Ge complementary tunneling field-effect transistors（TFETs） are fabricated with the NiGe metal source/drain（S/D） structure. The dopant segregation method is employed to form the NiGe/Ge tunneling junctions of suffi...Ge complementary tunneling field-effect transistors（TFETs） are fabricated with the NiGe metal source/drain（S/D） structure. The dopant segregation method is employed to form the NiGe/Ge tunneling junctions of sufficiently high Schottky barrier heights. As a result, the Ge p-and n-TFETs exhibit decent electrical properties of large ON-state current and steep sub-threshold slope（S factor）. Especially, I_d of 0.2 μA/μm is revealed at V_g-V_（th） = V_d = ±0.5 V for Ge pTFETs,with the S factor of 28 mV/dec at 7 K.展开更多
Dear Editor,We read with interest the article of Kinori et al[1]titled’Pediatric Nd:YAG laser capsulotomy in the operating room:review of 87 cases’.Facilities for laser capsulotomy under general anesthesia are essen...Dear Editor,We read with interest the article of Kinori et al[1]titled’Pediatric Nd:YAG laser capsulotomy in the operating room:review of 87 cases’.Facilities for laser capsulotomy under general anesthesia are essential for young children and uncooperative patients undergoing cataract surgery.展开更多
Since the 18th CPC National Congress,General Secretary Xi Jinping has raised new requirements for the Party’s international work under the new situation,emphasizing that on the basis of summarizing
Since first International Textile Exhibition created by SPINEXPO,it has been dedicated to the display of the Yarns–Fibres–Knitwear, Knitted Fabrics,Innovative Textile
A simple configuration for the generation of a switchable dual-wavelength fiber ring laser is presented.The proposed configuration employs a short twin-core photonic crystal fiber acting as a Mach–Zehnder interferome...A simple configuration for the generation of a switchable dual-wavelength fiber ring laser is presented.The proposed configuration employs a short twin-core photonic crystal fiber acting as a Mach–Zehnder interferometer at room temperature.A polarization controller is further utilized to enable switchable dualwavelength operation.展开更多
Visible and infrared(RGB-IR)fusion object detection plays an important role in security,disaster relief,etc.In recent years,deep-learning-based RGB-IR fusion detection methods have been developing rapidly,but still st...Visible and infrared(RGB-IR)fusion object detection plays an important role in security,disaster relief,etc.In recent years,deep-learning-based RGB-IR fusion detection methods have been developing rapidly,but still struggle to deal with the complex and changing scenarios captured by drones,mainly due to two reasons:(A)RGB-IR fusion detectors are susceptible to inferior inputs that degrade performance and stability.(B)RGB-IR fusion detectors are susceptible to redundant features that reduce accuracy and efficiency.In this paper,an innovative RGB-IR fusion detection framework based on global-local feature optimization,named GLFDet,is proposed to improve the detection performance and efficiency of drone-captured objects.The key components of GLFDet include a Global Feature Optimization(GFO)module,a Local Feature Optimization(LFO)module and a Channel Separation Fusion(CSF)module.Specifically,GFO calculates the information content of the input image from the frequency domain and optimizes the features holistically.Then,LFO dynamically selects high-value features and filters out low-value features before fusion,which significantly improves the efficiency of fusion.Finally,CSF fuses the RGB and IR features across the corresponding channels,which avoids the rearrangement of the channel relationships and enhances the model stability.Extensive experimental results show that the proposed method achieves the best performance on three popular RGB-IR datasets Drone Vehicle,VEDAI,and LLVIP.In addition,GLFDet is more lightweight than other comparable models,making it more appealing to edge devices such as drones.The code is available at https://github.com/lao chen330/GLFDet.展开更多
Automated essay scoring(AES)systems have gained significant importance in educational settings,offering a scalable,efficient,and objective method for evaluating student essays.However,developing AES systems for Arabic...Automated essay scoring(AES)systems have gained significant importance in educational settings,offering a scalable,efficient,and objective method for evaluating student essays.However,developing AES systems for Arabic poses distinct challenges due to the language’s complex morphology,diglossia,and the scarcity of annotated datasets.This paper presents a hybrid approach to Arabic AES by combining text-based,vector-based,and embeddingbased similarity measures to improve essay scoring accuracy while minimizing the training data required.Using a large Arabic essay dataset categorized into thematic groups,the study conducted four experiments to evaluate the impact of feature selection,data size,and model performance.Experiment 1 established a baseline using a non-machine learning approach,selecting top-N correlated features to predict essay scores.The subsequent experiments employed 5-fold cross-validation.Experiment 2 showed that combining embedding-based,text-based,and vector-based features in a Random Forest(RF)model achieved an R2 of 88.92%and an accuracy of 83.3%within a 0.5-point tolerance.Experiment 3 further refined the feature selection process,demonstrating that 19 correlated features yielded optimal results,improving R2 to 88.95%.In Experiment 4,an optimal data efficiency training approach was introduced,where training data portions increased from 5%to 50%.The study found that using just 10%of the data achieved near-peak performance,with an R2 of 85.49%,emphasizing an effective trade-off between performance and computational costs.These findings highlight the potential of the hybrid approach for developing scalable Arabic AES systems,especially in low-resource environments,addressing linguistic challenges while ensuring efficient data usage.展开更多
With the rapid expansion of drone applications,accurate detection of objects in aerial imagery has become crucial for intelligent transportation,urban management,and emergency rescue missions.However,existing methods ...With the rapid expansion of drone applications,accurate detection of objects in aerial imagery has become crucial for intelligent transportation,urban management,and emergency rescue missions.However,existing methods face numerous challenges in practical deployment,including scale variation handling,feature degradation,and complex backgrounds.To address these issues,we propose Edge-enhanced and Detail-Capturing You Only Look Once(EHDC-YOLO),a novel framework for object detection in Unmanned Aerial Vehicle(UAV)imagery.Based on the You Only Look Once version 11 nano(YOLOv11n)baseline,EHDC-YOLO systematically introduces several architectural enhancements:(1)a Multi-Scale Edge Enhancement(MSEE)module that leverages multi-scale pooling and edge information to enhance boundary feature extraction;(2)an Enhanced Feature Pyramid Network(EFPN)that integrates P2-level features with Cross Stage Partial(CSP)structures and OmniKernel convolutions for better fine-grained representation;and(3)Dynamic Head(DyHead)with multi-dimensional attention mechanisms for enhanced cross-scale modeling and perspective adaptability.Comprehensive experiments on the Vision meets Drones for Detection(VisDrone-DET)2019 dataset demonstrate that EHDC-YOLO achieves significant improvements,increasing mean Average Precision(mAP)@0.5 from 33.2%to 46.1%(an absolute improvement of 12.9 percentage points)and mAP@0.5:0.95 from 19.5%to 28.0%(an absolute improvement of 8.5 percentage points)compared with the YOLOv11n baseline,while maintaining a reasonable parameter count(2.81 M vs the baseline’s 2.58 M).Further ablation studies confirm the effectiveness of each proposed component,while visualization results highlight EHDC-YOLO’s superior performance in detecting objects and handling occlusions in complex drone scenarios.展开更多
Deep learning has made significant progress in the field of oriented object detection for remote sensing images.However,existing methods still face challenges when dealing with difficult tasks such as multi-scale targ...Deep learning has made significant progress in the field of oriented object detection for remote sensing images.However,existing methods still face challenges when dealing with difficult tasks such as multi-scale targets,complex backgrounds,and small objects in remote sensing.Maintaining model lightweight to address resource constraints in remote sensing scenarios while improving task completion for remote sensing tasks remains a research hotspot.Therefore,we propose an enhanced multi-scale feature extraction lightweight network EM-YOLO based on the YOLOv8s architecture,specifically optimized for the characteristics of large target scale variations,diverse orientations,and numerous small objects in remote sensing images.Our innovations lie in two main aspects:First,a dynamic snake convolution(DSC)is introduced into the backbone network to enhance the model’s feature extraction capability for oriented targets.Second,an innovative focusing-diffusion module is designed in the feature fusion neck to effectively integrate multi-scale feature information.Finally,we introduce Layer-Adaptive Sparsity for magnitude-based Pruning(LASP)method to perform lightweight network pruning to better complete tasks in resource-constrained scenarios.Experimental results on the lightweight platform Orin demonstrate that the proposed method significantly outperforms the original YOLOv8s model in oriented remote sensing object detection tasks,and achieves comparable or superior performance to state-of-the-art methods on three authoritative remote sensing datasets(DOTA v1.0,DOTA v1.5,and HRSC2016).展开更多
In response to the challenges in highway pavement distress detection,such as multiple defect categories,difficulties in feature extraction for different damage types,and slow identification speeds,this paper proposes ...In response to the challenges in highway pavement distress detection,such as multiple defect categories,difficulties in feature extraction for different damage types,and slow identification speeds,this paper proposes an enhanced pavement crack detection model named Star-YOLO11.This improved algorithm modifies the YOLO11 architecture by substituting the original C3k2 backbone network with a Star-s50 feature extraction network.The enhanced structure adjusts the number of stacked layers in the StarBlock module to optimize detection accuracy and improve model efficiency.To enhance the accuracy of pavement crack detection and improve model efficiency,three key modifications to the YOLO11 architecture are proposed.Firstly,the original C3k2 backbone is replaced with a StarBlock-based structure,forming the Star-s50 feature extraction backbone network.This lightweight redesign reduces computational complexity while maintaining detection precision.Secondly,to address the inefficiency of the original Partial Self-attention(PSA)mechanism in capturing localized crack features,the convolutional prior-aware Channel Prior Convolutional Attention(CPCA)mechanism is integrated into the channel dimension,creating a hybrid CPC-C2PSA attention structure.Thirdly,the original neck structure is upgraded to a Star Multi-Branch Auxiliary Feature Pyramid Network(SMAFPN)based on the Multi-Branch Auxiliary Feature Pyramid Network architecture,which adaptively fuses high-level semantic and low-level spatial information through Star-s50 connections and C3k2 extraction blocks.Additionally,a composite dataset augmentation strategy combining traditional and advanced augmentation techniques is developed.This strategy is validated on a specialized pavement dataset containing five distinct crack categories for comprehensive training and evaluation.Experimental results indicate that the proposed Star-YOLO11 achieves an accuracy of 89.9%(3.5%higher than the baseline),a mean average precision(mAP)of 90.3%(+2.6%),and an F1-score of 85.8%(+0.5%),while reducing the model size by 18.8%and reaching a frame rate of 225.73 frames per second(FPS)for real-time detection.It shows potential for lightweight deployment in pavement crack detection tasks.展开更多
Accurate purchase prediction in e-commerce critically depends on the quality of behavioral features.This paper proposes a layered and interpretable feature engineering framework that organizes user signals into three ...Accurate purchase prediction in e-commerce critically depends on the quality of behavioral features.This paper proposes a layered and interpretable feature engineering framework that organizes user signals into three layers:Basic,Conversion&Stability(efficiency and volatility across actions),and Advanced Interactions&Activity(crossbehavior synergies and intensity).Using real Taobao(Alibaba’s primary e-commerce platform)logs(57,976 records for 10,203 users;25 November–03 December 2017),we conducted a hierarchical,layer-wise evaluation that holds data splits and hyperparameters fixed while varying only the feature set to quantify each layer’s marginal contribution.Across logistic regression(LR),decision tree,random forest,XGBoost,and CatBoost models with stratified 5-fold cross-validation,the performance improvedmonotonically fromBasic to Conversion&Stability to Advanced features.With LR,F1 increased from 0.613(Basic)to 0.962(Advanced);boosted models achieved high discrimination(0.995 AUC Score)and an F1 score up to 0.983.Calibration and precision–recall analyses indicated strong ranking quality and acknowledged potential dataset and period biases given the short(9-day)window.By making feature contributions measurable and reproducible,the framework complements model-centric advances and offers a transparent blueprint for production-grade behavioralmodeling.The code and processed artifacts are publicly available,and future work will extend the validation to longer,seasonal datasets and hybrid approaches that combine automated feature learning with domain-driven design.展开更多
Discriminative region localization and efficient feature encoding are crucial for fine-grained object recognition.However,existing data augmentation methods struggle to accurately locate discriminative regions in comp...Discriminative region localization and efficient feature encoding are crucial for fine-grained object recognition.However,existing data augmentation methods struggle to accurately locate discriminative regions in complex backgrounds,small target objects,and limited training data,leading to poor recognition.Fine-grained images exhibit“small inter-class differences,”and while second-order feature encoding enhances discrimination,it often requires dual Convolutional Neural Networks(CNN),increasing training time and complexity.This study proposes a model integrating discriminative region localization and efficient second-order feature encoding.By ranking feature map channels via a fully connected layer,it selects high-importance channels to generate an enhanced map,accurately locating discriminative regions.Cropping and erasing augmentations further refine recognition.To improve efficiency,a novel second-order feature encoding module generates an attention map from the fourth convolutional group of Residual Network 50 layers(ResNet-50)and multiplies it with features from the fifth group,producing second-order features while reducing dimensionality and training time.Experiments on Caltech-University of California,San Diego Birds-200-2011(CUB-200-2011),Stanford Car,and Fine-Grained Visual Classification of Aircraft(FGVC Aircraft)datasets show state-of-the-art accuracy of 88.9%,94.7%,and 93.3%,respectively.展开更多
[Objectives]To analyze the clinical symptoms and epidemiological characteristics of 188 hospitalized pertussis cases in Jingzhou City.[Methods]Clinical data from 188 patients diagnosed with pertussis and admitted to t...[Objectives]To analyze the clinical symptoms and epidemiological characteristics of 188 hospitalized pertussis cases in Jingzhou City.[Methods]Clinical data from 188 patients diagnosed with pertussis and admitted to two tertiary hospitals in Jingzhou City between March and August 2024 were collected.Patients were randomly divided into three groups:<3-year-old,3—17-year-old,and≥18-year-old.A retrospective analysis was performed on their clinical features(including laboratory findings,disease course,and imaging characteristics)and epidemiological characteristics.[Results]In the<3-year-old group,28 cases(36.4%)were unvaccinated and 22 cases(28.6%)had received only one dose of the pertussis vaccine.In the 3—17-year-old group,91 cases(94.8%)had received four doses.Vaccination history was unknown for the≥18-year-old adult group.The<3-year-old group exhibited significantly higher incidences of cough with wheezing/dyspnea,paroxysmal spasmodic cough,cough with cyanosis or facial flushing,wheezes,and moist rales in the lungs compared to both the 3—17-year-old and≥18-year-old groups.Post-tussive vomiting was less frequent in the<3-year-old group than in the 3—17-year-old group but more frequent than in the≥18-year-old group;these differences were statistically significant(P<0.05).The≥18-year-old group had significantly lower incidences of cough with wheezing/dyspnea,paroxysmal spasmodic cough,cough with cyanosis or facial flushing,wheezes,and moist rales in the lungs compared to both the<3-year-old and 3—17-year-old groups(P<0.05).The proportion of cases with pneumonia and increased lung markings was higher in the<3-year-old group than in the 3—17-year-old group but lower than in the≥18-year-old group,showing statistically significant differences(P<0.05).The proportion of cases with pulmonary nodules and fibrotic foci was lower in the<3-year-old group than in both the 3—17-year-old and≥18-year-old groups,and these differences were also statistically significant(P<0.05).The proportion of pneumonia cases in the 3—17-year-old group was lower than in both the<3-year-old and≥18-year-old groups.The proportion of cases with increased lung markings was lower than in the<3-year-old group but higher than in the≥18-year-old group;these differences were statistically significant(P<0.05).The proportion of cases with pulmonary nodules and fibrotic foci in the 3—17-year-old group was higher than in the<3-year-old group but lower than in the≥18-year-old group,with statistically significant differences(P<0.05).The proportion of cases with pulmonary nodules and fibrotic foci was higher in the≥18-year-old group than in both the<3-year-old and 3—17-year-old groups,and these differences were also statistically significant(P<0.05).[Conclusions]Analysis of the clinical symptoms and epidemiological characteristics of 188 hospitalized pertussis cases in Jingzhou City contributes to enhancing the prevention and control of pertussis within the city.展开更多
Fault diagnosis of rolling bearings is crucial for ensuring the stable operation of mechanical equipment and production safety in industrial environments.However,due to the nonlinearity and non-stationarity of collect...Fault diagnosis of rolling bearings is crucial for ensuring the stable operation of mechanical equipment and production safety in industrial environments.However,due to the nonlinearity and non-stationarity of collected vibration signals,single-modal methods struggle to capture fault features fully.This paper proposes a rolling bearing fault diagnosis method based on multi-modal information fusion.The method first employs the Hippopotamus Optimization Algorithm(HO)to optimize the number of modes in Variational Mode Decomposition(VMD)to achieve optimal modal decomposition performance.It combines Convolutional Neural Networks(CNN)and Gated Recurrent Units(GRU)to extract temporal features from one-dimensional time-series signals.Meanwhile,the Markovian Transition Field(MTF)is used to transform one-dimensional signals into two-dimensional images for spatial feature mining.Through visualization techniques,the effectiveness of generated images from different parameter combinations is compared to determine the optimal parameter configuration.A multi-modal network(GSTCN)is constructed by integrating Swin-Transformer and the Convolutional Block Attention Module(CBAM),where the attention module is utilized to enhance fault features.Finally,the fault features extracted from different modalities are deeply fused and fed into a fully connected layer to complete fault classification.Experimental results show that the GSTCN model achieves an average diagnostic accuracy of 99.5%across three datasets,significantly outperforming existing comparison methods.This demonstrates that the proposed model has high diagnostic precision and good generalization ability,providing an efficient and reliable solution for rolling bearing fault diagnosis.展开更多
The Financial Technology(FinTech)sector has witnessed rapid growth,resulting in increasingly complex and high-volume digital transactions.Although this expansion improves efficiency and accessibility,it also introduce...The Financial Technology(FinTech)sector has witnessed rapid growth,resulting in increasingly complex and high-volume digital transactions.Although this expansion improves efficiency and accessibility,it also introduces significant vulnerabilities,including fraud,money laundering,and market manipulation.Traditional anomaly detection techniques often fail to capture the relational and dynamic characteristics of financial data.Graph Neural Networks(GNNs),capable of modeling intricate interdependencies among entities,have emerged as a powerful framework for detecting subtle and sophisticated anomalies.However,the high-dimensionality and inherent noise of FinTech datasets demand robust feature selection strategies to improve model scalability,performance,and interpretability.This paper presents a comprehensive survey of GNN-based approaches for anomaly detection in FinTech,with an emphasis on the synergistic role of feature selection.We examine the theoretical foundations of GNNs,review state-of-the-art feature selection techniques,analyze their integration with GNNs,and categorize prevalent anomaly types in FinTech applications.In addition,we discuss practical implementation challenges,highlight representative case studies,and propose future research directions to advance the field of graph-based anomaly detection in financial systems.展开更多
Gazetteer of Garze’s Natural Scenery This book is divided into five chapters,provides a comprehensive exploration of the geographical features and cultural context surrounding the thirteen renowned mountains,five maj...Gazetteer of Garze’s Natural Scenery This book is divided into five chapters,provides a comprehensive exploration of the geographical features and cultural context surrounding the thirteen renowned mountains,five major rivers,as well as numerous lakes,glaciers,and ancient trails within Garze Tibetan Autonomous Prefecture,Sichuan Province.By combining academic rigor with accessibility and substantial documentary value,it allows readers to survey all of Garze with a single volume in hand.Published by the Local Records Publishing House.展开更多
Rabies,a persistent and historic global zoonosis,continues to impose a significant public health burden,particularly in resource-limited regions.The causative agent,rabies virus(RABV;genus Lyssavirus,family Rhabdoviri...Rabies,a persistent and historic global zoonosis,continues to impose a significant public health burden,particularly in resource-limited regions.The causative agent,rabies virus(RABV;genus Lyssavirus,family Rhabdoviridae),possesses a surface glycoprotein(G)that is pivotal for virus entry and pathogenesis.Rabies virus glycoprotein(RABV-G)mediates binding to host cell receptor(s)and acidic-pH-dependent membrane fusion,enabling the release of RNA genome into the host cytoplasm.It is also the main target for neutralizing antibodies and the major component of rabies vaccines.In this review,we systematically summarize the structural features,functional mechanisms,and antiviral targeting strategies of RABV-G,emphasizing recent structural insights into its conformational dynamics.Key neutralizing epitopes and their recognition by monoclonal antibodies are discussed,along with antiviral strategies,including entry inhibitors,antibody therapies,and advanced vaccine platforms.Accumulating structural analyses indicate that the pH-dependent and reversible conformational transitions of this classⅢviral fusion protein underlie both viral infectivity and vulnerability to immune intervention.Collectively,available data establish that neutralizing epitopes on RABV-G are conformationally defined and dynamically regulated during fusion,thereby constraining viral entry and dictating the effectiveness of antibody-and entry inhibitor–mediated neutralization.Together,these findings establish RABV-G as the primary determinant of rabies virus virulence and immune control.By exploring the structural framework and prospective treatment modalities,we aim to enhance our understanding of rabies virus,particularly the glycoprotein G,and support ongoing initiatives to alleviate the burden of rabies,offering renewed optimism in the battle against this formidable infectious disease.展开更多
The initial noise present in the depth images obtained with RGB-D sensors is a combination of hardware limitations in addition to the environmental factors,due to the limited capabilities of sensors,which also produce...The initial noise present in the depth images obtained with RGB-D sensors is a combination of hardware limitations in addition to the environmental factors,due to the limited capabilities of sensors,which also produce poor computer vision results.The common image denoising techniques tend to remove significant image details and also remove noise,provided they are based on space and frequency filtering.The updated framework presented in this paper is a novel denoising model that makes use of Boruta-driven feature selection using a Long Short-Term Memory Autoencoder(LSTMAE).The Boruta algorithm identifies the most useful depth features that are used to maximize the spatial structure integrity and reduce redundancy.An LSTMAE is then used to process these selected features and model depth pixel sequences to generate robust,noise-resistant representations.The system uses the encoder to encode the input data into a latent space that has been compressed before it is decoded to retrieve the clean image.Experiments on a benchmark data set show that the suggested technique attains a PSNR of 45 dB and an SSIM of 0.90,which is 10 dB higher than the performance of conventional convolutional autoencoders and 15 times higher than that of the wavelet-based models.Moreover,the feature selection step will decrease the input dimensionality by 40%,resulting in a 37.5%reduction in training time and a real-time inference rate of 200 FPS.Boruta-LSTMAE framework,therefore,offers a highly efficient and scalable system for depth image denoising,with a high potential to be applied to close-range 3D systems,such as robotic manipulation and gesture-based interfaces.展开更多
基金Supported by the National Natural Science Foundation of China under Grant No 61504120the Zhejiang Provincial Natural Science Foundation of China under Grant No LR18F040001the Fundamental Research Funds for the Central Universities
文摘Ge complementary tunneling field-effect transistors（TFETs） are fabricated with the NiGe metal source/drain（S/D） structure. The dopant segregation method is employed to form the NiGe/Ge tunneling junctions of sufficiently high Schottky barrier heights. As a result, the Ge p-and n-TFETs exhibit decent electrical properties of large ON-state current and steep sub-threshold slope（S factor）. Especially, I_d of 0.2 μA/μm is revealed at V_g-V_（th） = V_d = ±0.5 V for Ge pTFETs,with the S factor of 28 mV/dec at 7 K.
文摘Dear Editor,We read with interest the article of Kinori et al[1]titled’Pediatric Nd:YAG laser capsulotomy in the operating room:review of 87 cases’.Facilities for laser capsulotomy under general anesthesia are essential for young children and uncooperative patients undergoing cataract surgery.
文摘Since the 18th CPC National Congress,General Secretary Xi Jinping has raised new requirements for the Party’s international work under the new situation,emphasizing that on the basis of summarizing
文摘Since first International Textile Exhibition created by SPINEXPO,it has been dedicated to the display of the Yarns–Fibres–Knitwear, Knitted Fabrics,Innovative Textile
基金Financial support for this work was provided by the Deanship of Scientific Research(DSR)of King Fahd University of Petroleum and Minerals under Grant No.FT121004
文摘A simple configuration for the generation of a switchable dual-wavelength fiber ring laser is presented.The proposed configuration employs a short twin-core photonic crystal fiber acting as a Mach–Zehnder interferometer at room temperature.A polarization controller is further utilized to enable switchable dualwavelength operation.
基金supported by the National Natural Science Foundation of China(No.62276204)the Fundamental Research Funds for the Central Universities,China(No.YJSJ24011)+1 种基金the Natural Science Basic Research Program of Shaanxi,China(Nos.2022JM-340 and 2023-JC-QN-0710)the China Postdoctoral Science Foundation(Nos.2020T130494 and 2018M633470)。
文摘Visible and infrared(RGB-IR)fusion object detection plays an important role in security,disaster relief,etc.In recent years,deep-learning-based RGB-IR fusion detection methods have been developing rapidly,but still struggle to deal with the complex and changing scenarios captured by drones,mainly due to two reasons:(A)RGB-IR fusion detectors are susceptible to inferior inputs that degrade performance and stability.(B)RGB-IR fusion detectors are susceptible to redundant features that reduce accuracy and efficiency.In this paper,an innovative RGB-IR fusion detection framework based on global-local feature optimization,named GLFDet,is proposed to improve the detection performance and efficiency of drone-captured objects.The key components of GLFDet include a Global Feature Optimization(GFO)module,a Local Feature Optimization(LFO)module and a Channel Separation Fusion(CSF)module.Specifically,GFO calculates the information content of the input image from the frequency domain and optimizes the features holistically.Then,LFO dynamically selects high-value features and filters out low-value features before fusion,which significantly improves the efficiency of fusion.Finally,CSF fuses the RGB and IR features across the corresponding channels,which avoids the rearrangement of the channel relationships and enhances the model stability.Extensive experimental results show that the proposed method achieves the best performance on three popular RGB-IR datasets Drone Vehicle,VEDAI,and LLVIP.In addition,GLFDet is more lightweight than other comparable models,making it more appealing to edge devices such as drones.The code is available at https://github.com/lao chen330/GLFDet.
基金funded by Deanship of Graduate studies and Scientific Research at Jouf University under grant No.(DGSSR-2024-02-01264).
文摘Automated essay scoring(AES)systems have gained significant importance in educational settings,offering a scalable,efficient,and objective method for evaluating student essays.However,developing AES systems for Arabic poses distinct challenges due to the language’s complex morphology,diglossia,and the scarcity of annotated datasets.This paper presents a hybrid approach to Arabic AES by combining text-based,vector-based,and embeddingbased similarity measures to improve essay scoring accuracy while minimizing the training data required.Using a large Arabic essay dataset categorized into thematic groups,the study conducted four experiments to evaluate the impact of feature selection,data size,and model performance.Experiment 1 established a baseline using a non-machine learning approach,selecting top-N correlated features to predict essay scores.The subsequent experiments employed 5-fold cross-validation.Experiment 2 showed that combining embedding-based,text-based,and vector-based features in a Random Forest(RF)model achieved an R2 of 88.92%and an accuracy of 83.3%within a 0.5-point tolerance.Experiment 3 further refined the feature selection process,demonstrating that 19 correlated features yielded optimal results,improving R2 to 88.95%.In Experiment 4,an optimal data efficiency training approach was introduced,where training data portions increased from 5%to 50%.The study found that using just 10%of the data achieved near-peak performance,with an R2 of 85.49%,emphasizing an effective trade-off between performance and computational costs.These findings highlight the potential of the hybrid approach for developing scalable Arabic AES systems,especially in low-resource environments,addressing linguistic challenges while ensuring efficient data usage.
文摘With the rapid expansion of drone applications,accurate detection of objects in aerial imagery has become crucial for intelligent transportation,urban management,and emergency rescue missions.However,existing methods face numerous challenges in practical deployment,including scale variation handling,feature degradation,and complex backgrounds.To address these issues,we propose Edge-enhanced and Detail-Capturing You Only Look Once(EHDC-YOLO),a novel framework for object detection in Unmanned Aerial Vehicle(UAV)imagery.Based on the You Only Look Once version 11 nano(YOLOv11n)baseline,EHDC-YOLO systematically introduces several architectural enhancements:(1)a Multi-Scale Edge Enhancement(MSEE)module that leverages multi-scale pooling and edge information to enhance boundary feature extraction;(2)an Enhanced Feature Pyramid Network(EFPN)that integrates P2-level features with Cross Stage Partial(CSP)structures and OmniKernel convolutions for better fine-grained representation;and(3)Dynamic Head(DyHead)with multi-dimensional attention mechanisms for enhanced cross-scale modeling and perspective adaptability.Comprehensive experiments on the Vision meets Drones for Detection(VisDrone-DET)2019 dataset demonstrate that EHDC-YOLO achieves significant improvements,increasing mean Average Precision(mAP)@0.5 from 33.2%to 46.1%(an absolute improvement of 12.9 percentage points)and mAP@0.5:0.95 from 19.5%to 28.0%(an absolute improvement of 8.5 percentage points)compared with the YOLOv11n baseline,while maintaining a reasonable parameter count(2.81 M vs the baseline’s 2.58 M).Further ablation studies confirm the effectiveness of each proposed component,while visualization results highlight EHDC-YOLO’s superior performance in detecting objects and handling occlusions in complex drone scenarios.
基金funded by the Hainan Province Science and Technology Special Fund under Grant ZDYF2024GXJS292.
文摘Deep learning has made significant progress in the field of oriented object detection for remote sensing images.However,existing methods still face challenges when dealing with difficult tasks such as multi-scale targets,complex backgrounds,and small objects in remote sensing.Maintaining model lightweight to address resource constraints in remote sensing scenarios while improving task completion for remote sensing tasks remains a research hotspot.Therefore,we propose an enhanced multi-scale feature extraction lightweight network EM-YOLO based on the YOLOv8s architecture,specifically optimized for the characteristics of large target scale variations,diverse orientations,and numerous small objects in remote sensing images.Our innovations lie in two main aspects:First,a dynamic snake convolution(DSC)is introduced into the backbone network to enhance the model’s feature extraction capability for oriented targets.Second,an innovative focusing-diffusion module is designed in the feature fusion neck to effectively integrate multi-scale feature information.Finally,we introduce Layer-Adaptive Sparsity for magnitude-based Pruning(LASP)method to perform lightweight network pruning to better complete tasks in resource-constrained scenarios.Experimental results on the lightweight platform Orin demonstrate that the proposed method significantly outperforms the original YOLOv8s model in oriented remote sensing object detection tasks,and achieves comparable or superior performance to state-of-the-art methods on three authoritative remote sensing datasets(DOTA v1.0,DOTA v1.5,and HRSC2016).
基金funded by the Jiangxi SASAC Science and Technology Innovation Special Project and the Key Technology Research and Application Promotion of Highway Overload Digital Solution.
文摘In response to the challenges in highway pavement distress detection,such as multiple defect categories,difficulties in feature extraction for different damage types,and slow identification speeds,this paper proposes an enhanced pavement crack detection model named Star-YOLO11.This improved algorithm modifies the YOLO11 architecture by substituting the original C3k2 backbone network with a Star-s50 feature extraction network.The enhanced structure adjusts the number of stacked layers in the StarBlock module to optimize detection accuracy and improve model efficiency.To enhance the accuracy of pavement crack detection and improve model efficiency,three key modifications to the YOLO11 architecture are proposed.Firstly,the original C3k2 backbone is replaced with a StarBlock-based structure,forming the Star-s50 feature extraction backbone network.This lightweight redesign reduces computational complexity while maintaining detection precision.Secondly,to address the inefficiency of the original Partial Self-attention(PSA)mechanism in capturing localized crack features,the convolutional prior-aware Channel Prior Convolutional Attention(CPCA)mechanism is integrated into the channel dimension,creating a hybrid CPC-C2PSA attention structure.Thirdly,the original neck structure is upgraded to a Star Multi-Branch Auxiliary Feature Pyramid Network(SMAFPN)based on the Multi-Branch Auxiliary Feature Pyramid Network architecture,which adaptively fuses high-level semantic and low-level spatial information through Star-s50 connections and C3k2 extraction blocks.Additionally,a composite dataset augmentation strategy combining traditional and advanced augmentation techniques is developed.This strategy is validated on a specialized pavement dataset containing five distinct crack categories for comprehensive training and evaluation.Experimental results indicate that the proposed Star-YOLO11 achieves an accuracy of 89.9%(3.5%higher than the baseline),a mean average precision(mAP)of 90.3%(+2.6%),and an F1-score of 85.8%(+0.5%),while reducing the model size by 18.8%and reaching a frame rate of 225.73 frames per second(FPS)for real-time detection.It shows potential for lightweight deployment in pavement crack detection tasks.
基金supported by the research fund of Hanyang University(HY-202500000001616).
文摘Accurate purchase prediction in e-commerce critically depends on the quality of behavioral features.This paper proposes a layered and interpretable feature engineering framework that organizes user signals into three layers:Basic,Conversion&Stability(efficiency and volatility across actions),and Advanced Interactions&Activity(crossbehavior synergies and intensity).Using real Taobao(Alibaba’s primary e-commerce platform)logs(57,976 records for 10,203 users;25 November–03 December 2017),we conducted a hierarchical,layer-wise evaluation that holds data splits and hyperparameters fixed while varying only the feature set to quantify each layer’s marginal contribution.Across logistic regression(LR),decision tree,random forest,XGBoost,and CatBoost models with stratified 5-fold cross-validation,the performance improvedmonotonically fromBasic to Conversion&Stability to Advanced features.With LR,F1 increased from 0.613(Basic)to 0.962(Advanced);boosted models achieved high discrimination(0.995 AUC Score)and an F1 score up to 0.983.Calibration and precision–recall analyses indicated strong ranking quality and acknowledged potential dataset and period biases given the short(9-day)window.By making feature contributions measurable and reproducible,the framework complements model-centric advances and offers a transparent blueprint for production-grade behavioralmodeling.The code and processed artifacts are publicly available,and future work will extend the validation to longer,seasonal datasets and hybrid approaches that combine automated feature learning with domain-driven design.
基金supported,in part,by the National Nature Science Foundation of China under Grant 62272236,62376128 and 62306139the Natural Science Foundation of Jiangsu Province under Grant BK20201136,BK20191401.
文摘Discriminative region localization and efficient feature encoding are crucial for fine-grained object recognition.However,existing data augmentation methods struggle to accurately locate discriminative regions in complex backgrounds,small target objects,and limited training data,leading to poor recognition.Fine-grained images exhibit“small inter-class differences,”and while second-order feature encoding enhances discrimination,it often requires dual Convolutional Neural Networks(CNN),increasing training time and complexity.This study proposes a model integrating discriminative region localization and efficient second-order feature encoding.By ranking feature map channels via a fully connected layer,it selects high-importance channels to generate an enhanced map,accurately locating discriminative regions.Cropping and erasing augmentations further refine recognition.To improve efficiency,a novel second-order feature encoding module generates an attention map from the fourth convolutional group of Residual Network 50 layers(ResNet-50)and multiplies it with features from the fifth group,producing second-order features while reducing dimensionality and training time.Experiments on Caltech-University of California,San Diego Birds-200-2011(CUB-200-2011),Stanford Car,and Fine-Grained Visual Classification of Aircraft(FGVC Aircraft)datasets show state-of-the-art accuracy of 88.9%,94.7%,and 93.3%,respectively.
文摘[Objectives]To analyze the clinical symptoms and epidemiological characteristics of 188 hospitalized pertussis cases in Jingzhou City.[Methods]Clinical data from 188 patients diagnosed with pertussis and admitted to two tertiary hospitals in Jingzhou City between March and August 2024 were collected.Patients were randomly divided into three groups:<3-year-old,3—17-year-old,and≥18-year-old.A retrospective analysis was performed on their clinical features(including laboratory findings,disease course,and imaging characteristics)and epidemiological characteristics.[Results]In the<3-year-old group,28 cases(36.4%)were unvaccinated and 22 cases(28.6%)had received only one dose of the pertussis vaccine.In the 3—17-year-old group,91 cases(94.8%)had received four doses.Vaccination history was unknown for the≥18-year-old adult group.The<3-year-old group exhibited significantly higher incidences of cough with wheezing/dyspnea,paroxysmal spasmodic cough,cough with cyanosis or facial flushing,wheezes,and moist rales in the lungs compared to both the 3—17-year-old and≥18-year-old groups.Post-tussive vomiting was less frequent in the<3-year-old group than in the 3—17-year-old group but more frequent than in the≥18-year-old group;these differences were statistically significant(P<0.05).The≥18-year-old group had significantly lower incidences of cough with wheezing/dyspnea,paroxysmal spasmodic cough,cough with cyanosis or facial flushing,wheezes,and moist rales in the lungs compared to both the<3-year-old and 3—17-year-old groups(P<0.05).The proportion of cases with pneumonia and increased lung markings was higher in the<3-year-old group than in the 3—17-year-old group but lower than in the≥18-year-old group,showing statistically significant differences(P<0.05).The proportion of cases with pulmonary nodules and fibrotic foci was lower in the<3-year-old group than in both the 3—17-year-old and≥18-year-old groups,and these differences were also statistically significant(P<0.05).The proportion of pneumonia cases in the 3—17-year-old group was lower than in both the<3-year-old and≥18-year-old groups.The proportion of cases with increased lung markings was lower than in the<3-year-old group but higher than in the≥18-year-old group;these differences were statistically significant(P<0.05).The proportion of cases with pulmonary nodules and fibrotic foci in the 3—17-year-old group was higher than in the<3-year-old group but lower than in the≥18-year-old group,with statistically significant differences(P<0.05).The proportion of cases with pulmonary nodules and fibrotic foci was higher in the≥18-year-old group than in both the<3-year-old and 3—17-year-old groups,and these differences were also statistically significant(P<0.05).[Conclusions]Analysis of the clinical symptoms and epidemiological characteristics of 188 hospitalized pertussis cases in Jingzhou City contributes to enhancing the prevention and control of pertussis within the city.
基金funded by the Jilin Provincial Department of Science and Technology,grant number 20230101208JC.
文摘Fault diagnosis of rolling bearings is crucial for ensuring the stable operation of mechanical equipment and production safety in industrial environments.However,due to the nonlinearity and non-stationarity of collected vibration signals,single-modal methods struggle to capture fault features fully.This paper proposes a rolling bearing fault diagnosis method based on multi-modal information fusion.The method first employs the Hippopotamus Optimization Algorithm(HO)to optimize the number of modes in Variational Mode Decomposition(VMD)to achieve optimal modal decomposition performance.It combines Convolutional Neural Networks(CNN)and Gated Recurrent Units(GRU)to extract temporal features from one-dimensional time-series signals.Meanwhile,the Markovian Transition Field(MTF)is used to transform one-dimensional signals into two-dimensional images for spatial feature mining.Through visualization techniques,the effectiveness of generated images from different parameter combinations is compared to determine the optimal parameter configuration.A multi-modal network(GSTCN)is constructed by integrating Swin-Transformer and the Convolutional Block Attention Module(CBAM),where the attention module is utilized to enhance fault features.Finally,the fault features extracted from different modalities are deeply fused and fed into a fully connected layer to complete fault classification.Experimental results show that the GSTCN model achieves an average diagnostic accuracy of 99.5%across three datasets,significantly outperforming existing comparison methods.This demonstrates that the proposed model has high diagnostic precision and good generalization ability,providing an efficient and reliable solution for rolling bearing fault diagnosis.
基金supported by Ho Chi Minh City Open University,Vietnam under grant number E2024.02.1CD and Suan Sunandha Rajabhat University,Thailand.
文摘The Financial Technology(FinTech)sector has witnessed rapid growth,resulting in increasingly complex and high-volume digital transactions.Although this expansion improves efficiency and accessibility,it also introduces significant vulnerabilities,including fraud,money laundering,and market manipulation.Traditional anomaly detection techniques often fail to capture the relational and dynamic characteristics of financial data.Graph Neural Networks(GNNs),capable of modeling intricate interdependencies among entities,have emerged as a powerful framework for detecting subtle and sophisticated anomalies.However,the high-dimensionality and inherent noise of FinTech datasets demand robust feature selection strategies to improve model scalability,performance,and interpretability.This paper presents a comprehensive survey of GNN-based approaches for anomaly detection in FinTech,with an emphasis on the synergistic role of feature selection.We examine the theoretical foundations of GNNs,review state-of-the-art feature selection techniques,analyze their integration with GNNs,and categorize prevalent anomaly types in FinTech applications.In addition,we discuss practical implementation challenges,highlight representative case studies,and propose future research directions to advance the field of graph-based anomaly detection in financial systems.
文摘Gazetteer of Garze’s Natural Scenery This book is divided into five chapters,provides a comprehensive exploration of the geographical features and cultural context surrounding the thirteen renowned mountains,five major rivers,as well as numerous lakes,glaciers,and ancient trails within Garze Tibetan Autonomous Prefecture,Sichuan Province.By combining academic rigor with accessibility and substantial documentary value,it allows readers to survey all of Garze with a single volume in hand.Published by the Local Records Publishing House.
基金supported by the National Natural Science Foundation of China(grant numbers 82272333 to G.L.and 32100114 to F.Y.)the 1.3.5 project for disciplines of excellence,West China Hospital,Sichuan University(grant number ZYGD23022 to G.L.)the National Postdoctoral Program for Innovative Talents of China(grant number BX20230243 to S.L.)。
文摘Rabies,a persistent and historic global zoonosis,continues to impose a significant public health burden,particularly in resource-limited regions.The causative agent,rabies virus(RABV;genus Lyssavirus,family Rhabdoviridae),possesses a surface glycoprotein(G)that is pivotal for virus entry and pathogenesis.Rabies virus glycoprotein(RABV-G)mediates binding to host cell receptor(s)and acidic-pH-dependent membrane fusion,enabling the release of RNA genome into the host cytoplasm.It is also the main target for neutralizing antibodies and the major component of rabies vaccines.In this review,we systematically summarize the structural features,functional mechanisms,and antiviral targeting strategies of RABV-G,emphasizing recent structural insights into its conformational dynamics.Key neutralizing epitopes and their recognition by monoclonal antibodies are discussed,along with antiviral strategies,including entry inhibitors,antibody therapies,and advanced vaccine platforms.Accumulating structural analyses indicate that the pH-dependent and reversible conformational transitions of this classⅢviral fusion protein underlie both viral infectivity and vulnerability to immune intervention.Collectively,available data establish that neutralizing epitopes on RABV-G are conformationally defined and dynamically regulated during fusion,thereby constraining viral entry and dictating the effectiveness of antibody-and entry inhibitor–mediated neutralization.Together,these findings establish RABV-G as the primary determinant of rabies virus virulence and immune control.By exploring the structural framework and prospective treatment modalities,we aim to enhance our understanding of rabies virus,particularly the glycoprotein G,and support ongoing initiatives to alleviate the burden of rabies,offering renewed optimism in the battle against this formidable infectious disease.
文摘The initial noise present in the depth images obtained with RGB-D sensors is a combination of hardware limitations in addition to the environmental factors,due to the limited capabilities of sensors,which also produce poor computer vision results.The common image denoising techniques tend to remove significant image details and also remove noise,provided they are based on space and frequency filtering.The updated framework presented in this paper is a novel denoising model that makes use of Boruta-driven feature selection using a Long Short-Term Memory Autoencoder(LSTMAE).The Boruta algorithm identifies the most useful depth features that are used to maximize the spatial structure integrity and reduce redundancy.An LSTMAE is then used to process these selected features and model depth pixel sequences to generate robust,noise-resistant representations.The system uses the encoder to encode the input data into a latent space that has been compressed before it is decoded to retrieve the clean image.Experiments on a benchmark data set show that the suggested technique attains a PSNR of 45 dB and an SSIM of 0.90,which is 10 dB higher than the performance of conventional convolutional autoencoders and 15 times higher than that of the wavelet-based models.Moreover,the feature selection step will decrease the input dimensionality by 40%,resulting in a 37.5%reduction in training time and a real-time inference rate of 200 FPS.Boruta-LSTMAE framework,therefore,offers a highly efficient and scalable system for depth image denoising,with a high potential to be applied to close-range 3D systems,such as robotic manipulation and gesture-based interfaces.
