Adaptive Distance Research Articles

Vehicle trajectory extraction with interacting multiple model for low-channel roadside LiDAR

High-precision and consistent vehicle trajectories encompass microscopic traffic parameters, mesoscopic traffic flow characteristics, and macroscopic traffic flow features, which is the cornerstone of innovation in data-driven traffic management and control applications. However, occlusion and trajectory interruption remain challenging in multivehicle tracking under complex traffic environments using low-channel roadside LiDAR. To address the challenge, a novel framework for vehicle trajectory extraction using low-channel roadside LiDAR was proposed. First, the geometric features of the cluster and its L-shape bounding box were used to address the over-segmentation in vehicle detection arising from occlusion and point cloud sparse. Then, objects within adjacent point cloud frames were associated by developing an improved Hungarian algorithm integrated with an adaptive distance threshold to solve the mismatching problem caused by objects entrancing and exiting in a new point cloud frame. Finally, an improved interacting multiple model by considering vehicle driving patterns was deployed to predict the location of missing vehicles and connect the interrupted trajectories. Experimental results showed that the proposed methods achieve 98.76 % of vehicle detection accuracy and 97.40 % of data association precision. The mean absolute error (MAE) and mean square error (MSE) of the vehicle position estimation are 0.2252 m and 0.0729 m2, respectively. The trajectory extraction precision outperforms most of the state-of-the-art algorithms.

An adaptive distance protection scheme considering fault resistance, injected current, and structural changes in the power system

AbstractFaults in power systems occur for various reasons, such as aging or natural disasters. Detecting, locating, and promptly clearing these faults is crucial for maintaining the safety and reliability of transmission lines (TLs). Distance relays (DRs), which protect TLs, detect faults, estimate their location, and send the required commands. However, these relays may experience mis‐detection due to manipulated impedance arising from both internal and external factors. These factors include measurement device errors, network topology changes, the presence of fault resistance (FR), and injected currents from remote line terminals. To address this challenge, an innovative adaptive protection scheme that considers FR, changes in network topology, and injected current from the opposite end of the line is proposed. By estimating the equivalent circuit impedances (ECIs) of the network connected to the terminal of the TL, this protection scheme utilizes impedance estimation techniques at the line terminals and offline network information. Simulation studies (tested on the IEEE 39‐bus standard network) show that the proposed scheme accurately estimates fault location (FL) and FR with high precision. The simulation results demonstrate its effectiveness in improving the performance of conventional distance protection relays in both the first and second protection zones ( and ).

Design of a Path-Tracking Controller with an Adaptive Preview Distance Scheme for Autonomous Vehicles

This paper presents a method to design a path-tracking controller with an adaptive preview distance scheme for autonomous vehicles. Generally, the performance of a path-tracking controller depends on tire–road friction and is severely deteriorated on low-friction roads. To cope with the problem, it is necessary to design a path-tracking controller that is robust against variations in tire–road friction. In this paper, a preview function is introduced into the state-space model built for better path-tracking performance. With the preview function, an adaptive preview distance scheme is proposed to adaptively adjust the preview distance according to the variations in tire–road friction. Front-wheel steering (FWS) and four-wheel steering (4WS) are adopted as actuators for path tracking. With the state-space model, a linear quadratic regulator (LQR) is adopted as a controller design methodology. In the adaptive preview distance scheme, the best preview distance is obtained from simulation for several tire–road friction conditions. Curve fitting with an exponential function is applied to those preview distances with respect to the tire–road friction. To verify the performance of the adaptive preview distance scheme under variations in tire–road friction, a simulation is conducted on vehicle simulation software. From the simulation results, it was shown that the path-tracking controller with an adaptive preview distance scheme presented in this paper was effective for path tracking against variations in tire–road friction in the peak’s center offset, and the settling delays were reduced by 60% and 23%, respectively.

ECM+: An improved evidential c-means with adaptive distance

Evidential c-means (ECM) is a prototype-based clustering algorithm that generates a credal partition. Such a partition encompasses the notions that can be encountered with a hard, fuzzy or possibilistic partition, allowing the representation of various situations concerning the class membership of an object. The ECM method provides a prototype for each subset of the possible classes, calculated by averaging the prototypes of the classes included in the subsets. Although this definition perfectly suits ECM when employing a Euclidean distance, it becomes inappropriate when using a Mahalanobis distance. In this context, a new definition of prototypes for the subsets is proposed. The ECM objective function is then optimized using the new definition of prototypes. The subsequent algorithm, named ECM+, is finally tested on various synthetic and real data sets to demonstrate its interest compared to ECM.

Multiple moving object classification and tracking using DenCNN classifier

A Multiple moving object detection, tracking, and counting algorithm is mainly designed exclusively suitable for congested areas. The counting system can alleviate the betrayal performance in the crowded areas. Most of the existing methods developed for tracking and counting face serious challenges in detection due to high densities of the target. This condition urged the researchers to update the existing systems. The present methodology was designed to address such issues. In the present methodology, the contrast was initially enhanced between the objects and their backgrounds using a Double Plateau Histogram Equalization (DPHE). Then, the motion was estimated for the contrast-enhanced image to identify the moment of the object using the modified Adaptive Distance Covariance Rood Pattern Search (ADCRPS) algorithm. After that, the morphological operation was deployed to sharpen the images by removing all the unwanted things. Then, the features were extracted and important features were selected using the modified Chaotic Tent Shuffled Shepherd Optimization (CTSSO) Algorithm. With the selected features object, detection was done using the proposed Scaled Non-Monotonic Cauchy Dense Convolutional Neural Network (SNMC-DenCNN). The detected object was then tracked with the aid of Channel and Spatial Reliability Tracker (CSRT). Finally, the objects were counted by intersection over union (IOU) by explicitly computing the association between detected and tracked objects. Also, the experimental results showed the effectiveness and efficiency of the proposed system with enhanced accuracy.

Stability coordinated control strategy of autonomous unmanned 4WID-4WIS vehicle based on APD-LQR and AFSMC

To improve the four-wheel independent driving and four-wheel independent steering (4WID-4WIS) autonomous unmanned vehicles’ active safety performance at their maximum operating capacity, the control of path following, four-wheel steering (4WS) and lateral stability should be coordinated. This paper introduces a hierarchical coordinated control framework, in which several independent controllers collaborate to enhance the overall performance of the vehicle system. Initially, in the upper controller, an adaptive preview distance linear quadratic regulator (APD-LQR) path following algorithm is proposed, considering the dynamic characteristics of the tire. It aimed at making the following error converge and obtaining the optimal front wheel steering angle. Meanwhile, an adaptive fuzzy sliding mode control (AFSMC) algorithm is implemented for obtaining additional yaw moment. It aimed at coordinating and improving effectively path following performance and lateral stability. Using the phase plane approach, the sliding surface is dynamically modified. Subsequently, in the lower controller, a rear wheel angle controller based on vehicle speed is proposed. It aimed at further enhancing vehicle’s maneuverability and stability by fully utilizing its steering redundancy features. Moreover, a torque distribution controller establishes a comprehensive cost function and then the NSGA-III algorithm is employed to optimize the torque distribution coefficients. Finally, simulation and Hardware-in-Loop (HIL) test results demonstrates that the proposed coordination algorithm can fully utilize the redundancy features of the 4WID-4WIS vehicle, and significantly enhances the vehicle’s path following accuracy and lateral stability, especially under extreme driving conditions.

Reinforced Lyapunov controllers for low-thrust lunar transfers

Future missions to the Moon and beyond are likely to involve low-thrust propulsion technologies due to their propellant efficiency. However, these still present a difficult trajectory design problem, owing to the near continuous thrust, lack of control authority and chaotic dynamics. Lyapunov control laws can generate sub-optimal trajectories for such missions with minimal computational cost and are suitable for feasibility studies and as initial guesses for optimisation methods. In this work a Reinforced Lyapunov Controller is used to design optimal low-thrust transfers from geostationary transfer orbit towards lunar polar orbit. Within the reinforcement learning (RL) framework, a dual-actor network setup is used, one in each of the Earth- and Moon-centred inertial frames respectively. A key contribution of this paper is the demonstration of a forwards propagated trajectory, removing the need to define a patch point a priori. This is enabled by an adaptive patch distance and extensive initial geometry exploration during the RL training. Results for both time- and fuel-optimal transfers are presented, along with a Monte Carlo analysis of the robustness to disturbances for such transfers. Phasing is introduced where necessary to aid rendezvous with the Moon. The results demonstrate the potential for such techniques to provide a basis for the design and guidance of low-thrust lunar transfers.

Self-organizing maps with adaptive distances for multiple dissimilarity matrices

Self-organizing maps with adaptive distances for multiple dissimilarity matrices

Adaptive Safety Distance for Collision Avoidance Based on a Full Braking Activation Parameter

Adaptive Safety Distance for Collision Avoidance Based on a Full Braking Activation Parameter

Multi-objective sand cat swarm optimization based on adaptive clustering for solving multimodal multi-objective optimization problems

Multimodal multi-objective optimization problems (MMOPs) represent a highly challenging class of complex problems, characterized by the presence of several Pareto solution sets in the decision space which map to the identical Pareto-optimal front. The goal of solving MMOPs is to find multiple distinct Pareto sets to sustain a balance between good convergence and diversification of populations. In this paper, a multi-objective sand cat swarm optimization algorithm (MOSCSO) is developed to address MMOPs. In the MOSCSO algorithm, an adaptive clustering-based specific congestion distance technique is introduced to compute the level of crowdedness. This ensures an even distribution of individuals, avoiding excessive crowding in the local area. Subsequently, enhanced search-and-attack prey updating mechanisms are designed to effectively increase not only the exploration and exploitation capabilities of the algorithm but also to enhance the diversity of the swarm in both the decision space and the objective space. To verify the effectiveness of the proposed algorithm, the MOSCSO is applied to solve the CEC2019 complex multimodal benchmark function. The experimental outcomes illustrate that the proposed approach possesses excellent performance in searching for Pareto solutions compared with other algorithms. Meanwhile, the method is also employed to address the map-based distance minimization problem, which further validates the usefulness of the MOSCSO.

Adaptive circumferential distance location of the laser energy beam in the laser-assisted turning of Al/SiC metal matrix composites

Laser-assisted turning (LAT) involves locally heating a rotating workpiece using a focused laser beam before the removal of material. A key aspect in optimising productivity with laser-assisted turning is understanding the thermal relationship between laser heating, the improved material removal rate, and machinability. Consequently, in this paper, a thermal heating and laser-assisted turning finite element model and experiments were conducted to assess the machinability of an Al/SiCp MMC workpiece, considering the circumferential location of the laser beam from the cutting point. The results confirm that laser power and cutting velocity influence the temperature profile from the laser spot to the tool point and the heat-affected depth. Positioning the cutting tool closer to the laser spot effectively reduces the Von Mises stress during cutting at higher cutting temperatures. At the same time, the experiment indicates an increased risk of directly heating the tool, which can affect the integrity of the cutting tool. The work further reveals that at specified cutting velocities, lower specific cutting energy improves the tool condition and surface quality of the machined parts. Based on a range of material removal rates and laser-specific energy density, a new criterion for optimal laser-tool circumferential distance was determined. Establishing this distance can act as a guide for the laser-assisted turning of Al/SiCp metal matrix composites and potentially other materials.

A Review on the Impact of Transmission Line Compensation and RES Integration on Protection Schemes

South Africa is currently experiencing an energy crisis because of a mismatch between energy supply and demand. Increasing energy demand necessitates the adequate operation of generation and transmission facilities to maintain the reliability of the power system. Transmission line compensation is used to increase the ability to transfer power, thereby enhancing system stability, voltage regulation, and reactive power balance. Also, in recent years, the introduction of renewable energy sources (RES) has proven to be effective in supporting the grid by providing additional energy. As a result, the dynamics of power systems have changed, and many developing nations are adopting the integration of renewable energy into the grid to increase the aspect ratio of the energy availability factor. While both techniques contribute to the grid’s ability to meet energy demand, they frequently introduce technical challenges that affect the stability and protection of the systems. This paper provides a comprehensive review of the challenges introduced by transmission line compensation and the integration of renewable energy, as well as the various techniques proposed in the literature to address these issues. Different compensation techniques, including fault detection, classification, and location, for compensated and uncompensated transmission lines, including those connected to renewable energy sources, are reviewed. This paper then analyzes the adaptive distance protection schemes available in the literature to mitigate the impact of compensation/integration of RES into the grid. Based on the literature reviewed, it is essential for protection engineers to understand the dynamics introduced by network topology incorporating a combination of RES and heavily compensated transmission lines.

Machine learning enables electrical resistivity modeling of printed lines in aerosol jet 3D printing

Among various non-contact direct ink writing techniques, aerosol jet printing (AJP) stands out due to its distinct advantages, including a more adaptable working distance (2–5 mm) and higher resolution (~ 10 μm). These characteristics make AJP a promising technology for the precise customization of intricate electrical functional devices. However, complex interactions among the machine, process, and materials result in low controllability over the electrical performance of printed lines. This significantly affects the functionality of printed components, thereby limiting the broad applications of AJP. Therefore, a systematic machine learning approach that integrates experimental design, geometrical features extraction, and non-parametric modeling is proposed to achieve printing quality optimization and electrical resistivity prediction for the printed lines in AJP. Specifically, three classical convolutional neural networks (CNNs) architectures are compared for extracting representative features of printed lines, and an optimal operating window is identified to effectively discriminate better line morphology from inferior printed line patterns within the design space. Subsequently, three representative non-parametric machine learning techniques are employed for resistivity modeling. Following that, the modeling performances of the adopted machine learning methods were systematically compared based on four conventional evaluation metrics. Together, these aspects contribute to optimizing the printed line morphology, while simultaneously identifying the optimal resistivity model for accurate predictions in AJP.

RectanglingGAN: Deep rectangling for stitched image via image inpainting

The deep rectangling task aims to transform edge-irregular stitched images into standardised rectangular formats using deep learning. Existing deep rectangling solutions rely on mesh-based segmentation and deformation, which introduce global distortions detrimental to subsequent analysis and processing. Therefore, we propose RectanglingGAN to handle missing regions in a distortion-free manner via image inpainting. Unlike generic inpainting models, RectanglingGAN focuses on preserving the quality of edge regions. In particular, we present an adaptive distance transform module to improve the attention of the feature maps to the mask boundaries. The module dynamically selects the appropriate distance transformation scheme according to the image content. Moreover, we introduce the distance-weighted decaying reconstruction loss into the pixel-wise reconstruction, which introduces the spatial location information between the inpainting pixels and the mask boundaries by inverting the distance-transformed mask. By incorporating this loss, the model pays more attention to the quality of generation pixels far from the mask boundary. Extensive experiments validate the effectiveness of RectanglingGAN compared to state-of-the-art methods, highlighting its significant advantages in terms of both the quality and the fidelity of the edge region in generation images.

Actual problems of modern education in technical university

Relevance. This research review focuses on the critical issues within technical education, emphasizing the need for new educational strategies and techniques to enhance learning outcomes. Purpose. The primary goal of this review is to investigate the factors influencing vocational education, particularly in the context of technical universities, and to evaluate the impact of current educational practices. Methodology. An analytical review of existing scientific publications on technical education was conducted to gather data on the effectiveness of traditional teaching methods and the integration of information and communication technologies (ICT) in education. Results. The review revealed significant challenges, including the low motivation of students and the inadequate competence of lecturers who prefer traditional teaching methods. These issues have persisted in technical education for many years. Additionally, the study highlighted the deficiencies in the modern educational process at technical universities, particularly during the COVID-19 pandemic, which necessitated the development of adaptive distance education systems. Conclusions. The authors discuss the theoretical approaches to organizing the educational process in modern higher education institutions and propose practical recommendations for the administration of these institutions. These recommendations aim to improve teaching methods, including the implementation of adaptive learning in higher education, to address the identified shortcomings and enhance the quality of technical education. Keywords: technical education; vocational training; institute of technology; engineering

Research on Decomposition and Offloading Strategies for Complex Divisible Computing Tasks in Computing Power Networks

With the continuous emergence of intelligent network applications and complex tasks for mobile terminals, the traditional single computing model often fails to meet the greater requirements of computing and network technology, thus promoting the formation of a new computing power network architecture, of ‘cloud, edge and end’ three-level heterogeneous computing. For complex divisible computing tasks in the network, task decomposition and offloading help to realize a distributed execution of tasks, thus reducing the overall running time and improving the utilization of fragmented resources in the network. However, in the process of task decomposition and offloading, there are problems, such as there only being a single method of task decomposition; that too large or too small decomposition granularity will lead to an increase in transmission delay; and the pursuit of low-delay and low-energy offloading requirements. Based on this, a complex divisible computing task decomposition and offloading scheme is proposed. Firstly, the computational task is decomposed into multiple task elements based on code partitioning, and then a density-peak-clustering algorithm with an improved adaptive truncation distance and clustering center (ATDCC-DPC) is proposed to cluster the task elements into subtasks based on the task elements themselves and the dependencies between the task elements. Secondly, taking the subtasks as the offloading objects, the improved Double Deep Q-Network subtask offloading algorithm (ISO-DDQN) is proposed to find the optimal offloading scheme that minimizes the delay and energy consumption. Finally, the proposed algorithms are verified by simulation experiments, and the scheme in this paper can effectively reduce the task delay and energy consumption and improve the service experience.

Active gas camera mass flow quantification (qOGI): Application in a biogas plant and comparison to state-of-the-art gas cams.

Gas cameras are primarily used to detect gas leaks, but their use has been increasingly extended to mass flow quantification (qOGI). We employ the previously published active illuminated gas camera [Bergau etal. "Real-time active-gas imaging of small gas leaks," J. Sens. Sens. Syst. 12, 61-68 (2023) and Bergau etal. "Flow rate quantification of small methane leaks using laser spectroscopy and deep learning," Process Saf. Environ. Prot. 182, 752-759 (2024)] in a real-world application for quantification, enhancing the camera with two new features: sensitivity adaptation and camera-gas distance detection. This technology was applied to a gas leak found in the pressure swing adsorption room of a biogas plant in Germany. We compare its performance with state-of-the-art quantification gas cameras (qOGI), such as Sensia Mileva 33. Such a comparison between active and passive gas cameras is possible for the first time due to the introduced sensitivity tuning. Additionally, we enclosed the gas leak and measure the methane concentration with a flame ionization detector, providing a gold standard for comparison. Our findings revealed relative offsets to our gold standard of -57% and +319% for the DAS-camera and the Sensia, respectively, suggesting that the accuracy of mass flow quantification could be improved through the use of active gas cameras.

Predicting species invasiveness with genomic data: Is genomic offset related to establishment probability?

Predicting the risk of establishment and spread of populations outside their native range represents a major challenge in evolutionary biology. Various methods have recently been developed to estimate population (mal)adaptation to a new environment with genomic data via so-called Genomic Offset (GO) statistics. These approaches are particularly promising for studying invasive species but have still rarely been used in this context. Here, we evaluated the relationship between GO and the establishment probability of a population in a new environment using both in silico and empirical data. First, we designed invasion simulations to evaluate the ability to predict establishment probability of two GO computation methods (Geometric GO and Gradient Forest) under several conditions. Additionally, we aimed to evaluate the interpretability of absolute Geometric GO values, which theoretically represent the adaptive genetic distance between populations from distinct environments. Second, utilizing public empirical data from the crop pest species Bactrocera tryoni, a fruit fly native from Northern Australia, we computed GO between "source" populations and a diverse range of locations within invaded areas. This practical application of GO within the context of a biological invasion underscores its potential in providing insights and guiding recommendations for future invasion risk assessment. Overall, our results suggest that GO statistics represent good predictors of the establishment probability and may thus inform invasion risk, although the influence of several factors on prediction performance (e.g., propagule pressure or admixture) will need further investigation.

Integrated form-position measurement of large-aperture transparent elements based on stereoscopic phase measuring deflectometry

In the field of ultra-precision manufacturing and measurement, sub-aperture stitching is a widely employed technique for the measurement of complex optical components. Those influencing factors like system errors and numerical bias introduce notable stitching errors in the overlapped areas between sub-apertures, consequently degrading measurement accuracy. In addition, the surfaces forms, refractive indices, and positions are difficult to be specified simultaneously. In this paper, an integrated measurement method based on the stereo deflectometry is proposed, which can measure the surface form, refractive index, and relative position of large-aperture transparent components together. This method utilizes a Gaussian process regression model to decouple and predict the refractive index and relative positions of the upper and lower surfaces. Then, a robust sub-aperture stitching technique with an adaptive distance function is employed to correct the positioning errors of sub-apertures. The feasibility and effectiveness of this method are demonstrated. The final stitched surface results exhibit a measurement error of 320 nm and a thickness deviation of 28 μm.

Interpretable metric learning in comparative metagenomics: The adaptive Haar-like distance.

Random forests have emerged as a promising tool in comparative metagenomics because they can predict environmental characteristics based on microbial composition in datasets where β-diversity metrics fall short of revealing meaningful relationships between samples. Nevertheless, despite this efficacy, they lack biological insight in tandem with their predictions, potentially hindering scientific advancement. To overcome this limitation, we leverage a geometric characterization of random forests to introduce a data-driven phylogenetic β-diversity metric, the adaptive Haar-like distance. This new metric assigns a weight to each internal node (i.e., split or bifurcation) of a reference phylogeny, indicating the relative importance of that node in discerning environmental samples based on their microbial composition. Alongside this, a weighted nearest-neighbors classifier, constructed using the adaptive metric, can be used as a proxy for the random forest while maintaining accuracy on par with that of the original forest and another state-of-the-art classifier, CoDaCoRe. As shown in datasets from diverse microbial environments, however, the new metric and classifier significantly enhance the biological interpretability and visualization of high-dimensional metagenomic samples.