Search Results (801)

Unmanned aerial vehicle (UAV)-based object detection shows promising potential in intelligent transportation and disaster response. However, detecting small targets remains challenging due to inherent limitations (long-distance and low-resolution imaging) and environmental interference (complex backgrounds and occlusions). To address these issues, this paper proposes an enhanced small target detection model, DDF-YOLO, which achieves higher detection performance. First, a dynamic feature extraction module (C2f-DCNv4) employs deformable convolutions to effectively capture features from irregularly shaped objects. In addition, a dynamic upsampling module (DySample) optimizes multi-scale feature fusion by combining shallow spatial details with deep semantic features, preserving critical low-level information while enhancing generalization across scales. Finally, to balance rapid convergence with precise localization, an adaptive Focaler-ECIoU loss function dynamically adjusts training weights based on sample quality during bounding box regression. Extensive experiments on VisDrone2019 and UAVDT benchmarks demonstrate DDF-YOLO’s superiority. Compared to YOLOv8n, our model achieves gains of 8.6% and 4.8% in mAP50, along with improvements of 5.0% and 3.3% in mAP50-95, respectively. Furthermore, it exhibits superior efficiency, requiring only 7.3 GFLOPs and attaining an inference speed of 179 FPS. These results validate the model’s robustness for UAV-based detection, particularly in small-object scenarios. Full article

To address the challenges of small target detection in UAV aerial images—such as difficulty in feature extraction, complex background interference, high miss rates, and stringent real-time requirements—this paper proposes an innovative model series named SRTSOD-YOLO, based on YOLO11. The backbone network incorporates a Multi-scale Feature Complementary Aggregation Module (MFCAM), designed to mitigate the loss of small target information as network depth increases. By integrating channel and spatial attention mechanisms with multi-scale convolutional feature extraction, MFCAM effectively locates small objects in the image. Furthermore, we introduce a novel neck architecture termed Gated Activation Convolutional Fusion Pyramid Network (GAC-FPN). This module enhances multi-scale feature fusion by emphasizing salient features while suppressing irrelevant background information. GAC-FPN employs three key strategies: adding a detection head with a small receptive field while removing the original largest one, leveraging large-scale features more effectively, and incorporating gated activation convolutional modules. To tackle the issue of positive-negative sample imbalance, we replace the conventional binary cross-entropy loss with an adaptive threshold focal loss in the detection head, accelerating network convergence. Additionally, to accommodate diverse application scenarios, we develop multiple versions of SRTSOD-YOLO by adjusting the width and depth of the network modules: a nano version (SRTSOD-YOLO-n), small (SRTSOD-YOLO-s), medium (SRTSOD-YOLO-m), and large (SRTSOD-YOLO-l). Experimental results on the VisDrone2019 and UAVDT datasets demonstrate that SRTSOD-YOLO-n improves the mAP@0.5 by 3.1% and 1.2% compared to YOLO11n, while SRTSOD-YOLO-l achieves gains of 7.9% and 3.3% over YOLO11l, respectively. Compared to other state-of-the-art methods, SRTSOD-YOLO-l attains the highest detection accuracy while maintaining real-time performance, underscoring the superiority of the proposed approach. Full article

Micro-expression recognition (MER) aims to detect brief and subtle facial movements that reveal suppressed emotions, discerning authentic emotional responses in scenarios such as visitor experience analysis in museum settings. However, it remains a highly challenging task due to the fleeting duration, low intensity, and limited availability of annotated data. Most existing approaches rely solely on either appearance or motion cues, thereby restricting their ability to capture expressive information fully. To overcome these limitations, we propose a lightweight multi-modal fusion network, termed M³ENet, which integrates both motion and appearance cues through early-stage feature fusion. Specifically, our model extracts horizontal, vertical, and strain-based optical flow between the onset and apex frames, alongside RGB images from the onset, apex, and offset frames. These inputs are processed by two modality-specific subnetworks, whose features are fused to exploit complementary information for robust classification. To improve generalization in low data regimes, we employ targeted data augmentation and adopt focal loss to mitigate class imbalance. Extensive experiments on five benchmark datasets, including CASME I, CASME II, CAS(ME)², SAMM, and MMEW, demonstrate that M³ENet achieves state-of-the-art performance with high efficiency. Ablation studies and Grad-CAM visualizations further confirm the effectiveness and interpretability of the proposed architecture. Full article

While insulator integrity is critical for power grid stability, prevailing detection algorithms often rely on computationally intensive models incompatible with resource-constrained edge devices like unmanned aerial vehicles (UAVs). Key limitations—including redundant feature interference, inadequate sensitivity to small targets, rigid fusion weights, and sample imbalance—further restrict practical deployment. To address those problems, this study presents a lightweight insulator anomaly detection algorithm, LAI-YOLO. First, the SqueezeGate-C3k2 (SG-C3k2) module, equipped with an adaptive gating mechanism, is incorporated into the Backbone network to reduce redundant information during feature extraction. Secondly, we propose a High-level Screening–Feature Weighted Feature Pyramid Network (HS-WFPN) to replace FPN+PAN via selective weighted feature fusion, enabling dynamic cross-scale integration and enhanced small-target detection. Then, a reconstructed lightweight detection head coupled with Slide Weighted Focaler Loss (SWFocalerLoss) mitigates performance degradation from sample imbalance. Ultimately, the layer adaptation for the magnitude-based pruning (LAMP) technique slashes computational demands without sacrificing detection prowess. Experimental results on our insulator anomaly dataset demonstrate that the improved model achieves higher efficacy in identifying insulator anomalies, with mAP@0.5 increasing from 88.2% to 91.1%, while model parameters and FLOPs are diminished to 45.7% and 53.9% of the baseline, respectively. This efficiency facilitates the deployment of edge devices and highlights the method’s considerable application potential. Full article

To address the technical challenges in the educational domain named entity recognition (NER), such as ambiguous entity boundaries and difficulties with nested entity identification, this study proposes an enhanced semantic BERT model (ES-BERT). The model innovatively adopts an education domain, vocabulary-assisted semantic enhancement strategy that (1) applies the term frequency–inverse document frequency (TF-IDF) algorithm to weight domain-specific terms, and (2) fuses the weighted lexical information with character-level features, enabling BERT to generate enriched, domain-aware, character–word hybrid representations. A complete bidirectional long short-term memory-conditional random field (BiLSTM-CRF) recognition framework was established, and a novel focal loss-based joint training method was introduced to optimize the process. The experimental design employed a three-phase validation protocol, as follows: (1) In a comparative evaluation using 5-fold cross-validation on our proprietary computer-education dataset, the proposed ES-BERT model yielded a precision of 90.38%, which is higher than that of the baseline models; (2) Ablation studies confirmed the contribution of domain-vocabulary enhancement to performance improvement; (3) Cross-domain experiments on the 2016 knowledge base question answering datasets and resume benchmark datasets demonstrated outstanding precision of 98.41% and 96.75%, respectively, verifying the model’s transfer-learning capability. These comprehensive experimental results substantiate that ES-BERT not only effectively resolves domain-specific NER challenges in education but also exhibits remarkable cross-domain adaptability. Full article

Accurate tree health monitoring in orchards is essential for optimal orchard production. This study investigates the efficacy of a deep learning-based object detection single-step method for detecting tree health on multispectral UAV imagery. A modified Mask R-CNN framework is employed with four different backbones—ResNet-50, ResNet-101, ResNeXt-101, and Swin Transformer—on three image combinations: (1) RGB images, (2) 5-band multispectral images comprising RGB, Red-Edge, and Near-Infrared (NIR) bands, and (3) three principal components (3PCs) computed from the reflectance of the five spectral bands and twelve associated vegetation index images. The Mask R-CNN, having a ResNeXt-101 backbone, and applied to the 5-band multispectral images, consistently outperforms other configurations, with an F1-score of 85.68% and a mean Intersection over Union (mIoU) of 92.85%. To address the class imbalance, class weighting and focal loss were integrated into the model, yielding improvements in the detection of the minority class, i.e., the unhealthy trees. The tested method has the advantage of allowing the detection of unhealthy trees over UAV images using a single-step approach. Full article

Identifying concealed explosives in X-ray backscatter (XRBS) imagery remains a critical challenge, primarily due to low image contrasts, cluttered backgrounds, small object sizes, and limited structural details. To address these limitations, we propose YOLOv11-XRBS, an enhanced detection framework tailored to the characteristics of XRBS images. A dedicated dataset (SBCXray) comprising over 10,000 annotated images of simulated explosive scenarios under varied concealment conditions was constructed to support training and evaluation. The proposed framework introduces three targeted improvements: (1) adaptive architectural refinement to enhance multi-scale feature representation and suppress background interference, (2) a Size-Aware Focal Loss (SaFL) strategy to improve the detection of small and weak-feature objects, and (3) a recomposed loss function with scale-adaptive weighting to achieve more accurate bounding box localization. The experiments demonstrated that YOLOv11-XRBS achieves better performance compared to both existing YOLO variants and classical detection models such as Faster R-CNN, SSD512, RetinaNet, DETR, and VGGNet, achieving a mean average precision (mAP) of 94.8%. These results confirm the robustness and practicality of the proposed framework, highlighting its potential deployment in XRBS-based security inspection systems. Full article

This report describes a case of feline gastrointestinal eosinophilic sclerosing fibroplasia (FGESF) in a 6-year-old spayed female European Shorthair cat presenting with chronic vomiting and weight loss. Endoscopic examination revealed a submucosal duodenal mass, and histopathological evaluation of endoscopic biopsies confirmed a diagnosis of FGESF. The cat was treated exclusively with oral prednisolone (1 mg/kg SID), leading to complete clinical remission within 15 days. Follow-up ultrasonography and endoscopy performed 30 days later confirmed full resolution of the mass, which was replaced by a focal mucosal depression. Histopathology at that site revealed chronic-active lymphoplasmacytic and neutrophilic enteritis with mild fibroplasia. A mild recurrence of duodenal thickening was observed after steroid tapering, which resolved upon dosage adjustment. The patient has remained clinically stable for 15 months with normal imaging and blood parameters. Full article

Background: Temporal lobe epilepsy (TLE), a prevalent refractory focal epilepsy frequently complicated by comorbid anxiety and depression, poses significant therapeutic challenges due to the inadequate efficacy of current antiepileptic drugs in seizure control. Carbon dots (CDs) demonstrate notable biological activities and represent a promising class of nanomedicines for TLE intervention. Methods: This study established an eco-friendly calcination protocol to synthesize a novel suspension of Crinis Carbonisatus-derived carbon dots (CC-CDs) as a candidate therapeutic for TLE. Results: In a TLE mouse model, the CC-CDs suspension significantly inhibited phosphorylation of the MAPK pathway (p-JNK, p-ERK, p-p38; p < 0.01, p < 0.05), leading to reduced levels of pro-inflammatory cytokines (IL-6, IL-1β, TNF-α; p < 0.01, p < 0.05), upregulation of TGF-β1 (p < 0.01, p < 0.05), and restoration of antioxidant enzyme activities (SOD, GSH, CAT; p < 0.01, p < 0.05). These modifications subsequently regulated the Glu/GABA balance, alleviating excitotoxicity (p < 0.05), attenuating neuronal damage and Nissl body loss in hippocampal CA1/CA3 regions, and improving cognitive function alongside reducing anxiety-like behaviors (p < 0.01, p < 0.05). In vitro, the CC-CDs suspension suppressed LPS-induced apoptosis in BV2 cells. Conclusions: The CC-CDs suspension ameliorates TLE by inhibiting MAPK signaling, thereby reducing neuroinflammation and oxidative stress, rectifying Glu/GABA imbalance, attenuating excitotoxicity, and ultimately improving behavioral deficits. These findings underscore the therapeutic potential of CC-CDs suspension for TLE treatment. Full article

Automatic detection of clue cells is crucial for rapid diagnosis of bacterial vaginosis (BV), but existing algorithms suffer from low sensitivity. This is because clue cells are highly similar to normal epithelial cells in terms of macroscopic size and shape. The key difference between clue cells and normal epithelial cells lies in the surface texture and edge morphology. To address this specific problem, we propose an clue cell detection algorithm named CA-YOLO. The contributions of our approach lie in two synergistic and custom-designed feature extraction modules: the context-aware module (CAM) extracts and captures bacterial distribution patterns on the surface of clue cells; and the shuffle global attention mechanism (SGAM) enhances cell edge features and suppresses irrelevant information. In addition, we integrate focal loss into the classification loss to alleviate the severe class imbalance problem inherent in clinical samples. Experimental results show that the proposed CA-YOLO achieves a sensitivity of 0.778, which is 9.2% higher than the baseline model, making the automated BV detection more reliable and feasible. Full article

In recent years, telecom fraud remains prevalent in many regions, severely impacting people’s daily lives and causing substantial economic losses. However, previous research has mainly relied on expert knowledge for feature engineering, which lags behind and struggles to adapt to the continuously evolving patterns of fraud effectively. In addition, the extreme imbalance in fraud amounts within real communication data hinders the development of deep learning methods. In response, we propose a feature transformation method to represent users’ communication behavior as comprehensively as possible, and develop a convolutional neural network (CNN) with a Focal Loss function to identify rare fraudulent activities in highly imbalanced data. Experimental results on a real-world dataset show that, under conditions of severe class imbalance, the proposed method significantly outperforms existing approaches in two key metrics: recall (0.7850) and AUC (0.8662). Our work provides a new approach for telecommunication fraud detection, enabling the effective identification of fraudulent numbers. Full article

This study explores the use of conditional Generative Adversarial Networks (cGANs) for simulating urban morphology, a domain where such models remain underutilized but have significant potential to generate realistic and controllable city patterns. To explore this potential, this research includes several contributions: a bespoke model architecture that integrates attention mechanisms with visual reasoning through a generalized conditioning layer. A novel mechanism that enables the steering of urban pattern generation through the use of statistical input distributions, the development of a novel and comprehensive training dataset, meticulously derived from open-source geospatial data of Berlin. Our model is trained using a hybrid loss function, combining adversarial, focal and L1 losses to ensure perceptual realism, address challenging fine-grained features, and enforce pixel-level accuracy. Model performance was assessed through a combination of qualitative visual analysis and quantitative evaluation using metrics such as Kullback–Leibler Divergence (KL Divergence), Structural Similarity Index (SSIM), and Dice Coefficient. The proposed approach has demonstrated effectiveness in generating realistic and spatially coherent urban patterns, with promising potential for controllability. In addition to showcasing its strengths, we also highlight the limitations and outline future directions for advancing future work. Full article

Background: Severe class imbalance limits reliable tabular AI in manufacturing, finance, and healthcare. Methods: We built a modular pipeline comprising correlation-aware seriation; a hybrid convolutional neural network (CNN)–transformer–Bidirectional Long Short-Term Memory (BiLSTM) encoder; variational autoencoder (VAE)-based minority augmentation; and deep/tree ensemble heads (XGBoost and Support Vector Machine, SVM). We benchmarked the Synthetic Minority Oversampling Technique (SMOTE) and ADASYN under identical protocols. Focal loss and ensemble weights were tuned per dataset. The primary metric was the Area Under the Precision–Recall Curve (AUPRC), with receiver operating characteristic area under the curve (ROC AUC) as complementary. Synthetic-data fidelity was quantified by train-on-synthetic/test-on-real (TSTR) utility, two-sample discriminability (ROC AUC of a real-vs-synthetic classifier), and Maximum Mean Discrepancy (MMD²). Results: Across five datasets (SECOM, CREDIT, THYROID, APS, and UCI), augmentation was data-dependent: VAE led on APS (+3.66 pp AUPRC vs. SMOTE) and was competitive on CREDIT (+0.10 pp vs. None); the SMOTE dominated SECOM; no augmentation performed best for THYROID and UCI. Positional embedding (PE) with seriation helped when strong local correlations were present. Ensembles typically favored XGBoost while benefiting from the hybrid encoder. Efficiency profiling and a slim variant supported latency-sensitive use. Conclusions: A data-aware recipe emerged: prefer VAE when fidelity is high, the SMOTE on smoother minority manifolds, and no augmentation when baselines suffice; apply PE/seriation selectively and tune per dataset for robust, reproducible deployment. Full article

Abnormal shutdown detection in oilfield pumping units presents significant challenges, including degraded image quality under low-light conditions, difficulty in detecting small or obscured targets, and limited capabilities for dynamic state perception. Previous approaches, such as traditional visual inspection and conventional image processing, often struggle with these limitations. To address these challenges, this study proposes an intelligent method integrating multi-scale feature enhancement and low-light image optimization. Specifically, a lightweight low-light enhancement framework is developed based on the Zero-DCE algorithm, improving the deep curve estimation network (DCE-Net) and non-reference loss functions through training on oilfield multi-exposure datasets. This significantly enhances brightness and detail retention in complex lighting conditions. The DAFE-Net detection model incorporates a four-level feature pyramid (P3–P6), channel-spatial attention mechanisms (CBAM), and Focal-EIoU loss to improve localization of small/occluded targets. Inter-frame difference algorithms further analyze motion states for robust “pump-off” determination. Experimental results on 5000 annotated images show the DAFE-Net achieves 93.9% mAP@50%, 96.5% recall, and 35 ms inference time, outperforming YOLOv11 and Faster R-CNN. Field tests confirm 93.9% accuracy under extreme conditions (e.g., strong illumination fluctuations and dust occlusion), demonstrating the method’s effectiveness in enabling intelligent monitoring across seven operational areas in the Changqing Oilfield while offering a scalable solution for real-time dynamic anomaly detection in industrial equipment monitoring. Full article

Podocytes are highly specialized, terminally differentiated epithelial cells essential for maintaining the glomerular filtration barrier. Their limited regenerative capacity and high metabolic demands render them particularly susceptible to aging-related stress. Accumulating evidence indicates that podocyte aging, characterized by cellular senescence, mitochondrial dysfunction, autophagy impairment, and epigenetic alterations, significantly contributes to the pathogenesis of diverse glomerular diseases collectively termed podocytopathies. These include focal segmental glomerulosclerosis, membranous nephropathy, minimal change disease, diabetic kidney disease, and lupus nephritis. This review discusses the cellular and molecular mechanisms driving podocyte aging and explores how these alterations predispose to podocyte injury, loss, and dysfunction, ultimately culminating in podocytopathies. Furthermore, we highlight current and emerging therapeutic strategies that aim to preserve podocyte health by targeting aging-associated pathways. Understanding podocyte aging elucidates mechanisms of chronic kidney disease progression and identifies novel therapeutic strategies for age-specific interventions in podocytopathies. Full article