Search Results (1,056)

Accurate landslide segmentation from remote sensing imagery is important for geohazard assessment and emergency response, yet it remains challenging because landslide regions are often spectrally confused with bare soil, riverbeds, shadows, and disturbed surfaces while also suffering from severe foreground–background imbalance. To address these issues, we propose an Efficient Spectrally Guided Hierarchical Fusion Network (SGH-Net) for multi-modal landslide segmentation. Instead of directly concatenating heterogeneous inputs at the image level, SGH-Net adopts an asymmetric encoder–decoder design in which a pretrained EfficientNet-B4 extracts RGB features, while two lightweight guidance encoders capture complementary multispectral band and DEM-derived terrain cues. These guidance features are progressively injected into the RGB backbone through multi-stage Guided Attention Blocks, enabling selective feature recalibration and reducing cross-modal interference. In addition, a hybrid Dice–Focal loss is used to alleviate class imbalance. Experiments on the Landslide4Sense dataset show that SGH-Net achieves the best overall performance among the compared methods under the adopted evaluation protocol, reaching 81.15% IoU and a 77.86% F1-score. Compared with representative multi-modal baselines, the proposed method delivers more accurate boundary delineation and fewer false alarms while maintaining favorable model complexity. These results indicate that modality-guided hierarchical fusion is an effective and efficient strategy for multi-modal landslide segmentation. Full article

Coral reef ecosystems are declining rapidly due to climate change, disease, and anthropogenic stressors, driving the expansion of land-based coral propagation for reef restoration. A major bottleneck in these efforts is the manual measurement of coral recruit tissue area from microscopy images, which requires 2–7 min per image and limits scalability. We present a hierarchical deep learning pipeline that automates this measurement by integrating YOLO-based detection with Segment Anything Model (SAM) segmentation. YOLO localizes recruits and classifies them by developmental stage; stage-specific fine-tuned SAM models then segment live tissue using bounding box and background point prompts to suppress segmentation leakage and improve boundary precision. Surface area is computed directly from the segmented masks using pixel size extracted from image metadata. The pipeline reduces processing time to approximately 3–5 s per image—a 24–140× speedup over manual tracing. Evaluated on 3668 microscopy images from two national coral research facilities, the system achieves a mean IoU exceeding 95% and an auto-acceptance rate (AAR) of 71.51%, where predicted-to-ground-truth area ratios fall within a ±5% tolerance of expert annotation, substantially reducing manual workload while maintaining measurement reliability across species, developmental stages, and imaging conditions. This workflow addresses a critical bottleneck in restoration research and demonstrates the broader applicability of AI-based image analysis in marine ecology. Full article

Reliable textile recycling requires automated unfolding to expose hidden hard components such as zippers, buttons, and metal fasteners, which otherwise risk damaging machinery and compromising downstream processes. This paper presents the design and implementation of an automated textile unfolding system based on a dual-arm robotic manipulation framework. The system uses two Interbotix WidowX 250s 6-DoF robotic arms and an Intel RealSense L515 LiDAR camera for visual perception. The unfolding process consists of three stages: initial dual-arm stretching to reduce major folds, refinement through a second stretch targeting the lower region, and a machine-learning stage that employs a YOLOv11 framework trained on depth-encoded textile images, followed by a depth-gradient-based estimator for fold direction. The system applies an extremity-based grasping strategy that selects leftmost and rightmost textile points from a custom error-corrected depth map, enabling robust grasp point selection, and a fold direction estimation method based on depth gradients around the detected fold. The most confident fold region is selected, an unfolding direction is determined using depth ranking, and the textile is manipulated until a flat state is confirmed through depth uniformity. Experiments show that depth correction significantly reduces spatial error in the robot frame, while segmentation and extremity detection achieve high accuracy across varied fold configurations, and the YOLOv11n-based model reaches 98.8% classification accuracy, while fold direction is estimated correctly in 87% of test cases. By enabling robust, largely autonomous textile unfolding, the system demonstrates a practical approach that could support safer and more efficient automated textile recycling workflows. Full article

This study proposes a new deep learning-based approach for detecting pitting corrosion on stainless-steel sheet pile surfaces in drainage channels. Conventional ultrasonic thickness measurement methods cannot detect microscopic pitting corrosion that occurs before measurable thickness reduction. The research develops an automated detection system using visible images captured with smartphone cameras and U-net semantic segmentation. Two stainless steel grades (SUS410 and SUS430) were exposed for 5 years to a brackish water environment and analyzed. The deep learning approach achieved F1-scores of 0.831 (SUS410) and 0.808 (SUS430), outperforming binary thresholding methods (F1-scores: 0.407 and 0.329, respectively). Data augmentation improved performance by 1–3 percentage points. The method enabled non-destructive, quantitative assessment of early-stage corrosion using readily available equipment, providing a practical tool for infrastructure maintenance and long-term durability evaluation. Full article

The global incidence of skin cancer is rising, making it an increasingly critical public health issue. Malignant skin tumors such as melanoma originate from pathological alterations in skin cells, and their accurate early-stage segmentation is crucial for quantitative analysis, early diagnosis, and effective treatment. However, achieving precise and efficient segmentation remains a major challenge, as existing methods often struggle to capture complex lesion characteristics. To address this challenge, we propose a novel deep learning framework that integrates the PVT v2 backbone with two key modules: the Spatial-Aware Feature Enhancement (SAFE) module and the Multiscale Dual Cross-attention Fusion (MDCF) module. The SAFE module enhances multi-scale encoder features through a dual-branch architecture, which adaptively extracts offset information to integrate fine-grained shallow details with deep semantic information, thereby bridging the feature gap across network depths. The MDCF module establishes bidirectional cross-attention between decoder and encoder features, followed by multi-scale deformable convolutions that capture lesion boundaries and small fragments across heterogeneous receptive fields, thereby enriching semantic details while suppressing background interference. The proposed model was evaluated on two public benchmark datasets (ISIC 2016 and ISIC 2018), achieving Intersection over Union (IoU) scores of 87.33% and 83.67%, respectively. These results demonstrate superior performance compared to current state-of-the-art methods and indicate that our framework significantly enhances skin lesion image analysis, offering a promising tool for improving early detection of skin cancer. Full article

The increasing penetration of renewable energy is driving the use of grid-forming energy storage (GFM-ES) for black start in pure renewable power grids. However, practical implementation is challenged by three coupled problems: transient voltage overshoot during bus energization, imbalance of state of charge (SOC) among distributed storage units during islanded operation, and synchronization shocks during grid reconnection. This paper proposes a coordinated multi-stage black-start strategy that integrates (1) an improved V/f startup control with a two-segment voltage reference to soften bus energization; (2) an SOC-aware adaptive droop law based on a bounded arcsine SOC index to balance the charge/discharge effort among distributed storage units; and (3) a virtual-capacitor-based phase-angle control to accelerate synchronization before grid connection. Compared with existing black-start schemes, the proposed framework provides stronger voltage regulation, better SOC consistency, and shorter synchronization time in a pure renewable scenario. The method is validated through PSCAD/EMTDC simulations and an engineering case study of the Ejina pure renewable grid. Full article

Wafer defect analysis is important for semiconductor manufacturing, but labeled data are limited, and class distributions are highly imbalanced. We present a semi-supervised framework with two lightweight hybrid CNN–Transformer models for wafer defect classification and segmentation. For classification, HybridCNN-ViT combines CNN-based local feature extraction with Transformer-based global context modeling, and adopts a three-stage progressive pseudo-labeling strategy to leverage unlabeled samples. The pseudo-label selection mechanism is systematically calibrated to improve pseudo-label reliability under limited labeled data. For segmentation, ConvoFormer-UNet integrates convolution-enhanced embeddings with Transformer blocks to balance boundary detail and global context. On the public WM-811K dataset, HybridCNN-ViT achieves 98.72% accuracy and 0.9985 macro-AUC under the semi-supervised setting for classification, while ConvoFormer-UNet reaches 99.19% IoU for segmentation with fewer parameters than several baselines. We also report efficiency on a single GPU to illustrate practical inference speed. Full article

The Johnson–Mehl–Avrami–Kolmogorov (JMAK) formalism provides a classical framework for describing polymer crystallization kinetics; its applicability under finite-domain confinement requires quantitative assessment. In this work, the influence of one-dimensional geometric restriction on cylindrical growth in polymer thin films is investigated using a stochastic Monte Carlo approach. The model considers site-saturated nucleation on randomly distributed cylindrical nanofibers with constant radial growth velocity under hard-wall boundary conditions. Crystallization kinetics were evaluated through automated segmented regression of the double-logarithmic JMAK representation. Under confinement, the Avrami plot departs from single-slope linearity and exhibits two successive quasi-linear regimes characterized by effective parameter pairs $\left(n_1,\ln k_1\right)$ and $\left(n_2,\ln k_2\right)$. The primary exponent $n_1$ remains thickness-independent, consistent with early-stage radial expansion prior to boundary interaction. The secondary exponent $n_2$ displays a non-monotonic dependence on reduced film thickness, reflecting the competing influence of wall-induced truncation and inter-domain impingement on late-stage transformation. These results support a geometric interpretation in which finite-domain constraints modify the apparent Avrami response through the competing effects of wall-induced truncation and inter-domain impingement and provide a reproducible framework for analyzing dual-regime Avrami behavior in confined crystallization systems. Full article

In low-altitude complex environments, accurately reconstructing the three-dimensional (3D) flight trajectories of small unmanned aerial vehicles (UAV) without onboard positioning modules remains challenging. To address this issue, this paper proposes a multi-view ground camera-based UAV 3D trajectory detection method founded on an optical imaging geometric model. Multiple ground cameras are used to synchronously observe UAV flight, enabling stable 3D trajectory reconstruction without relying on onboard Global Navigation Satellite System (GNSS). At the two-dimensional (2D) observation level, a lightweight object detection model is employed for rapid UAV detection. Foreground segmentation is further introduced to extract accurate UAV contours, and geometric centroids are computed to obtain precise image plane coordinates. At the 3D reconstruction stage, camera extrinsic parameters are estimated using a back intersection method with ground control points, and the UAV spatial position in the world coordinate system is recovered via multi-view forward intersection. Field experiments demonstrate that the proposed method achieves stable 3D trajectory reconstruction in real urban environments, with a median error of 4.93 m and a mean error of 5.83 m. The mean errors along the X, Y, and Z axes are 2.28 m, 4.58 m, and 1.09 m, respectively, confirming its effectiveness for low-cost UAV trajectory monitoring. Full article

Internal reconnection events (IREs) are rapid magnetohydrodynamic phenomena that play an important role in the confinement and stability of spherical tokamak plasmas. Reliable identification of IREs in experimental data is challenging due to short discharge durations, ambiguous event boundaries, and the limited availability of labeled data. In this study, we propose an unsupervised, event-level IRE detection framework based on anomaly detection techniques and apply it to experimental data from the VEST spherical tokamak. The proposed framework combines a two-stage detection strategy using plasma current and $H_{\alpha }$ emission signals with sliding-window segmentation and event-level evaluation, enabling physically meaningful IRE identification without labeled training data. Three unsupervised models—K-Nearest Neighbors (KNN), One-Class Support Vector Machine (OCSVM), and an autoencoder (AE)—are evaluated within a unified framework. All models achieve stable detection performance, with precision exceeding 80% and recall above 70% under a precision-oriented operating point. To enhance detection robustness, a KNN-based cleaning procedure is introduced during training to remove noise-driven, locally isolated windows, significantly reducing spurious detections while preserving physically meaningful IRE signatures. Event-level analysis indicates that missed detections under this operating regime predominantly correspond to weak events with limited impact on global plasma behavior. The proposed framework is fully unsupervised, computationally efficient, and readily extensible to other spherical tokamak devices, providing a flexible foundation for incorporating additional diagnostics, such as Mirnov coil signals, toward precursor-aware detection and future predictive modeling of IRE activity. Full article

Hypertension is a leading global health risk and requires accurate and continuous monitoring for effective management. Although photoplethysmography (PPG) is a promising non-invasive modality for cuffless blood pressure (BP) assessment, many existing approaches (especially raw-signal deep learning) are vulnerable to data leakage, overfitting on small datasets, limited interpretability, and poor performance on minority BP stages. To address these limitations, we propose a robust and physiologically grounded framework for multi-class BP stage classification based on interpretable PPG features. Our approach centers on a comprehensive multi-domain feature engineering pipeline that extracts 124 PPG features, including demographic, morphological, functional decomposition, spectral, nonlinear dynamics, and clinical composite indices. We apply rigorous preprocessing and feature selection prior to model training. We validate the framework on two datasets: PPG-BP dataset (657 segments, 4 classes) for benchmarking and PulseDB (283,773 segments, 3 classes) to assess scalability. We evaluate the proposed framework using a segment-level train/test split, appropriate for assessing intra-subject BP tracking after initial personalization. For the PulseDB dataset, this follows the protocol established by the dataset creators, while for the PPG-BP dataset, it enables direct comparison with prior work given practical dataset constraints. On PPG-BP, LightGBM trained on the selected features achieved macro-F1 = 0.78 and accuracy = 0.74, outperforming comparable deep-learning models. On the PulseDB, a custom Residual MLP achieved accuracy = 0.81 and macro-F1 = 0.79, supporting generalization at scale. These results show that the proposed feature-based approach can outperform complex end-to-end deep-learning models on small datasets while providing improved interpretability. This work establishes a reliable and transparent pathway toward clinically viable continuous BP staging, moving beyond black-box models toward physiologically grounded decision support. Ablation analysis reveals that engineered features provide most of the predictive power (F1 = 0.911), while raw PPG features alone achieve modest performance (F1 = 0.384). For the minority hypertension stage 2 (HT-2) class, a bootstrap 95% confidence interval of [0.762, 1.000] is reported, reflecting uncertainty due to limited sample size. Full article

The coupling of non-stationary marine noise and complex ship-radiated signals makes high-fidelity signal recovery exceptionally difficult. Existing deep learning methods often prioritize objective metrics, such as the Scale-Invariant Signal-to-Noise Ratio (SI-SNR), but fail to maintain the integrity of narrow-band line spectral data. We propose FocuS-MN, an end-to-end framework that combines learnable resampling with Feedforward Sequential Memory Network (FSMN)-based temporal modeling for precise waveform reconstruction. The model is optimized using a two-stage training strategy to ensure stable magnitude estimation and waveform consistency. On the ShipsEar dataset, FocuS-MN shows strong generalization to unseen vessel types. At a −5 dB Signal-to-Noise Ratio (SNR), it achieves a Signal-to-Distortion Ratio (SDR) of 3.77 dB and a Segmental Signal-to-Noise Ratio (SSNR) of 3.83 dB. Power Spectral Density (PSD) analysis further confirms that FocuS-MN recovers fine-grained line spectral structures, proving its effectiveness in both noise suppression and signal fidelity. Full article

This study presents an integrated simulation framework that combines agent-based transport modeling with probabilistic load-flow analysis to quantify power system loading of long-haul heavy-duty electrification. The approach is applied to a case study considering fully electrified road freight in the Skåne region in Sweden, using high-resolution transport demand data and the actual power grid model used by the grid owner in the study area. The synthetic freight population covers the full long-haul truck segment intersecting Skåne. Both public en-route fast charging and end-of-trip depot charging are considered. The analysis reveals two fundamentally different charging demand profiles: a heavily fluctuating profile for public en-route charging, accounting on average for 82% of the total daily charging energy, and a stable profile for end-of-trip depot charging, covering on average the remaining 18%. The latter is achieved through a Linear Programming (LP) optimization model that flattens the load by scheduling charging across depot stay windows. These profiles serve as inputs to a probabilistic load-flow simulation that computes loading distributions for substation transformers. The simulation results show that in 4 of the 43 primary substations studied, the maximum transformer loading exceeds 100% following the introduction of truck charging, with peak loading at the most affected substation rising from 99% to 159%. This stress is primarily caused by the public charging demand, which peaks from late morning to noon, aligning with the early stages of logistics operations. However, there is no clear correlation between the magnitude of the truck charging load and the impact on transformer loading, since this is also highly dependent on local grid conditions. These findings highlight the value of integrated transport-energy simulations for planning resilient infrastructure and guiding targeted grid reinforcements. Full article

Motor vehicle encroachment into non-motorized lanes is a common but hard-to-verify violation in urban intersections, especially when monitored from unmanned aerial vehicles (UAVs) or high-mounted overhead views. Existing rule-based solutions built on horizontal bounding boxes and center-point/line-crossing criteria are sensitive to perspective distortion, occlusion, and frame-to-frame jitter, resulting in unstable decisions and low evidential value. This paper presents a cascaded UAV-view system that closes the loop from perception to evidence output through detection–segmentation–recognition–decision. First, we adopt a two-stage detection cascade: a lightweight vehicle detector localizes vehicles using axis-aligned bounding boxes, and a dedicated YOLOv5n-based oriented bounding box (OBB) license plate detector, constructed via architecture grafting and weight transfer, is then applied within each vehicle region of interest (ROI) to localize rotated license plates under large pose variation and small-target conditions. Second, a U-Net lane region segmentation module provides pixel-level spatial constraints to define an enforceable lane occupancy region. Third, a perspective rectification step is integrated with the PP-OCRv4 optical character recognition (OCR) framework to improve license plate recognition reliability for tilted plates. Finally, an area ratio criterion and an N-frame temporal counter are used to suppress transient misdetections and stabilize alarms. On a representative 100-sample controlled encroachment benchmark, the proposed system improves detection accuracy from 67.0% to 92.0% and reduces the false positive rate from 32.35% to 5.88% compared with a baseline horizontal bounding box (HBB)-based rule. The system outputs both violation alarms and license plate evidence, supporting practical deployment for multi-view traffic governance. Full article

Background/Objectives: Accurate and reproducible lymph node (LN) measurement is essential for oncologic staging and therapy monitoring but is subject to inter-reader variability. This study evaluated the accuracy and reproducibility of a fully automated artificial intelligence (AI)-based LN measurement workflow in contrast-enhanced chest CT, using multi-reader manual measurements as reference. Methods: Sixty thoracic LNs from seven patients were independently measured by 13 radiologists in two reading rounds. The median of all measurements served as the ground truth (GT). Automated short- and long-axis diameters were derived from fully automated 3D CNN-based segmentations. Agreement between AI and manual measurements was assessed using Friedman testing, intraclass correlation coefficients (ICCs), and concordance correlation coefficients (CCCs). Measurement stability was evaluated across repeated runs on different hardware systems. Results: A total of 2280 manual measurements were analyzed. Manual assessment showed significant inter-reader variability (p < 0.01), while intra-reader agreement was high. No significant differences were observed between AI-based measurements and the GT (all p > 0.01). Agreement was good, with CCC values of 0.86 (SAD) and 0.79 (LAD). AI-based measurements were numerically stable across hardware configurations. Conclusions: Fully automated AI-based LN measurements in chest CT scans provide strong agreement with multi-reader consensus and high numerical stability. Automated measurement may support more standardized and reproducible oncologic imaging assessment. Full article