will be most effective in real-time tool condition prediction. In contrast to previous studies that only examine a small number of machine learning models, our approach systematically evaluates a wide range of machine learning and deep learning architectures. The performances of 47 classical ML models and 6 deep learning (DL) architectures were analyzed using the set of the four features identified as most suitable. The Extra Trees Classifier (an ML model) and the one-dimensional Convolutional Neural Network (1D CNN) exhibited the best prediction accuracy among the models studied. Using real-time data, these models monitored the drilling tool condition in real-time to classify the tool wear into three categories of slight, moderate, and severe. Full article

Automated berthing remains a critical challenge for autonomous surface vessels (ASVs), necessitating precise berthing state estimation as a fundamental prerequisite. In this paper, we present a novel berthing state estimation method tailored for ASVs and based on 3D LiDAR technology. Firstly, a berthing plane acquisition scheme based on point cloud plane fitting is proposed; the feasibility of the scheme was verified by experiments. The point cloud registration algorithm was used to realize the ship pose estimation. Before registration, the preprocessing technology was used to filter out the noise and outliers in the point cloud data to improve the accuracy of pose estimation. A detailed method for calculating the berthing state information is proposed. This method considers the influence of ship roll, pitch, and yaw during berthing, and ensures the accuracy of the obtained state information. Finally, a real-time ship berthing perception framework was constructed using the Robot Operating System (ROS), enabling the continuous output of vital berthing state information, including berthing distance, velocity, approaching angle, and yaw rate, at a frequency of 10 Hz. To validate the effectiveness of our algorithm, extensive real ship experiments were conducted, yielding highly promising results. The average angle error was found to be less than 0.26°, with an average distance error below 0.023 m. Full article

Artificial intelligence (AI) and machine learning (ML) have become integral to various applications, leveraging vast amounts of heterogeneous, globally distributed Internet of Things (IoT) data to identify patterns and build accurate ML models for predictive tasks. Federated learning (FL) is a distributed ML technique developed to learn from such distributed data while ensuring privacy. Nevertheless, traditional FL requires a central server for aggregation, which can be a central point of failure and raises trust issues. Blockchain-based federated learning (BFL) has emerged as an FL extension that provides guaranteed decentralization alongside other security assurances. However, due to the inherent openness of blockchain, BFL comes with several vulnerabilities that remain unexplored in literature, e.g., a higher possibility of model poisoning attacks. This paper investigates how scaling-based model poisoning attacks are made easier in BFL systems and their effects on model performance. Subsequently, it proposes FedECPA-an extension of FedAvg aggregation algorithm with Efficient Countermeasure against scaling-based model Poisoning Attacks in BFL. FedECPA filters out clients with outlier weights and protects the model against these attacks. Several experiments are conducted with different attack scenarios and settings. We further compared our results to a frequently used defense mechanism, Multikrum. Results show the effectiveness of our defense mechanism in protecting BFL from these attacks. On the MNIST dataset, it maintains an overall accuracy of $98\%$ and $89\%$ and outperforms our baseline with $4\%$ and $38\%$ in both IID and non-IID settings, respectively. Similar results were achieved with the CIFAR-10 dataset. Full article

Photogrammetry offers a non-contact and efficient alternative for monitoring structural deformation and is particularly suited to large or complex surfaces such as masonry walls. This study proposes a spatio-temporal photogrammetric refinement framework that enhances the accuracy of three-dimensional (3D) deformation and strain analysis by integrating advanced filtering techniques into markerless image-based measurement workflows. A hybrid methodology was developed using natural image features extracted using the Speeded-Up Robust Features algorithm and refined through a three-stage filtering process: median absolute deviation filtering, Gaussian smoothing, and representative point selection. These techniques significantly mitigated the influence of noise and outliers on deformation and strain analysis. Comparative experiments using both manually placed targets and automatically extracted feature points on a full-scale masonry wall under destructive loading demonstrated that the proposed spatio-temporal filtering effectively improves the consistency of displacement and strain fields, achieving results comparable to traditional marker-based methods. Validation against laser rangefinder measurements confirmed sub-millimeter accuracy in displacement estimates. Additionally, strain analysis based on filtered data captured crack evolution patterns and spatial deformation behavior. Therefore, integrating photogrammetric 3D point tracking with spatio-temporal refinement provides a practical, accurate, and scalable approach to monitor structural deformation in civil engineering applications. Full article

Line feature matching is a fundamental and extensively studied subject in the fields of photogrammetry and computer vision. Traditional methods, which rely on handcrafted descriptors and distance-based filtering outliers, frequently encounter challenges related to robustness and a high incidence of outliers. While some approaches leverage point features to assist line feature matching by establishing the invariant geometric constraints between points and lines, this typically results in a considerable computational load. In order to overcome these limitations, we introduce a novel Bayesian posterior probability framework for line matching that incorporates three geometric constraints: the distance between line feature endpoints, midpoint distance, and angular consistency. Our approach initially characterizes inter-image geometric relationships using Fourier representation. Subsequently, we formulate the posterior probability distributions for the distance constraint and the uniform distribution based on the constraint of angular consistency. By calculating the joint probability distribution under three geometric constraints, robust line feature matches are iteratively optimized through the Expectation–Maximization (EM) algorithm. Comprehensive experiments confirm the effectiveness of our approach: (i) it outperforms state-of-the-art (including deep learning-based) algorithms in match count and accuracy across common scenarios; (ii) it exhibits superior robustness to rotation, illumination variation, and motion blur compared to descriptor-based methods; and (iii) it notably reduces computational overhead in comparison to algorithms that involve point-assisted line matching. Full article

This article introduces an algorithm that uses a U-Net architecture to determine vertical ground surface displacements from unmanned aerial vehicle (UAV)-photogrammetry point clouds, offering an alternative to traditional ground filtering methods. Unlike conventional ground filters that rely on point cloud classification, the proposed approach employs heteroscedastic regression. The U-Net model predicts the conditional expected values of the elevation corrections, aiming to reduce the impact of vegetation on determined ground surface elevations. Concurrently, it estimates the logarithm of the elevation correction variance, allowing for direct quantification of the uncertainty associated with each elevation correction value. The algorithm was evaluated using three metrics: the root mean square error (RMSE) of vertical displacements, the percentage of nodes with determined displacement values, and the percentage of outliers among those values. Performance was assessed using the technique for order of preference by similarity to ideal solution (TOPSIS) method and compared against several ground-filter-based algorithms across four datasets, each including at least two time intervals. In most cases, the U-Net-based approach demonstrated a slight performance advantage over traditional ground filtering techniques. For example, for the U-Net-based algorithm, for one of the test datasets, the RMSE of the determined subsidences was 6.1 cm, the percentage of nodes with determined subsidences was 80.5%, and the percentage of outliers was 0.2%. For the same case, the algorithm based on the next best model (SMRF) allowed an RMSE of 7.7 cm to be obtained; for 77.3% of nodes, the subsidences were determined; and the percentage of outliers was 0.3%. Full article

Power transformers represent critical assets within the electrical power system, and their unexpected failures may result in substantial financial losses for both utilities and consumers. Dissolved Gas Analysis (DGA) is a well-established diagnostic method extensively employed to detect incipient faults in power transformers. Although several conventional and machine learning techniques have been applied to DGA, most of them focus only on fault classification and lack the capability to provide predictive scenarios that would enable proactive maintenance planning. In this context, the present study introduces a novel approach to DGA interpretation, which highlights the trends and progression of faults by exploring the feature space through the algorithms k-Nearest Neighbors (KNN) and Optimum-Path Forest (OPF). To improve accuracy, the following strategies were implemented: statistical filtering based on normal distribution to eliminate outliers from the dataset; augmentation of gas-related features; and feature selection using optimization algorithms such as Cuckoo Search and Genetic Algorithms. The approach was validated using data from several transformers, with fault diagnoses cross-checked against inspection reports provided by the utility company. The findings indicate that the proposed method offers valuable insights into the progression, proximity, and classification of faults with satisfactory accuracy, thereby supporting its recommendation as a complementary tool for diagnosing incipient transformer faults. Full article

The preventive maintenance of power transformers is essential to ensure their reliability and is supported by efficient predictive techniques and accurate diagnostics. In this context, the objective of this work is to present a hybrid Artificial Intelligence (AI) model for reliable decision making in transformer maintenance based on performance index monitoring. The innovation lies in the application of Monte Carlo filters to monitor the operational state of transformers combined with a novel clustering strategy. The used methodology includes the development of an algorithm for outlier removal in the historical series of each predictive technique as well as the implementation of stochastic filters to forecast the overall operational condition. The results demonstrate the robustness and effectiveness of the developed model. This work contributes a new AI-based strategy for supporting preventive maintenance decisions, enabling precise and individualized actions for each piece of equipment, with broad applicability to companies in the electrical power sector. Full article

With the advancement of autonomous driving technology, the performance of LiDAR in adverse weather conditions has garnered increasing attention. Traditional denoising algorithms, including intensity-based methods like LIOR (a representative intensity-based filter that relies solely on signal intensity), have limited effectiveness in handling snow noise, especially in removing dynamic noise points and distinguishing them from environmental features. This paper proposes a Dynamic Vertical and Low-Intensity Outlier Removal (DVIOR) algorithm, specifically designed to optimize LiDAR point cloud data under snowy conditions. The DVIOR algorithm, as an extension of intensity-based filtering augmented with vertical height information, dynamically adjusts filter parameters by combining the height and intensity information of the point cloud, effectively filtering out snow noise while preserving environmental features. In our experiments, the DVIOR algorithm was evaluated on several publicly available adverse weather datasets, including the Winter Adverse Driving Scenarios (WADS), the Canadian Adverse Driving Conditions (CADC), and the Radar Dataset for Autonomous Driving in Adverse weather conditions (RADIATE) datasets. Compared with both the mainstream dynamic distance–intensity hybrid algorithm in recent years, Dynamic Distance–Intensity Outlier Removal (DDIOR), and the representative intensity-based filter LIOR, DVIOR achieved notable improvements: it gained a 10.2-point higher F1-score than DDIOR and an 11.8-point higher F1-score than LIOR (79.00) on the WADS dataset. Additionally, DVIOR performed excellently on the CADC and RADIATE datasets, achieving F1-scores of 87.35 and 86.68, respectively—representing an improvement of 19.82 and 36.9 points over DDIOR and 4.67 and 17.95 points over LIOR (82.68 and 68.73). These results demonstrate that the DVIOR algorithm outperforms existing methods, including both distance–intensity hybrid approaches and intensity-based filters like LIOR, in snow noise removal, particularly in complex snowy environments. Full article