Search Results (963)

Deep learning models for atmospheric pattern recognition require spatially consistent training labels that align precisely with input meteorological fields. This study introduces an automatic cold front detection method using the ERA5 reanalysis dataset from the European Centre for Medium-Range Weather Forecasts (ECMWF) at 850 hPa, specifically designed to generate physically consistent labels for machine learning applications. The approach combines the Thermal Front Parameter (TFP) with temperature advection (AdvT), applying optimized thresholds (TFP < 5 × 10⁻¹¹ K m⁻²; AdvT < −1 × 10⁻⁴ K s⁻¹), morphological filtering, and polynomial smoothing. Comparison against 1426 manual charts from 2009 revealed systematic spatial displacement, with mean offsets of ~502 km. Although pixel-level overlap was low, with Intersection over Union (IoU) = 0.013 and Dice coefficient (Dice) = 0.034, spatial concordance exceeded 99%, confirming both methods identify the same synoptic systems. The automatic method detects 58% more fronts over the South Atlantic and 44% fewer over the Andes compared to manual charts. Seasonal variability shows maximum activity in austral winter (31.3%) and minimum in summer (20.1%). This is the first automatic front detection system calibrated for South America that maintains direct correspondence between training labels and reanalysis input fields, addressing the spatial misalignment problem that limits deep learning applications in atmospheric sciences. Full article

Coating degradation monitoring is increasingly important in offshore industries, where protective layers ensure corrosion prevention and structural integrity. In this context, coating thickness estimation provides critical information. The ultrasound pulse-echo technique is widely used for non-destructive testing (NDT), but closely spaced acoustic interfaces often produce overlapping echoes, which complicates detection and accurate isolation of each layer’s thickness. In this study, analysis of the pulse-echo signal from a coated sample has shown that the front-coating reflection affects each main backwall echo differently; by comparing two consecutive backwall echoes, we can cancel the acquisition system’s impulse response and isolate the propagation path-related information between the echoes. This work introduces an ultrasound echo-based methodology for estimating coating thickness by first obtaining the impulse response of the test medium (reflectivity sequence) through a deconvolution model, developed using two consecutive backwall echoes. This is followed by an enhanced detection of coating layer thickness in the reflectivity function using a 1D convolutional neural network (1D-CNN) trained with synthetic signals obtained from finite-difference time-domain (FDTD) simulations with k-Wave MATLAB toolbox (v1.4.0). The proposed approach estimates the front-side coating thickness in steel samples coated on both sides, with coating layers ranging from $60\mathsf{\mu }$m to $740\mathsf{\mu }$m applied over 5 mm substrates and under varying coating and steel properties. The minimum detectable thickness corresponds to approximately $\lambda /5$ for an 8 MHz ultrasonic transducer. On synthetic signals, where the true coating thickness and speed of sound are known, the model achieves an accuracy of approximately $8\mathsf{\mu }$m. These findings highlight the strong potential of the model for reliably monitoring relative thickness changes across a wide range of coatings in real samples. Full article

This paper proposes a multi-sensor data-fusion-based method for real-scene 3D reconstruction and digital twin visualization of coal mine tunnels, aiming to address issues such as low accuracy in non-photorealistic modeling and difficulties in feature object recognition during traditional coal mine digitization processes. The research employs cubemap-based mapping technology to project acquired real-time tunnel images onto six faces of a cube, combined with navigation information, pose data, and synchronously acquired point cloud data to achieve spatial alignment and data fusion. On this basis, inner/outer corner detection algorithms are utilized for precise image segmentation, and a point cloud region growing algorithm integrated with information entropy optimization is proposed to realize complete recognition and segmentation of tunnel planes (e.g., roof, floor, left/right sidewalls) and high-curvature feature objects (e.g., ventilation ducts). Furthermore, geometric dimensions extracted from segmentation results are used to construct 3D models, and real-scene images are mapped onto model surfaces via UV (U and V axes of texture coordinate) texture mapping technology, generating digital twin models with authentic texture details. Experimental validation demonstrates that the method performs excellently in both simulated and real coal mine environments, with models capable of faithfully reproducing tunnel spatial layouts and detailed features while supporting multi-view visualization (e.g., bottom view, left/right rotated views, front view). This approach provides efficient and precise technical support for digital twin construction, fine-grained structural modeling, and safety monitoring of coal mine tunnels, significantly enhancing the accuracy and practicality of photorealistic 3D modeling in intelligent mining applications. Full article

A compact electrochemical sensor module for pH detection was developed for potential integration into specialized devices used for live cell or tissue incubation, for applications in highly parallelized cell culture analysis, by incorporating Organ-on-Chip devices. This research focuses on the deposition, structural and chemical analysis, and functional characterization of different titanium-oxide layers with various compositions as potentially sensitive materials for pH sensing applications. The titanium-oxide layers were deposited using vacuum sputtering and atomic layer deposition at 100 °C and 300 °C, respectively. Transmission electron microscopy and X-ray photoelectron spectroscopy were utilized to determine the specific composition and structure of different titanium-oxide layers. These TiO_x-functionalized electrodes were connected to the application-specific analog front-end chip of the low-power readout circuit for precise evaluation. The pH sensitivity of the differently modified electrodes, employing various TiO_x materials, was evaluated using pH calibration solutions ranging from pH 6 to 8. Among the various deposition solutions, such as sputtering or high-temperature atomic layer deposition, the TiO_x layer deposited using low-temperature atomic layer deposition proved more suitable for pH sensing applications, with a sensitivity of 54.8–56.7 mV/pH, which closely approximates the Nernstian response. Full article

Crack monitoring in concrete structures is essential to maintaining structural integrity. Therefore, this paper proposes a mobile ground robot equipped with a 2-DoF manipulator and stereo vision sensors for autonomous crack monitoring and mapping. To facilitate crack detection over large areas, a 2-DoF motorized manipulator providing linear and rotational motions, with a stereo vision sensor mounted on the end effector, was deployed. In combination with a manual rotation plate, this configuration enhances accessibility and expands the field of view for crack monitoring. Another stereo vision sensor, mounted at the front of the robot, was used to acquire point cloud data of the surrounding environment, enabling tasks such as SLAM (simultaneous localization and mapping), path planning and following, and obstacle avoidance. Cracks are detected and segmented using the deep learning algorithms YOLO (You Only Look Once) v6-s and SFNet (Semantic Flow Network), respectively. To enhance the performance of crack segmentation, synthetic image generation and preprocessing techniques, including cropping and scaling, were applied. The dimensions of cracks are calculated using point clouds filtered with the median absolute deviation method. To validate the performance of the proposed crack-monitoring and mapping method with the robot system, indoor experimental tests were performed. The experimental results confirmed that, in cases of divided imaging, the crack propagation direction was predicted, enabling robotic manipulation and division-point calculation. Subsequently, total crack length and width were calculated by combining reconstructed 3D point clouds from multiple frames, with a maximum relative error of 1%. Full article

Vision is a critical component of daily life, and its loss significantly hinders an individual’s ability to navigate, particularly when using public transportation systems. To address this challenge, this paper introduces a novel approach for accurately identifying bus route numbers and destinations, designed to assist visually impaired individuals in navigating urban transit networks. Our system integrates object detection, image enhancement, and Optical Character Recognition (OCR) technologies to achieve reliable and precise recognition of bus information. We employ a custom-trained You Only Look Once version 8 (YOLOv8) model to isolate the front portion of buses as the region of interest (ROI), effectively eliminating irrelevant text and advertisements that often lead to errors. To further enhance accuracy, we utilize the Enhanced Super-Resolution Generative Adversarial Network (ESRGAN) to improve image resolution, significantly boosting the confidence of the OCR process. Additionally, a post-processing step involving a pre-defined list of bus routes and the Levenshtein algorithm corrects potential errors in text recognition, ensuring reliable identification of bus numbers and destinations. Tested on a dataset of 120 images featuring diverse bus routes and challenging conditions such as poor lighting, reflections, and motion blur, our system achieved an accuracy rate of 95%. This performance surpasses existing methods and demonstrates the system’s potential for real-world application. By providing a robust and adaptable solution, our work aims to enhance public transit accessibility, empowering visually impaired individuals to navigate cities with greater independence and confidence. Full article

Background/Objectives: Adnexal masses are commonly encountered in the routine practice of gynecologists, and transvaginal ultrasonography is the preferred imaging modality for assessing the masses in size and complexity. There has been a notable lack of focus on comparative studies concerning benign adnexal tumors. This study aimed to define and compare the specific morphological and vascular characteristics of ovarian mature cystic teratomas (MCTs) and endometriomas using transvaginal ultrasound and Doppler analysis. Methods: This retrospective analysis included 93 patients who underwent surgical intervention for benign adnexal masses at the Obstetrics and Gynecology Clinic Narodni Front from 1 January 2020 to 1 January 2022. Morphological parameters included the appearance of tumors, the largest diameter, volume, capsule thickness, and the presence of fluid in the pouch of Douglas. Hemodynamic parameters included the localization and quantity of blood vessels within the mass, Resistance Index (RI), peak systolic velocity (Vmax), and end-diastolic velocity (Vmin) within detectable tumor vessels. Flow was also assessed in the uterine arteries, calculating the AURI (uterine artery RI) on both the tumor and contralateral sides. Results: There were 46 patients with ovarian mature cystic teratomas, as well as 46 patients with endometriomas; 1 patient presented with both tumors. There were significant differences in ultrasonographic morphological appearance between the two groups. MCTs most frequently presented as multilocular solid cysts (51.0%) or unilocular solid cysts with hyperechoic content (20.4%). Conversely, the majority of endometriomas were classified as unilocular cysts with ground-glass echogenicity (45.5%). A significant difference was identified in the RI of intracystic vessels and the RI of the ipsilateral uterine artery (AURI). Endometriomas presented elevated RI values (0.57 vs. 0.54, p = 0.04) and reduced AURI (0.81 vs. 0.83, p = 0.02) compared to teratomas. Conclusions: These findings confirm that specific morphological and Doppler parameters, particularly the RI and AURI, can assist in distinguishing between endometriomas and mature cystic teratomas. This suggests a potential role for Doppler analysis in improving diagnostic precision for common benign adnexal tumors in clinical practice. Full article

Heavy metal contamination poses significant environmental risks to groundwater and soil, necessitating efficient early-warning technologies for leakage detection. This study proposes a novel early-warning approach for heavy metal leakage using the self-potential (SP) method. A coupled numerical model integrating seepage, ion diffusion, and electric potential fields was developed within the COMSOL Multiphysics platform in order to elucidate the dynamic response mechanism of SP signals to advancing seepage fronts. Key findings reveal that the SP signal responds 1.5 h earlier than the contaminant diffusion front (Case 1), providing a critical early-warning window. The leakage process exhibits a distinct bipolar SP anomaly pattern (negative upstream/positive downstream), with the most significant response observed at the downstream toe area. Consequently, an optimized monitoring strategy prioritizing downstream deployment is proposed and validated using a representative landfill model. This SP-based technology offers a promising solution for real-time environmental risk monitoring, particularly in ecologically sensitive zones. Full article

Low-level wind shear (LLWS) is a critical issue in aviation meteorology, posing serious risks to flight safety—especially at plateau airports with high elevation and complex terrain. This study investigates a convective wind shear event at Xining Airport on 29 May 2021. Multi-source observations—including the Doppler Wind Lidar (DWL), the Doppler weather radar (DWR), reanalysis datasets, and automated weather observation systems (AWOS)—were integrated to examine the event’s fine-scale structure and temporal evolution. High-resolution simulations were conducted using the Large Eddy Simulation (LES) framework within the Weather Research and Forecasting (WRF) model. Results indicate that the formation of this wind shear was jointly triggered by convective downdrafts and the gust front. A northwesterly flow with peak wind speeds of 18 m/s intruded eastward across the runway, generating multiple radial velocity couplets on the eastern side, closely associated with mesoscale convergence and divergence. A vertical shear layer developed around 700 m above ground level, and the critical wind shear during aircraft go-around was linked to two convergence zones east of the runway. The event lasted about 30 min, producing abrupt changes in wind direction and vertical velocity, potentially causing flight path deviation and landing offset. Analysis of horizontal, vertical, and glide-path wind fields reveals the spatiotemporal evolution of the wind shear and its impact on aviation safety. The WRF-LES accurately captured key features such as wind shifts, speed surges, and vertical disturbances, with strong agreement to observations. The integration of multi-source observations with WRF-LES improves the accuracy and timeliness of wind shear detection and warning, providing valuable scientific support for enhancing safety at plateau airports. Full article

A novel rolling scheme incorporating an inclined oval-caliber configuration is proposed to enhance plastic deformation mechanisms in the traditional oval–round rolling sequence. Finite Element Method (FEM) simulations were performed using DEFORM-3D to evaluate and optimize this new scheme across multiple objectives: maximizing average effective strain, minimizing strain non-uniformity (captured via the standard deviation of effective strain), and minimizing rolling force. Numerical modeling was conducted for calibration angles of γ = 0°, 25°, 35°, and 45°, from which Pareto-optimal solutions were identified based on classical non-dominance criteria. Pairwise 2D projections of the Pareto front enabled visualization of trade-offs and revealed γ = 35° as the Pareto knee-point, representing the most balanced compromise among high deformation intensity, increased uniformity, and reduced energy consumption. This optimal angle was further corroborated through a normalized weighted sum of the objective functions. The findings provide a validated reference for designing prototype deforming tools and support future experimental validation. Full article

In ultra-wideband (UWB) radio fuzes, the signal processing unit’s capability to rapidly and accurately extract target characteristics under battlefield conditions directly determines detonation precision and reliability. Escalating electronic warfare creates complex electromagnetic environments that compromise UWB fuze reliability through false alarms and missed detections. This study pioneers a novel signal processing architecture. The framework integrates: (1) fixed-parameter Least Mean Squares (LMS) front-end filtering for interference suppression; (2) One-Dimensional Convnlutional Neural Network (1D-CNN) recognition trained on One-Dimensional Conditional Generative Adversarial Network (1D-CGAN)-augmented datasets. Validated on test samples, the system achieves 0% false alarm/miss detection rates and 97.66% segment recognition accuracy—representing a 5.32% improvement over the baseline 1D-CNN model trained solely on original data. This breakthrough resolves energy-threshold detection’s critical vulnerability to deliberate jamming while establishing a new technical framework for UWB fuze operation in contested spectra. Full article

We live in a time dominated by interconnected networks surrounding us on all fronts. The emergence of social media platforms has driven the expansion of social networks, facilitating fast communication worldwide. Responses to content shared on these platforms can be seen as a propagation process, where information spreads through social networks. Analyzing propagation graphs presents a significant challenge in identifying sources, which is crucial in various fields. This includes detecting the origins of disinformation, identifying patient zero in an epidemic, and tracing the initial sources of viral trends or malware. Numerous studies have attempted to identify these sources using methods similar to centrality measures which assign a value indicating the likelihood of being a source. While centrality measures are a popular topic, with many new measures introduced each year, only a few have been explored in the context of source identification. This article explores a wide range of centrality measures in the context of source identification. The results help identify the most effective measures and pave the way for the development of more efficient detection techniques. Additionally, an analysis was conducted considering multiple hops in the propagation network, providing deeper insights into the impact of extended neighborhood structures on detection performance. Full article

Background and Clinical Significance: Purtscher-like retinopathy is a rare occlusive microangiopathy that causes sudden vision loss of varying severity. It presents with diverse retinal findings, such as cotton-wool spots, haemorrhages, and optic disc and macular edema, among others. A key characteristic is the absence of trauma. This condition has been observed in patients with acute pancreatitis, renal failure, preeclampsia, HELLP syndrome, childbirth, and other systemic disorders. Case Presentation: A 35-year-old male presented with complaints of seeing spots in front of both eyes, with a duration of ten days following the initiation of treatment for acute alcoholic pancreatitis. On examination, best-corrected visual acuity (BCVA) in both eyes was 5/6. Fundus examination revealed multiple cotton-wool spots and haemorrhages located in the posterior pole and around the optic disc, more pronounced in the left eye, where the optic disc had blurred margins and the macular reflex was absent. Perimetry showed paracentral scotomas, and optical coherence tomography (OCT) revealed thickening and disruption of the inner retinal layers in the papillomacular region of both eyes. Fundus fluorescein angiography demonstrated adequate perfusion of the vascular network, with hypofluorescent areas in the arteriovenous phase, peripapillary and in the papillomacular zone, due to masking by cotton-wool spots and haemorrhages. Treatment included systemic antiplatelet agents, anticoagulants, and vitamins, along with topical non-steroidal anti-inflammatory drugs. Two months after the initial presentation visual acuity improved to 6/6 in both eyes. Follow-up OCT scans showed atrophy of the inner retinal layers corresponding to the previous cotton-wool spot and the areas of reduced light sensitivity on perimetry had decreased in size. Conclusions: Acute pancreatitis is the most common systemic condition associated with the development of Purtscher-like retinopathy. Timely diagnosis and management of the underlying systemic disease are essential for preventing ocular complications. Ophthalmological evaluation is necessary in patients with acute pancreatitis who present with visual symptoms in order to detect this often-overlooked rare condition. Full article

Automated Valet Parking (AVP) systems require high-precision positioning, especially in indoor environments where Global Positioning System (GPS) is unavailable. Existing methods, which use markers installed on parking lot walls or ceilings, often encounter difficulties due to marker detection failures caused by complex parking behaviors, such as infrastructure constraints or perpendicular parking. This study proposes an optimized indoor positioning system for AVP using fiducial markers recognized by front and rear vehicle cameras. To enhance accuracy and robustness, an Extended Kalman Filter (EKF) fuses vehicle kinematic data with marker pose information. Critically, to address the issue of marker occlusion by the front camera during reverse parking, a novel camera switching algorithm employing a hysteresis pattern based on vehicle position, heading, and motion direction is introduced. This ensures continuous marker visibility and stable positioning during parking maneuvers. The system’s effectiveness was validated through simulations and extensive real-vehicle experiments in a real parking space. Results demonstrate that the EKF significantly reduces positioning errors compared to kinematic prediction alone, particularly during curved driving. Furthermore, the proposed camera switching algorithm successfully overcomes the limitations of a front-only camera system, significantly improving positioning accuracy (e.g., reducing RMS error by up to 25.0% in X and 17.6% in Y during parking) and eliminating instability observed with simpler switching logic. This research contributes a cost-effective and reliable positioning solution, advancing the feasibility of AVP systems in challenging indoor environments. Full article

Bridge Structural Health Monitoring (BSHM) is vital for assessing structural integrity and operational safety. Traditional wired systems are limited by high installation costs and complexity, while existing wireless systems still face issues with cost, synchronization, and reliability. Moreover, cloud-based methods for extreme event detection struggle to meet real-time and bandwidth constraints in edge environments. To address these challenges, this study proposes a lightweight wireless BSHM system based on edge computing, enabling local data acquisition and real-time intelligent detection of extreme events. The system consists of wireless sensor nodes for front-end acceleration data collection and an intelligent hub for data storage, visualization, and earthquake recognition. Acceleration data are converted into time–frequency images to train a MobileNetV2-based model. With model quantization and Neural Processing Unit (NPU) acceleration, efficient on-device inference is achieved. Experiments on a laboratory steel bridge verify the system’s high acquisition accuracy, precise clock synchronization, and strong anti-interference performance. Compared with inference on a general-purpose ARM CPU running the unquantized model, the quantized model deployed on the NPU achieves a 26× speedup in inference, a 35% reduction in power consumption, and less than 1% accuracy loss. This solution provides a cost-effective, reliable BSHM framework for small-to-medium-sized bridges, offering local intelligence and rapid response with strong potential for real-world applications. Full article