Search Results (25,531)

Accurate target localization via matching real-time UAV images with reference satellite imagery is essential for autonomous environmental perception. Nonetheless, operational constraints and weather conditions often necessitate oblique photography. This large-tilt mode causes significant perspective and radiometric distortions, resulting in a substantial domain gap between UAV and vertical satellite imagery. The scarcity of datasets featuring extreme viewpoint shifts and fine-grained ground-truth labels hinders the validation of image matching algorithms in multi-tilt-angle environments. To address this issue, we introduce the multiple-tilt-angle dataset (MTA-Dataset), containing 1892 UAV images with tilt angles spanning $\left[0°,\right.\left.90°\right)$ and flight altitudes up to 300 m, supported by high-precision five-point manual annotations. Based on this benchmark, we evaluate state-of-the-art matching algorithms and propose a spatial-resolution-based cropping strategy. Experimental results demonstrate that, as the UAV tilt angle increases within the range of $\left[0°,\right.\left.90°\right)$, although the expanding field of view provides richer contextual information, the localization errors of all methods increase significantly and matching precision drops sharply due to severe geometric distortions in far-field regions and interference from redundant background information, with performance deteriorating most drastically in the $\left[50°,\right.\left.90°\right)$ range. With the integration of our strategy, the average matching localization errors of SuperPoint + SuperGlue baseline for UAV images within the tilt-angle ranges of $\left[50°,\right.\left.60°\right)$, $\left[60°,\right.\left.70°\right)$, $\left[70°,\right.\left.80°\right)$, and $\left[80°,\right.\left.90°\right)$ are reduced by 33.49 m, 37.86 m, 98.3 m, and 109.95 m, respectively. Our study provides a more comprehensive evaluation framework for robust UAV–satellite image matching algorithms in multi-tilt-angle scenarios. Full article

This study presents an explainable knowledge graph (KG) framework that transforms continuous spindle monitoring time-series data into transparent, reasoning-ready diagnostic structures. Existing data-driven approaches, while accurate, often lack the interpretability required for high-stakes industrial decision-making and are sensitive to operating condition drifts. To address these limitations, we propose a two-level temporal segmentation method combining label transition detection and statistical drift analysis to identify meaningful state boundaries. Furthermore, a percentile-based discretization mechanism converts statistical features into interpretable semantic tags. A Neo4j-based state–event–feature schema captures lifecycle evolution and evidence relations, enabling attribution path reasoning that links failure events to salient precursor features. Experiments on real industrial spindle data demonstrate a fault detection accuracy of 84.97% and a false alarm rate of 3.43%, effectively capturing stable baselines and intermittent abnormal bursts. The proposed framework provides a distinct novelty in bridging the gap between numerical time-series and symbolic reasoning, offering a practical pathway for deploying explainable and maintainable spindle health analytics. Full article

Mangrove extent has increased in many regions under strengthened conservation policies and large-scale restoration programs. Nevertheless, mangrove ecosystems continue to face multiple pressures, including limited total area, habitat degradation, biodiversity decline, and biological invasion, and localized deterioration in ecosystem structure and function has been increasingly reported. Despite extensive mapping efforts, the spatiotemporal dynamics of mangrove degradation—particularly in tidally influenced environments—remain insufficiently understood. Focusing on the Nanliu River Delta, the largest deltaic mangrove system in the Northern Beibu Gulf of China, this study integrates long-term Landsat time-series imagery (1990–2025) with deep learning to quantify both mangrove extent change and canopy degradation. To mitigate tidal inundation effects, a NDVI Pseudo-P75 compositing strategy was applied using Google Earth Engine (GEE), enabling consistent observation of mangrove canopies across tidal stages. Global Mangrove Watch v4 (GMW-V4) and HGMF2020 mangrove dataset for China were used as reference labels to train a ResNet34–UNet segmentation framework incorporating Digital Elevation Model (DEM) constraints. The model achieved high classification performance, with an IoU of 0.822 for mangroves and 0.981 for background, yielding a mean IoU of 0.902. The resulting maps, following manual verification, provided a robust basis for spatiotemporal and degradation analyses. Canopy condition was further assessed using the Enhanced Vegetation Index (EVI), which is less prone to saturation in high-biomass mangrove stands. Results show that mangrove area in the Nanliu River Delta expanded from 266 ha in 1990 to 1414 ha in 2025, with the annual expansion rate after 2005 being nearly seven times higher than that before 2005. Despite this net gain, a cumulative loss of 347.45 ha was recorded, primarily during 1990–2000, with approximately 70% converted to aquaculture and coastal engineering. Spatial analysis revealed that mangrove expansion occurred predominantly seaward, whereas both mangrove loss and canopy degradation exhibited an inverse J-shaped relationship with seawall proximity. More than 80% of mangrove loss occurred within 200 m of seawalls, indicating concentrated anthropogenic encroachment, while 75.6% of canopy degradation was observed within 350 m, potentially reflecting landward forest senescence. These results indicate a transition in dominant threats from permanent land conversion in the late 20th century to more subtle, internal functional degradation in recent decades, underscoring the need to complement extent-based assessments with canopy condition monitoring in mangrove conservation and management. Full article

To mitigate UAV (unmanned aerial vehicle) range limitation risks and scheduling disruptions caused by complex wind fields in urban instant delivery, this paper proposes a UAV–rider collaborative dispatching framework. By incorporating aerodynamic-based nonlinear energy dynamics, the model accurately characterizes power variations under stochastic wind conditions, significantly enhancing the operational reliability of urban delivery missions. First, an aerodynamic-based nonlinear energy function is constructed, coupling payload, airspeed, and random wind vectors to accurately characterize power variations. Second, a scenario-based two-stage stochastic programming framework is adopted, where the rider’s deterministic path is optimized in the first-stage decision to ensure stability, and the UAV’s scenario-dependent flight plan is resolved in the second stage to adapt to wind uncertainty. An improved branch-and-price (IBP) algorithm is designed to solve this large-scale model, where nonlinear energy is evaluated during label extension in the pricing sub-problem, effectively avoiding linearization errors. The numerical results demonstrate that the proposed framework improves the mission success probability (the likelihood of completing delivery routes without battery exhaustion across all considered wind scenarios) by 25% under strong-wind conditions by effectively avoiding power failure risks. Furthermore, the IBP algorithm outperforms traditional exact solvers by over 40% in solution efficiency for large-scale cases. These findings demonstrate that energy-aware stochastic dispatching significantly improves the reliability and robustness of UAV-assisted last-mile delivery in windy urban environments, thereby providing an effective operational solution for real-world drone delivery logistics. Full article

Artificial intelligence (AI), including machine learning (ML) and deep learning (DL), is increasingly transforming the study, manufacturing, and clinical translation of adipose-derived stem/stromal cells (ADSCs). ADSC-based therapies face persistent challenges related to donor variability, heterogeneous cell populations, limited standardization of culture protocols, and the need for robust quality control (QC) and potency assessment under Good Manufacturing Practice (GMP) conditions. This review discusses how AI-driven approaches can support the ADSC pipeline from donor and tissue pre-screening, through isolation and expansion, to differentiation and batch release decisions. We highlight major methodological advances in computer vision and label-free imaging for monitoring morphology, confluency, proliferation, senescence, and contamination, as well as AI-assisted optimization strategies for culture parameters and differentiation protocols. In addition, we examine the growing role of multi-omics integration (transcriptomics, proteomics, metabolomics, and secretomics) combined with ML to predict functional potency, stratify donors, and identify biomarkers associated with therapeutic efficacy. Finally, we address current limitations, including data scarcity, inter-laboratory variability, model interpretability, and regulatory requirements, and outline future perspectives such as closed-loop bioprocess control, foundation models, and federated learning frameworks. Overall, AI offers a powerful toolkit to improve the reproducibility, safety, and scalability of ADSC manufacturing and to accelerate the development of standardized, data-driven regenerative medicine products. Full article

The emergence of the Internet of Things (IoT) has introduced major security challenges. Deep learning models have shown strong potential for intrusion detection. However, they often require large datasets and high computational resources. In contrast, IoT environments are resource-constrained and lack sufficient labeled data. This paper proposes a lightweight intrusion detection approach based on Long Short-Term Memory (LSTM) networks and homogeneous transfer deep learning. The model is first trained on a subset of the BoT-IoT dataset as a source domain. It is then fine-tuned on a disjoint subset containing a rare attack type. This setup represents adaptation to unseen attack behaviors within the same environment. By freezing earlier layers and fine-tuning only the final layers, the method reduces training overhead while preserving performance. This is important to meet the IoT requirement for frequent, lightweight model updates on resource-constrained devices. The proposed model achieved 99.9% accuracy, a macro F1-score of 0.96, and a 47.8% reduction in training time compared to training from scratch. Extensive experiments confirm that it maintains balanced detection across both common and rare classes. Full article

Reliable traffic sign detection is essential for the safety of autonomous driving systems. However, manually annotating large-scale datasets for this task is resource-intensive, making semi-supervised learning (SSL) a vital alternative. Despite their potential, current SSL methods often struggle with unreliable pseudo-label filtering and limited detection accuracy. To address these limitations, we propose a novel framework integrating a Dual Confidence Fusion (DC-Fusion) module and a Structured Block-Regularized Neck (SBR-Neck). The former improves pseudo-label reliability by combining classification and localization confidence scores, while the latter optimizes feature representation through multi-scale fusion and block-wise regularization. To preserve high-frequency spatial details, SBR-Neck incorporates Spatial-Context-Aware Upsampling (SCA-Upsampling), which utilizes multi-granularity feature decomposition. Experimental results on a proprietary traffic sign dataset demonstrate that our method achieves ${\mathrm{mAP}}_{50}$ scores of 10.4%, 17.8%, 23.7%, and 32.1% using 1%, 2%, 5%, and 10% labeled data, respectively. These results surpass the “Efficient Teacher” baseline by margins ranging from 3.07% to 11%, confirming the framework’s ability to provide robust detection in complex traffic scenarios. Full article

The fabrication of a real-time intelligent indication label for food freshness has emerged as an effective strategy to reduce food waste and improve food safety. In this study, utilizing polyvinyl alcohol (PVA) and arabinoxylan (AX) as the polymer matrices, and incorporating purple cabbage anthocyanins (PCAs) as natural pH-responsive agents, we fabricated a PVA/AX/PCA nanofiber-based intelligent indication label via electrospinning. The results confirmed that the nanofibers exhibited uniform morphology and good structural stability, with the PCA successfully embedded within the nanofibers. The nanofiber membrane exhibits a low water contact angle (54°) and demonstrates a tensile strength of 5.34 ± 0.09 MPa with an elongation at break of 32.43 ± 1.02%, while maintaining a certain degree of flexibility. The nanofiber labels exhibited distinct color changes within a wide pH range (2 to 12), which confirms their pH-responsive characteristics. After being stored at 4 °C and 25 °C for 14 days, the maximum color difference related to storage stability was 1.53 ± 0.02. In practical applications at 25 °C, this intelligent label demonstrated significant color changes when monitoring low-temperature-cooked sausages and fresh shrimp, with total color differences of 41.57 and 53.06, respectively. Degradation experiments showed that the nanofiber labels gradually decomposed, reflecting good biodegradability and environmental-protection characteristics. In conclusion, the green intelligent indication label developed in this study offers a feasible solution for real-time monitoring of food quality. Full article

Over the past two decades, the term cervical incompetence has largely been replaced by cervical insufficiency in clinical guidelines, reflecting efforts to avoid pejorative language and to acknowledge functional variability. However, despite this terminological evolution, the underlying conceptual framework has remained largely static, continuing to treat cervical insufficiency as a fixed anatomic defect inferred from obstetric history or single-point measurements. This Perspective argues that such a model inadequately explains the substantial clinical heterogeneity observed across and within pregnancies, limiting its usefulness for individualized clinical interpretation and study design. Drawing on contemporary guideline frameworks, systematic reviews, and international disease classification systems, this article highlights the limitations of static, anatomy-centered approaches and proposes an alternative conceptualization of cervical insufficiency as a dynamic, pregnancy-specific vulnerability. Within this framework, cervical behavior is understood as time-dependent and context-sensitive, shaped by the interplay of mechanical load, biological processes, and gestational timing rather than predetermined structural failure. This conceptualization is intended to inform interpretation across diverse clinical contexts, rather than to redefine diagnostic criteria or existing guideline recommendations. By shifting emphasis from fixed diagnostic labels to trajectories of cervical vulnerability, this Perspective situates cervical insufficiency within the broader continuum of spontaneous preterm birth and aligns its interpretation with the principles of personalized medicine. This conceptual reframing positions cervical insufficiency as a model condition for personalized maternal–fetal care, emphasizing time- and context-aware risk assessment and trajectory-informed clinical decision-making, while providing a coherent foundation for individualized surveillance and future research aimed at improving maternal–fetal outcomes. Full article

The creation and application of classification category labels are essential tasks for transforming complex information into structured knowledge. Categories are used for summary and reporting purposes and have historically been identified by domain experts based on their past experiences and norms. Our interest lies in the general case where expert-generated category lists require improvement, and unsupervised learning, on its own, struggles to effectively identify categories for multi-class classification of human-generated texts. We hypothesise that including an annotated knowledge graph (KG) in an embedding process will positively impact unsupervised clustering performance. Our goal is to identify clusters that can be labelled and used for classification. We look at unsupervised clustering of Maintenance Work Order (MWO) texts. MWOs capture vital observations about equipment failures in process and heavy industries. The selected KG contains a mapping of equipment types to their inherent function based on the IEC 81346-2 international standard for classification of objects in industrial systems. Performance is assessed by statistical analysis, subject matter experts, and Normalized Mutual Information score. We demonstrate that Word2Vec Bi-LSTM and Sentence-BERT NN embedding methods can leverage equipment inherent function information in the KG to improve failure mode cluster identification for the MWO. Organisations seeking to use AI to automate assignment of a failure mode code to each MWO currently need test sets classified by humans. The results of this work suggest that a semantic layer containing a knowledge graph mapping equipment types to inherent function, and inherent function to failure modes could assist in quality control for automated failure mode classification. Full article

High-quality RGB–thermal infrared (RGB-T) semantic segmentation datasets are crucial for search-and-rescue (SAR) applications, yet their development is hindered by the scarcity of annotated ground-truth and by the challenges of thermal-camera calibration, which typically depends on heated targets with limited geometric definition. Recent approaches focus on using semantic segmentation annotation tools and transferring RGB masks to multi-spectral data, but they do not fully address the need for robust cross-modal geometric validation, quality control, or human-in-the-loop reliability assessment in RGB-T segmentation. To fill this gap, we propose a validated cross-modal annotation pipeline that combines deep correspondence matching, geometric transformation (affine or homography) of RGB-T pairs, and quantitative alignment validation. Our RGB-T pipeline integrates a semi-automatic annotation pipeline based on the Segment Anything Model 2 (SAM2) in Label Studio, with guided human refinement, and incorporates quantitative cost and quality control via inter-annotator agreement before being used in downstream model training. Results across three annotators show that the proposed approach reduces annotation time by 36% while achieving high annotation quality (mean IoU = 74.9%) and strong inter-annotator agreement (mean pixel accuracy = 74.3%, Cohen’s $\kappa$ = 65%). The proposed RGB-T pipeline was annotated on a SAR-oriented RGB-T dataset comprising 306 image pairs and trained on two SOTA RGB-T. These findings demonstrate the practical value of the proposed methodology and establish a reproducible framework for generating reliable RGB-T semantic segmentation datasets, complementing and extending recent multispectral auto-labeling approaches. Full article

Indoor 3D point cloud semantic segmentation is a fundamental task for fine-grained scene understanding and intelligent perception. Due to the prohibitive cost of dense point-wise annotations, weakly supervised learning has emerged as a promising alternative for indoor point cloud segmentation. However, existing weakly supervised methods commonly rely on fixed confidence thresholds for pseudo-label selection, which exhibit limited generalization caused by threshold sensitivity, underutilization of informative low-confidence regions, and progressive noise accumulation during self-training. To address these issues, we propose TGR-T, a weakly supervised framework for indoor 3D point cloud semantic segmentation that incorporates truncated-Gaussian-weighted reliability with adaptive dynamic thresholding. Specifically, a reliability-adaptive dynamic thresholding strategy is introduced to guide pseudo-label selection based on the evolving confidence statistics of unlabeled mini-batches, with exponential moving average smoothing employed to produce stable global estimates and robust separation of reliable and ambiguous regions. To further exploit uncertain regions, a learnable truncated Gaussian weighting function is designed to explicitly model prediction uncertainty within the ambiguous set, providing soft supervision by assigning adaptive weights to low-confidence predictions during optimization. Extensive experimental results demonstrate that the proposed framework significantly enhances the exploitation of unlabeled data under extremely limited supervision: extensive experiments conducted on standard indoor 3D scene benchmarks demonstrate that TGR-T achieves competitive or superior segmentation performance under extremely sparse supervision and can even outperform several fully supervised baselines trained with dense annotations while using only 1% labeled points, thereby substantially narrowing the performance gap between weakly supervised and fully supervised 3D semantic segmentation methods. Full article

In medical endoscopic imaging, specular reflection (SR) frequently leads to local overexposure, obscuring essential tissue information and complicating computer-aided diagnosis (CAD). Traditional convolutional neural networks (CNNs) face difficulties in modeling global illumination phenomena due to their biased local receptive fields and the inherent “object assumption.” Conversely, pure transformer models often lose high-frequency boundary details and incur substantial computational costs. To tackle these challenges, this paper introduces VDTAR-Net, a specialized framework adapted to address the unique optical characteristics of specular reflections. Building upon hybrid architectures, our contribution focuses on two core mechanisms: (1) a Cross-architecture Fusion Module (CFM) that enables deep, bidirectional information flow, allowing the Transformer’s global illumination modeling to continuously correct the CNN’s local texture biases; and (2) a Reflective-Aware Module (RAM), which explicitly integrates the physical prior of high-intensity saturation into the attention mechanism. This task-specific design significantly enhances sensitivity to boundary details in overexposed regions. We also created the first large-scale, expert-labeled cervical white light segmentation dataset, Cervix-WL-900. High-quality ground truth labels were generated through rigorous double-blind annotation and arbitration by senior experts. Experimental results show that VDTAR-Net achieves a Dice score of 92.56% and a mean Intersection over Union (mIoU) score of 87.31% on Cervix-WL-900, demonstrating superior performance compared to methods like U-Net, DeepLabv3+, SegFormer, and PSPNet. Ablation studies further confirm the substantial contributions of dual-path collaboration, CFM deep fusion, and RAM task-specific priors. VDTAR-Net provides a robust baseline for precise highlight segmentation, laying a foundation for subsequent image quality assessment, restoration, and feature decoupling in diagnostic models. Full article

Sweeteners occupy a pivotal role in the global transition toward sustainable, health-aligned, and resource-efficient food systems. Conventional sucrose production carries significant environmental burdens, while escalating metabolic health concerns intensify demand for viable alternatives. This paper reframes sweeteners not as commodity ingredients, but as digitally engineered, biologically manufactured, and circularity-optimized materials within the emerging bioeconomy. Advances in artificial intelligence (AI), metabolic engineering, precision fermentation, and lignocellulosic valorization are fundamentally reshaping sweetener innovation. We introduce the Sweetener Innovation 4.0 framework, in which AI functions as the integrative engine linking molecular design, bioprocess optimization, and system-level sustainability. Across diverse sweetener classes, including steviol glycosides, mogrosides, rare sugars, sweet proteins, and forestry-derived polyols, AI accelerates discovery, improves metabolic flux control, optimizes downstream processing and enables more adaptive manufacturing systems. This digital–biological convergence is progressively decoupling sweetness production from land-intensive agriculture, reducing dependence on geographically constrained crops, and enabling resilient, low-carbon manufacturing pathways. Comparative life-cycle assessments highlight substantial sustainability gains, but also reveal persistent methodological gaps, particularly in accounting for downstream-processing energy and digital infrastructure emissions. Socioeconomic analysis further underscores the importance of equitable transitions, transparent labeling, and effective consumer communication as fermentation-derived sweeteners enter global markets. Looking forward, we identify key frontiers for Sweetener Innovation 4.0, including de novo AI-designed sweeteners, autonomous fermentation systems, carbon-negative feedstocks, personalized sweetness modulation, and integrated circular biorefineries. Together, these developments position sweeteners as a top domain for demonstrating how AI, biotechnology, and sustainability principles can jointly reshape ingredient development and industrial systems within the 21st-century circular-economy. Full article

Ginger (Zingiber officinale) is an essential crop that is widely cultivated for its medical and culinary value. In 2023, ginger was considered one of the highest value herbs, with approximately 9089.85 tons produced in Malaysia. However, the ginger cultivation suffers from plant diseases, which lead to plant death and eventually cause crop losses. Furthermore, the lack of studies in ginger leaf disease detection using deep learning techniques is a limitation that hinders the early diagnosis and management of ginger diseases. To address this limitation, we collected 968 ginger plant images cropped into single leaf images and labelled into 4 classes: leaf blight, dehydrated, damaged pest, and healthy, using the Encordplatform. The generated dataset consisted of 4033 leaf images. Through data augmentation, the dataset was expanded into 10,910 leaf images to improve the model’s generalization. As deep learning techniques are popular in plant disease detection, we evaluated several popular pre-trained models using TensorFlow and PyTorch libraries and compared the performance with that of other models. For all of these models, the same settings were applied with minimal modification to the model’s layers. Among the compared models, EfficientNetB3 achieved the highest accuracy of 94.3% in detecting ginger leaf diseases. It surpassed other models and exceeded the next-best model in this experiment, MobileNetV2, which achieved 89.66% accuracy, by 4.64%. Full article