Search Results (274)

With the increasing integration of renewable energy sources (RESs) into power systems, batteries are playing a critical role in ensuring grid reliability and flexibility. Among them, vanadium redox flow batteries (VRFBs) have emerged as a promising solution for large-scale storage due to their long cycle life, scalability, and deep discharge capability. However, achieving optimal control and system-level integration of VRFBs requires accurate, real-time modeling and parameter estimation, challenging tasks given the multi-physics nature and time-varying dynamics of such systems. This paper presents a lightweight physics-informed neural network (PINN) framework tailored for VRFBs, which directly embeds the discrete-time state-space dynamics into the network architecture. The model simultaneously predicts terminal voltage and estimates five discrete-time physical parameters associated with RC dynamics and internal resistance, while avoiding hidden layers to enhance interpretability and computational efficiency. The resulting PINN model is integrated into a modulated model predictive control (MMPC) scheme for a dual-stage DC-AC converter interfacing the VRFB with low-voltage AC grids. Simulation and hardware-in-the-loop results demonstrate that adaptive tuning of the PINN-estimated parameters enables precise tracking of battery parameter variations, thereby improving the robustness and performance of the MMPC controller under varying operating conditions. Full article

With the exponential growth of textual data, traditional topic modeling methods based on static analysis demonstrate limited effectiveness in tracking the dynamics of thematic content. This research aims to develop a method for quantifying the dynamics of topics within text corpora using a thematic signal (TS) function that accounts for temporal changes and semantic relationships. The proposed method combines associative tokens with original lexical units to reduce thematic entropy and information noise. Approaches employed include topic modeling (LDA), vector representations of texts (TF-IDF, Word2Vec), and time series analysis. The method was tested on a corpus of news texts (5000 documents). Results demonstrated robust identification of semantically meaningful thematic clusters. An inverse relationship was observed between the level of thematic significance and semantic diversity, confirming a reduction in entropy using the proposed method. This approach allows for quantifying topic dynamics, filtering noise, and determining the optimal number of clusters. Future applications include analyzing multilingual data and integration with neural network models. The method shows potential for monitoring information flows and predicting thematic trends. Full article

This paper reviews the variability of passenger service time (PST) at the platform–train interface (PTI), a critical performance indicator in metro systems shaped by the infrastructure design, affecting passenger behavior and accessibility. Despite its operational importance, PST remains underexplored in relation to crowd management strategies. This review synthesizes findings from empirical and experimental research to clarify the main factors influencing PST and their implications for platform-level interventions. Key contributors to PST variability include door width, gap dimensions, crowd density, and user characteristics such as mobility impairments. Design elements—such as platform edge doors, yellow safety lines, and vertical handrails—affect flow efficiency and spatial dynamics during boarding and alighting. Advanced tracking and simulation tools (e.g., PeTrack and YOLO-based systems) are identified as essential for evaluating pedestrian behavior and supporting Level of Service (LOS) analysis. To complement traditional LOS metrics, the paper introduces Level of Interaction (LOI) and a multidimensional LOS framework that captures spatial conflicts and user interaction zones. Control strategies such as platform signage, seating arrangements, and visual cues are also reviewed, with experimental evidence showing that targeted design interventions can reduce PST by up to 35%. The review highlights a persistent gap between academic knowledge and practical implementation. It calls for greater integration of empirical evidence into policy, infrastructure standards, and operational contracts. Ultimately, it advocates for human-centered, data-informed approaches to PTI planning that enhance efficiency, inclusivity, and resilience in high-demand transit environments. Full article

In water-scarce regions such as Jordan, accurate tracking of water flows is critical for informed water management. This study applied the Water Accounting Plus (WA+) framework using open-source remote sensing data from the FAO WaPOR portal to develop agricultural water accounting (AWA) for the Amman–Zarqa Basin (AZB) during 2014–2022. Inflows, outflows, and water consumption were quantified using WaPOR and other open datasets. The results showed a strong correlation between WaPOR precipitation (P) and rainfall station data, while comparisons with other remote sensing sources were weaker. WaPOR evapotranspiration (ET) values were generally lower than those from alternative datasets. To improve classification accuracy, a correction of the WaPOR-derived land cover map was performed. The revised map achieved a producer’s accuracy of 15.9% and a user’s accuracy of 86.6% for irrigated areas. Additionally, ET values over irrigated zones were adjusted, resulting in a fivefold improvement in estimates. These corrections significantly enhanced the reliability of key AWA indicators such as basin closure, ET fraction, and managed fraction. The findings demonstrate that the accuracy of P and ET data strongly affects AWA outputs, particularly the estimation of percolation and beneficial water use. Therefore, calibrating remote sensing data is essential to ensure reliable water accounting, especially in agricultural settings where data uncertainty can lead to misleading conclusions. This study recommends the use of open-source datasets such as WaPOR—combined with field validation and calibration—to improve agricultural water resource assessments and support decision making at basin and national levels. Full article

Accurate real-time tracking of forest fires using UAV platforms is crucial for timely early warning, reliable spread prediction, and effective autonomous suppression. Existing detection-based multi-object tracking methods face challenges in accurately associating targets and maintaining smooth tracking trajectories in complex forest environments. These difficulties stem from the highly nonlinear movement of flames relative to the observing UAV and the lack of robust fire-specific feature modeling. To address these challenges, we introduce AO-OCSORT, an association-optimized observation-centric tracking framework designed to enhance robustness in dynamic fire scenarios. AO-OCSORT builds on the YOLOX detector. To associate detection results across frames and form smooth trajectories, we propose a temporal–physical similarity metric that utilizes temporal information from the short-term motion of targets and incorporates physical flame characteristics derived from optical flow and contours. Subsequently, scene classification and low-score filtering are employed to develop a hierarchical association strategy, reducing the impact of false detections and interfering objects. Additionally, a virtual trajectory generation module is proposed, employing a kinematic model to maintain trajectory continuity during flame occlusion. Locally evaluated on the 1080P-resolution FireMOT UAV wildfire dataset, AO-OCSORT achieves a 5.4% improvement in MOTA over advanced baselines at 28.1 FPS, meeting real-time requirements. This improvement enhances the reliability of fire front localization, which is crucial for forest fire management. Furthermore, AO-OCSORT demonstrates strong generalization, achieving 41.4% MOTA on VisDrone, 80.9% on MOT17, and 92.2% MOTA on DanceTrack. Full article

To correspond to the advancement of technology, programming has become an indispensable course in university curricula. However, students easily become confused by the rules governing program execution or by complex logical structures. Mastering program structure and logic often is a significant challenge for beginners, especially. Despite the availability of information on programming on various websites and tools, including generative artificial intelligence (AI), there is still a gap between conceptual understanding and practical application for beginners. They overlook important implementation details or struggle to grasp the flow of a program, making the mastery of program logic a persistent challenge. To address these issues, we have developed a system that dynamically generates process architecture diagrams. Users upload their code, and the system produces corresponding diagrams that decompose and execute the code line by line. Its visual representation allows users to observe the program’s execution and aids them in comprehending the sequence and operational flow of the code. By understanding the structure and logic of the program intuitively, this system supplements traditional teaching methods and AI-assisted question-and-answer tools. The experimental results demonstrated that students found the system helpful to track their learning progress (87%) and improved their understanding of program code (81%). Additionally, 84% of students reported that the system was easy to use, highlighting its user-friendliness. In terms of student interest, 83% of students agreed that the interactive elements made learning more engaging, indicating that the system positively contributed to dynamic and enjoyable learning. However, 63% of students reported an improvement in coding and were influenced by the complexity of the programming tasks assigned. Despite this, the overall satisfaction with the system developed in this study was high. Full article

In addition to architecture and infrastructure, urban outdoor advertising also shapes urban visual identity, serving as a prominent carrier of public information and visual stimuli. However, excessive or poorly designed advertisements disrupt the cityscape and contribute to visual pollution and cognitive overload. Leveraging computer-based eye tracking, this study examines the visual and cognitive effects of outdoor advertising designs within urban contexts. Key eye-tracking metrics, including total fixation duration, fixation count, time to first fixation, and first fixation duration, are measured to analyze the influence of various variables on visual attention and user experience, such as color contrast, text complexity, information hierarchy, and spatial layout. The findings reveal that high-contrast, text-heavy designs hinder visual flow and increase mental effort, while visually balanced layouts improve legibility and reduce cognitive burden. These results offer actionable insights for optimizing urban visual identity and enhancing the clarity, comfort, and coherence of outdoor advertising. By integrating perceptual data into urban design strategies, this research provides a data-driven approach to smarter, more human-centered advertising management and urban aesthetic governance. Full article

The generation of road interchange networks benefits various applications, such as vehicle navigation and intelligent transportation systems. Traditional methods often focus on common road structures but fail to fully utilize long-term trajectory continuity and flow information, leading to fragmented results and misidentification of overlapping roads as intersections. To address these limitations, we propose a forward and reverse tracking method for high-accuracy road interchange network generation. First, raw crowdsourced trajectory data is preprocessed by filtering out non-interchange trajectories and removing abnormal data based on both static and dynamic characteristics of the trajectories. Next, road subgraphs are extracted by identifying potential transition nodes, which are verified using directional and distribution information. Trajectory bifurcation is then performed at these nodes. Finally, a two-stage fusion process combines forward and reverse tracking results to produce a geometrically complete and topologically accurate road interchange network. Experiments using crowdsourced trajectory data from Shenzhen demonstrated highly accurate results, with 95.26% precision in geometric road network alignment and 90.06% accuracy in representing the connectivity of road interchange structures. Compared to existing methods, our approach enhanced accuracy in spatial alignment by 13.3% and improved the correctness of structural connections by 12.1%. The approach demonstrates strong performance across different types of interchanges, including cloverleaf, turbo, and trumpet interchanges. Full article

Aiming at the state estimation problem of nonlinear systems (NLSs), the traditional typical nonlinear filtering methods (e.g., Particle Filter, PF) have large errors in system state, resulting in low accuracy and high computational speed. To perfect the imperfections, a new Bayesian estimation method based on particle flow velocity (PFV-BEM) is proposed in this paper. Firstly, a symmetrical projection space based on the state information is selected, the basis function is determined by a set of Fourier series with symmetric properties, the state update is carried out according to the projection principle to calculate the prior information of the state, and select its particle points. Secondly, the particle flow velocity is defined, which describes the evolution process of random samples from the prior distribution to the posterior distribution. The posterior information of the state is calculated by solving the parameters related to the particle flow velocity. Finally, the estimated mean and standard deviation of the state are solved. Simulation experiments are carried out based on two instances of one-dimensional general nonlinear examples and multi-target motion tracking, The newly proposed algorithm is compared with the Particle Filter (PF), and the simulation results clearly indicate the feasibility of this novel Bayesian estimation algorithm. Full article

In multi-vehicle traffic scenarios, achieving accurate environmental perception and motion trajectory tracking through LiDAR–camera fusion is critical for downstream vehicle planning and control tasks. To address the challenges of cross-modal feature interaction in LiDAR–image fusion and the low recognition efficiency/positioning accuracy of traffic participants in dense traffic flows, this study proposes an attention-based 3D object detection network integrating point cloud and image features. The algorithm adaptively fuses LiDAR geometric features and camera semantic features through channel-wise attention weighting, enhancing multi-modal feature representation by dynamically prioritizing informative channels. A center point detection architecture is further employed to regress 3D bounding boxes in bird’s-eye-view space, effectively resolving orientation ambiguities caused by sparse point distributions. Experimental validation on the nuScenes dataset demonstrates the model’s robustness in complex scenarios, achieving a mean Average Precision (mAP) of 64.5% and a 12.2% improvement over baseline methods. Real-vehicle deployment further confirms the fusion module’s effectiveness in enhancing detection stability under dynamic traffic conditions. Full article

There are two types of noninvasive biomarkers of human embryo developmental potential: those based on a direct assessment of embryo morphology over time and those using spent media after embryo in vitro culture as source of information. Both are derived from previously acquired knowledge on different aspects of pre-implantation embryo development. These aspects include embryo morphology and kinetics, chromosomal ploidy status, metabolism, and embryonic gene transcription, translation, and expression. As to the direct assessment of morphology and kinetics, pertinent data can be obtained by analyzing sequential microscopic images of in vitro cultured embryos. Spent media can serve a source of genomic, metabolomic, transcriptomic and proteomic markers. Methods used in the early pioneering studies, such as microscopy, fluorescence in situ hybridization, autoradiography, electrophoresis and immunoblotting, or enzyme-linked immunosorbent assay, are too subjective, invasive, and/or time-consuming. As such, they are unsuitable for the current in vitro fertilization (IVF) practice, which needs objective, rapid, and noninvasive selection of the best embryo for uterine transfer or cryopreservation. This has been made possible by the use of high-throughput techniques such as time-lapse (for direct embryo evaluation), next-generation sequencing, quantitative real-time polymerase chain reaction, high-performance liquid chromatography, nanoparticle tracking analysis, flow cytometry, mass spectroscopy, Raman spectroscopy, near-infrared spectroscopy, and nuclear magnetic resonance spectroscopy (for spent culture media analysis). In this review, individual markers are presented systematically, with each marker’s history and current status, including available methodologies, strengths, and limitations, so as to make the essential information accessible to all health professionals, even those whose expertise in the matter is limited. Full article

In recent years, the realization of a society in which humans and robots coexist has become highly anticipated. As a result, robots are expected to exhibit versatility regardless of their operating environments, along with high responsiveness, to ensure safety and enable dynamic task execution. To meet these demands, we design a comprehensive system composed of two primary components: high-speed skeleton tracking and path planning. For tracking, we implement a high-speed skeleton tracking method that combines deep learning-based detection with optical flow-based motion extraction. In addition, we introduce a dynamic search area adjustment technique that focuses on the target joint to extract the desired motion more accurately. For path planning, we propose a high-speed, geometry-informed potential field model that addresses four key challenges: (P1) avoiding local minima, (P2) suppressing oscillations, (P3) ensuring adaptability to dynamic environments, and (P4) handling obstacles with arbitrary 3D shapes. We validated the effectiveness of our high-frequency feedback control and the proposed system through a series of simulations and real-world collision-free path planning experiments. Our high-speed skeleton tracking operates at 250 Hz, which is eight times faster than conventional deep learning-based methods, and our path planning method runs at over 10,000 Hz. The proposed system offers both versatility across different working environments and low latencies. Therefore, we hope that it will contribute to a foundational motion generation framework for human–robot collaboration (HRC), applicable to a wide range of downstream tasks while ensuring safety in dynamic environments. Full article

E-commerce live streaming attracts consumers by displaying product information and anchor introductions. However, the complexity and variety of interface information pose challenges in design, and research on live-streaming interface design remains limited. This study examines how patch design affects the customer experience in live-streaming rooms, considering different product types and virtual backgrounds. Based on the flow theory and the Stimulus–Organism–Response model, we conducted experiments simulating live-streaming scenarios and collected behavioral and eye-tracking data. Our results confirmed that cognitive load negatively mediates, while mental imagery and flow experience positively mediate, the relationship between patch design and consumer behavior. Additionally, the interaction between product type and virtual background proximity was revealed, with product type moderating the effect of cognitive load on purchase behavior. This study contributes to understanding the impact of live-streaming interface design on consumer experience and purchase behavior, providing design guidelines for online retailers and managerial insights for retail platforms. Full article

Dynamic weighing systems, an advanced technology for traffic management, are designed to measure the weight of moving vehicles without obstructing traffic flow. These systems play a critical role in monitoring freight vehicle overloading, collecting weight-based tolls, and assessing the structural health of roads and bridges. However, due to the complex road traffic environment in real-world applications of dynamic weighing systems, some vehicles cannot be accurately weighed, even though precise parameter calibration was conducted prior to the system’s official use. The variation in driving behaviors among different drivers contributes to this issue. When different types and sizes of vehicles pass through the dynamic weighing area simultaneously, changes in the vehicles’ motion states are the main factors affecting weighing accuracy. This study proposes an improved SSD vehicle detection model to address the high sensitivity to vehicle occlusion and frequent vehicle ID changes in current multi-target tracking methods. The goal is to reduce detection omissions caused by vehicle occlusion. Additionally, to obtain more stable trajectory and speed data, a Gaussian Smoothing Interpolation (GSI) method is introduced into the DeepSORT algorithm. The fusion of dynamic weighing data is used to analyze the impact of changes in vehicle size and motion states on weighing accuracy, followed by compensation and experimental validation. A compensation strategy is implemented to address the impact of speed fluctuations on the weighing accuracy of vehicles approximately 12.5 m in length. This is completed to verify the feasibility of the compensation method proposed in this paper, which is based on vehicle information. A dataset containing vehicle length, width, height, and speed fluctuation information in the dynamic weighing area is constructed, followed by an analysis of the key factors influencing dynamic weighing accuracy. Finally, the improved dynamic weighing model for extracting vehicle motion state information is validated using a real dataset. The results demonstrate that the model can accurately detect vehicle targets in video footage and shows strong robustness under varying road illumination conditions. Full article

In highway scenarios, factors such as high-speed vehicle movement, lighting conditions, and positional changes significantly affect the quality of trajectories in multi-object tracking. This, in turn, impacts the trajectory clustering process within the multi-target multi-camera tracking (MTMCT) system. To address this challenge, we present the weak-cue mixed similarity matrix and boundary expansion clustering (WCBE) MTMCT system. First, the weak-cue mixed similarity matrix (WCMSM) enhances the original trajectory features by incorporating weak cues. Then, considering the practical scene and incorporating richer information, the boundary expansion clustering (BEC) algorithm improves trajectory clustering performance by taking the distribution of trajectory observation points into account. Finally, to validate the effectiveness of our proposed method, we conduct experiments on both the Highway Surveillance Traffic (HST) dataset developed by our team and the public CityFlow dataset. The results demonstrate promising outcomes, validating the efficacy of our approach. Full article