Human Activity Recognition(HAR)is a novel area for computer vision.It has a great impact on healthcare,smart environments,and surveillance while is able to automatically detect human behavior.It plays a vital role in ...Human Activity Recognition(HAR)is a novel area for computer vision.It has a great impact on healthcare,smart environments,and surveillance while is able to automatically detect human behavior.It plays a vital role in many applications,such as smart home,healthcare,human computer interaction,sports analysis,and especially,intelligent surveillance.In this paper,we propose a robust and efficient HAR system by leveraging deep learning paradigms,including pre-trained models,CNN architectures,and their average-weighted fusion.However,due to the diversity of human actions and various environmental influences,as well as a lack of data and resources,achieving high recognition accuracy remain elusive.In this work,a weighted average ensemble technique is employed to fuse three deep learning models:EfficientNet,ResNet50,and a custom CNN.The results of this study indicate that using a weighted average ensemble strategy for developing more effective HAR models may be a promising idea for detection and classification of human activities.Experiments by using the benchmark dataset proved that the proposed weighted ensemble approach outperformed existing approaches in terms of accuracy and other key performance measures.The combined average-weighted ensemble of pre-trained and CNN models obtained an accuracy of 98%,compared to 97%,96%,and 95%for the customized CNN,EfficientNet,and ResNet50 models,respectively.展开更多
Wearable sensors integrated with deep learning techniques have the potential to revolutionize seamless human-machine interfaces for real-time health monitoring,clinical diagnosis,and robotic applications.Nevertheless,...Wearable sensors integrated with deep learning techniques have the potential to revolutionize seamless human-machine interfaces for real-time health monitoring,clinical diagnosis,and robotic applications.Nevertheless,it remains a critical challenge to simultaneously achieve desirable mechanical and electrical performance along with biocompatibility,adhesion,self-healing,and environmental robustness with excellent sensing metrics.Herein,we report a multifunctional,anti-freezing,selfadhesive,and self-healable organogel pressure sensor composed of cobalt nanoparticle encapsulated nitrogen-doped carbon nanotubes(CoN CNT)embedded in a polyvinyl alcohol-gelatin(PVA/GLE)matrix.Fabricated using a binary solvent system of water and ethylene glycol(EG),the CoN CNT/PVA/GLE organogel exhibits excellent flexibility,biocompatibility,and temperature tolerance with remarkable environmental stability.Electrochemical impedance spectroscopy confirms near-stable performance across a broad humidity range(40%-95%RH).Freeze-tolerant conductivity under sub-zero conditions(-20℃)is attributed to the synergistic role of CoN CNT and EG,preserving mobility and network integrity.The Co N CNT/PVA/GLE organogel sensor exhibits high sensitivity of 5.75 k Pa^(-1)in the detection range from 0 to 20 k Pa,ideal for subtle biomechanical motion detection.A smart human-machine interface for English letter recognition using deep learning achieved 98%accuracy.The organogel sensor utility was extended to detect human gestures like finger bending,wrist motion,and throat vibration during speech.展开更多
The exponential growth of video content has driven significant advancements in video summarization techniques in recent years.Breakthroughs in deep learning have been particularly transformative,enabling more effectiv...The exponential growth of video content has driven significant advancements in video summarization techniques in recent years.Breakthroughs in deep learning have been particularly transformative,enabling more effective detection of key information and creating new possibilities for video synopsis.To summarize recent progress and accelerate research in this field,this paper provides a comprehensive review of deep learning-based video summarization methods developed over the past decade.We begin by examining the research landscape of video abstraction technologies and identifying core challenges in video summarization.Subsequently,we systematically analyze prevailing deep learning frameworks and methodologies employed in current video summarization systems,offering researchers a clear roadmap of the field's evelution.Unlike previous review works,we first classify research papers based on the structural hierarchy of the video(from frame-level to shot-level to video-level),then further categorize them according to the summary backbone model(feature extraction and spatiotemporal modeling).This approach provides a more systematic and hierarchical organization of the documents.Following this comprehensive review,we summarize the benchmark datasets and evaluation metrics commonly employed in the field.Finally,we analyze persistent challenges and propose insightful directions for future research,providing a forward-looking perspective on video summarization technologies.This systematic literature review is of great reference value to new researchers exploring the fields of deep learning and video summarization.展开更多
Modern manufacturing processes have become more reliant on automation because of the accelerated transition from Industry 3.0 to Industry 4.0.Manual inspection of products on assembly lines remains inefficient,prone t...Modern manufacturing processes have become more reliant on automation because of the accelerated transition from Industry 3.0 to Industry 4.0.Manual inspection of products on assembly lines remains inefficient,prone to errors and lacks consistency,emphasizing the need for a reliable and automated inspection system.Leveraging both object detection and image segmentation approaches,this research proposes a vision-based solution for the detection of various kinds of tools in the toolkit using deep learning(DL)models.Two Intel RealSense D455f depth cameras were arranged in a top down configuration to capture both RGB and depth images of the toolkits.After applying multiple constraints and enhancing them through preprocessing and augmentation,a dataset consisting of 3300 annotated RGB-D photos was generated.Several DL models were selected through a comprehensive assessment of mean Average Precision(mAP),precision-recall equilibrium,inference latency(target≥30 FPS),and computational burden,resulting in a preference for YOLO and Region-based Convolutional Neural Networks(R-CNN)variants over ViT-based models due to the latter’s increased latency and resource requirements.YOLOV5,YOLOV8,YOLOV11,Faster R-CNN,and Mask R-CNN were trained on the annotated dataset and evaluated using key performance metrics(Recall,Accuracy,F1-score,and Precision).YOLOV11 demonstrated balanced excellence with 93.0%precision,89.9%recall,and a 90.6%F1-score in object detection,as well as 96.9%precision,95.3%recall,and a 96.5%F1-score in instance segmentation with an average inference time of 25 ms per frame(≈40 FPS),demonstrating real-time performance.Leveraging these results,a YOLOV11-based windows application was successfully deployed in a real-time assembly line environment,where it accurately processed live video streams to detect and segment tools within toolkits,demonstrating its practical effectiveness in industrial automation.The application is capable of precisely measuring socket dimensions by utilising edge detection techniques on YOLOv11 segmentation masks,in addition to detection and segmentation.This makes it possible to do specification-level quality control right on the assembly line,which improves the ability to examine things in real time.The implementation is a big step forward for intelligent manufacturing in the Industry 4.0 paradigm.It provides a scalable,efficient,and accurate way to do automated inspection and dimensional verification activities.展开更多
Underwater pipeline inspection plays a vital role in the proactive maintenance and management of critical marine infrastructure and subaquatic systems.However,the inspection of underwater pipelines presents a challeng...Underwater pipeline inspection plays a vital role in the proactive maintenance and management of critical marine infrastructure and subaquatic systems.However,the inspection of underwater pipelines presents a challenge due to factors such as light scattering,absorption,restricted visibility,and ambient noise.The advancement of deep learning has introduced powerful techniques for processing large amounts of unstructured and imperfect data collected from underwater environments.This study evaluated the efficacy of the You Only Look Once(YOLO)algorithm,a real-time object detection and localization model based on convolutional neural networks,in identifying and classifying various types of pipeline defects in underwater settings.YOLOv8,the latest evolution in the YOLO family,integrates advanced capabilities,such as anchor-free detection,a cross-stage partial network backbone for efficient feature extraction,and a feature pyramid network+path aggregation network neck for robust multi-scale object detection,which make it particularly well-suited for complex underwater environments.Due to the lack of suitable open-access datasets for underwater pipeline defects,a custom dataset was captured using a remotely operated vehicle in a controlled environment.This application has the following assets available for use.Extensive experimentation demonstrated that YOLOv8 X-Large consistently outperformed other models in terms of pipe defect detection and classification and achieved a strong balance between precision and recall in identifying pipeline cracks,rust,corners,defective welds,flanges,tapes,and holes.This research establishes the baseline performance of YOLOv8 for underwater defect detection and showcases its potential to enhance the reliability and efficiency of pipeline inspection tasks in challenging underwater environments.展开更多
The stator of the maglev track plays a crucial role in the operation of the maglev system.Currently,the efficiency of maglev track inspection is limited by several factors,including the large span of elevated structur...The stator of the maglev track plays a crucial role in the operation of the maglev system.Currently,the efficiency of maglev track inspection is limited by several factors,including the large span of elevated structures,manual visual inspection,short inspection window times,and limited GPS positioning accuracy.To address these issues,this paper proposes a deep learning-based method for detecting and locating stator surface damage.This study establishes a maglev track stator surface image dataset,trains different object detection models,and compares their performance.Ultimately,YOLO and ByteTrack object tracking algorithms were chosen as the basic framework and enhanced to achieve automatic identification of high-speed maglev track stator surface damage images and track and count stator surface localization feature images.By matching the identified damaged images with their corresponding stator segment and beam segment sequence numbers,the location of the damage is pinpointed to the corresponding stator segment,enabling rapid and accurate identification and localization of complex damage to the maglev track stator surface.展开更多
Nondestructive measurement technology of phenotype can provide substantial phenotypic data support for applications such as seedling breeding,management,and quality testing.The current method of measuring seedling phe...Nondestructive measurement technology of phenotype can provide substantial phenotypic data support for applications such as seedling breeding,management,and quality testing.The current method of measuring seedling phenotypes mainly relies on manual measurement which is inefficient,subjective and destroys samples.Therefore,the paper proposes a nondestructive measurement method for the canopy phenotype of the watermelon plug seedlings based on deep learning.The Azure Kinect was used to shoot canopy color images,depth images,and RGB-D images of the watermelon plug seedlings.The Mask-RCNN network was used to classify,segment,and count the canopy leaves of the watermelon plug seedlings.To reduce the error of leaf area measurement caused by mutual occlusion of leaves,the leaves were repaired by CycleGAN,and the depth images were restored by image processing.Then,the Delaunay triangulation was adopted to measure the leaf area in the leaf point cloud.The YOLOX target detection network was used to identify the growing point position of each seedling on the plug tray.Then the depth differences between the growing point and the upper surface of the plug tray were calculated to obtain plant height.The experiment results show that the nondestructive measurement algorithm proposed in this paper achieves good measurement performance for the watermelon plug seedlings from the 1 true-leaf to 3 true-leaf stages.The average relative error of measurement is 2.33%for the number of true leaves,4.59%for the number of cotyledons,8.37%for the leaf area,and 3.27%for the plant height.The experiment results demonstrate that the proposed algorithm in this paper provides an effective solution for the nondestructive measurement of the canopy phenotype of the plug seedlings.展开更多
Underground engineering projects such as deep tunnel excavation often encounter rockburst disasters accompanied by numerous microseismic events.Rapid interpretation of microseismic signals is crucial for the timely id...Underground engineering projects such as deep tunnel excavation often encounter rockburst disasters accompanied by numerous microseismic events.Rapid interpretation of microseismic signals is crucial for the timely identification of rockbursts.However,conventional processing encompasses multi-step workflows,including classification,denoising,picking,locating,and computational analysis,coupled with manual intervention,which collectively compromise the reliability of early warnings.To address these challenges,this study innovatively proposes the“microseismic stethoscope"-a multi-task machine learning and deep learning model designed for the automated processing of massive microseismic signals.This model efficiently extracts three key parameters that are necessary for recognizing rockburst disasters:rupture location,microseismic energy,and moment magnitude.Specifically,the model extracts raw waveform features from three dedicated sub-networks:a classifier for source zone classification,and two regressors for microseismic energy and moment magnitude estimation.This model demonstrates superior efficiency compared to traditional processing and semi-automated processing,reducing per-event processing time from 0.71 s to 0.49 s to merely 0.036 s.It concurrently achieves 98%accuracy in source zone classification,with microseismic energy and moment magnitude estimation errors of 0.13 and 0.05,respectively.This model has been well applied and validated in the Daxiagu Tunnel case in Sichuan,China.The application results indicate that the model is as accurate as traditional methods in determining source parameters,and thus can be used to identify potential geomechanical processes of rockburst disasters.By enhancing the signal processing reliability of microseismic events,the proposed model in this study presents a significant advancement in the identification of rockburst disasters.展开更多
Recent advances in deep learning have significantly improved flood detection and segmentation from aerial and satellite imagery.However,conventional convolutional neural networks(CNNs)often struggle in complex flood s...Recent advances in deep learning have significantly improved flood detection and segmentation from aerial and satellite imagery.However,conventional convolutional neural networks(CNNs)often struggle in complex flood scenarios involving reflections,occlusions,or indistinct boundaries due to limited contextual modeling.To address these challenges,we propose a hybrid flood segmentation framework that integrates a Vision Transformer(ViT)encoder with a U-Net decoder,enhanced by a novel Flood-Aware Refinement Block(FARB).The FARB module improves boundary delineation and suppresses noise by combining residual smoothing with spatial-channel attention mechanisms.We evaluate our model on a UAV-acquired flood imagery dataset,demonstrating that the proposed ViTUNet+FARB architecture outperforms existing CNN and Transformer-based models in terms of accuracy and mean Intersection over Union(mIoU).Detailed ablation studies further validate the contribution of each component,confirming that the FARB design significantly enhances segmentation quality.To its better performance and computational efficiency,the proposed framework is well-suited for flood monitoring and disaster response applications,particularly in resource-constrained environments.展开更多
Microscopy imaging is fundamental in analyzing bacterial morphology and dynamics,offering critical insights into bacterial physiology and pathogenicity.Image segmentation techniques enable quantitative analysis of bac...Microscopy imaging is fundamental in analyzing bacterial morphology and dynamics,offering critical insights into bacterial physiology and pathogenicity.Image segmentation techniques enable quantitative analysis of bacterial structures,facilitating precise measurement of morphological variations and population behaviors at single-cell resolution.This paper reviews advancements in bacterial image segmentation,emphasizing the shift from traditional thresholding and watershed methods to deep learning-driven approaches.Convolutional neural networks(CNNs),U-Net architectures,and three-dimensional(3D)frameworks excel at segmenting dense biofilms and resolving antibiotic-induced morphological changes.These methods combine automated feature extraction with physics-informed postprocessing.Despite progress,challenges persist in computational efficiency,cross-species generalizability,and integration with multimodal experimental workflows.Future progress will depend on improving model robustness across species and imaging modalities,integrating multimodal data for phenotype-function mapping,and developing standard pipelines that link computational tools with clinical diagnostics.These innovations will expand microbial phenotyping beyond structural analysis,enabling deeper insights into bacterial physiology and ecological interactions.展开更多
Deep learning and fatigue life prediction remain focal research areas in rail vehicle engineering.This study addresses the vibration fatigue of wheelset lifting lug in Chengdu Metro Line 1 bogies,aiming to develop a f...Deep learning and fatigue life prediction remain focal research areas in rail vehicle engineering.This study addresses the vibration fatigue of wheelset lifting lug in Chengdu Metro Line 1 bogies,aiming to develop a fatigue life prediction method for critical bogie components using deep learning models and measured track load spectra.Extensive field tests on Chengdu Metro Line 1 were conducted to acquire acceleration and stress response data of the wheelset lifting lug,generating training samples for the neural network system.Component stress responses were calculated via time-domain track acceleration and validated against in-situ stress measurements.Results show that neural network-fitted dynamic stress values exhibit excellent consistency with measured data,with errors constrained within 5%.This study validates the proposed small-sample deep learning approach as an effective and accurate solution for fatigue life prediction of critical bogie components under operational load conditions.展开更多
Waves are important physical phenomena in an ocean,and their accurate prediction is essential for ocean engineering,maritime traffic,and marine early warning systems.This study focuses on the Qinhuangdao Sea area loca...Waves are important physical phenomena in an ocean,and their accurate prediction is essential for ocean engineering,maritime traffic,and marine early warning systems.This study focuses on the Qinhuangdao Sea area located in the Bohai Sea,China.Herein,we use on-site wind data to correct the reanalysis wind data obtained from the European Centre for Medium-Range Weather Forecasts(ECMWF),improving the accuracy of boundary conditions.Then,we use the Simulating WAves Nearshore(SWAN)model to simulate the regional wave field over time.A regional wave-parameter prediction model is then developed using a limited number of sampled data(covering only 2 years,2020–2021);the model is based on the Whale Optimization Algorithm(WOA),convolutional neural networks(CNNs),and long short-term memory(LSTM)neural networks.WOA is used to optimize the CNN and LSTM framework;in this framework,CNN extracts spatial features,and the LSTM network captures temporal features,enabling accurate short and long-term predictions of wave height,period,and direction.The experimental results showed that despite the small sample size,the model achieves a goodness of fit of 0.9957 for wave height prediction,0.9973 for period,and 0.9749 for wave direction in short-term forecasting.As the prediction step size increases,the accuracy of the model decreases.When the prediction step size reaches 9 h,the root mean square error for the prediction of wave height,period,and direction increases to 0.2060 m,0.4582 s,and32.5358°,respectively.The reliability and applicability of the model are further validated by the experimental results.Our findings highlighted the potential of the developed model in operational wave forecasting,even with a limited number of sampled data.展开更多
Breast cancer screening programs rely heavily on mammography for early detection;however,diagnostic performance is strongly affected by inter-reader variability,breast density,and the limitations of conven-tional comp...Breast cancer screening programs rely heavily on mammography for early detection;however,diagnostic performance is strongly affected by inter-reader variability,breast density,and the limitations of conven-tional computer-aided detection systems.Recent advances in deep learning have enabled more robust and scalable solutions for large-scale screening,yet a systematic comparison of modern object detection architectures on nationally representative datasets remains limited.This study presents a comprehensive quantitative comparison of prominent deep learning–based object detection architectures for Artificial Intelligence-assisted mammography analysis using the MammosighTR dataset,developed within the Turkish National Breast Cancer Screening Program.The dataset comprises 12,740 patient cases collected between 2016 and 2022,annotated with BI-RADS categories,breast density levels,and lesion localization labels.A total of 31 models were evaluated,including One-Stage,Two-Stage,and Transformer-based architectures,under a unified experimental framework at both patient and breast levels.The results demonstrate that Two-Stage architectures consistently outperform One-Stage models,achieving approximately 2%–4%higher Macro F1-Scores and more balanced precision–recall trade-offs,with Double-Head R-CNN and Dynamic R-CNN yielding the highest overall performance(Macro F1≈0.84–0.86).This advantage is primarily attributed to the region proposal mechanism and improved class balance inherent to Two-Stage designs.One-Stage detectors exhibited higher sensitivity and faster inference,reaching Recall values above 0.88,but experienced minor reductions in Precision and overall accuracy(≈1%–2%)compared with Two-Stage models.Among Transformer-based architectures,Deformable DEtection TRansformer demonstrated strong robustness and consistency across datasets,achieving Macro F1-Scores comparable to CNN-based detectors(≈0.83–0.85)while exhibiting minimal performance degradation under distributional shifts.Breast density–based analysis revealed increased misclassification rates in medium-density categories(types B and C),whereas Transformer-based architectures maintained more stable performance in high-density type D tissue.These findings quantitatively confirm that both architectural design and tissue characteristics play a decisive role in diagnostic accuracy.Overall,the study provides a reproducible benchmark and highlights the potential of hybrid approaches that combine the accuracy of Two-Stage detectors with the contextual modeling capability of Transformer architectures for clinically reliable breast cancer screening systems.展开更多
Wind turbine blade defect detection faces persistent challenges in separating small,low-contrast surface faults from complex backgrounds while maintaining reliability under variable illumination and viewpoints.Conven-...Wind turbine blade defect detection faces persistent challenges in separating small,low-contrast surface faults from complex backgrounds while maintaining reliability under variable illumination and viewpoints.Conven-tional image-processing pipelines struggle with scalability and robustness,and recent deep learning methods remain sensitive to class imbalance and acquisition variability.This paper introduces TurbineBladeDetNet,a convolutional architecture combining dual-attention mechanisms with multi-path feature extraction for detecting five distinct blade fault types.Our approach employs both channel-wise and spatial attention modules alongside an Albumentations-driven augmentation strategy to handle dataset imbalance and capture condition variability.The model achieves 97.14%accuracy,98.65%precision,and 98.68%recall,yielding a 98.66%F1-score with 0.0110 s inference time.Class-specific analysis shows uniformly high sensitivity and specificity;lightning damage reaches 99.80%for sensitivity,precision,and F1-score,and crack achieves perfect precision and specificity with a 98.94%F1-score.Comparative evaluation against recent wind-turbine inspection approaches indicates higher performance in both accuracy and F1-score.The resulting balance of sensitivity and specificity limits both missed defects and false alarms,supporting reliable deployment in routine unmanned aerial vehicle(UAV)inspection.展开更多
The rapid growth of biomedical data,particularly multi-omics data including genomes,transcriptomics,proteomics,metabolomics,and epigenomics,medical research and clinical decision-making confront both new opportunities...The rapid growth of biomedical data,particularly multi-omics data including genomes,transcriptomics,proteomics,metabolomics,and epigenomics,medical research and clinical decision-making confront both new opportunities and obstacles.The huge and diversified nature of these datasets cannot always be managed using traditional data analysis methods.As a consequence,deep learning has emerged as a strong tool for analysing numerous omics data due to its ability to handle complex and non-linear relationships.This paper explores the fundamental concepts of deep learning and how they are used in multi-omics medical data mining.We demonstrate how autoencoders,variational autoencoders,multimodal models,attention mechanisms,transformers,and graph neural networks enable pattern analysis and recognition across all omics data.Deep learning has been found to be effective in illness classification,biomarker identification,gene network learning,and therapeutic efficacy prediction.We also consider critical problems like as data quality,model explainability,whether findings can be repeated,and computational power requirements.We now consider future elements of combining omics with clinical and imaging data,explainable AI,federated learning,and real-time diagnostics.Overall,this study emphasises the need of collaborating across disciplines to advance deep learning-based multi-omics research for precision medicine and comprehending complicated disorders.展开更多
Structural Health Monitoring(SHM)plays a critical role in ensuring the safety,integrity,longevity and economic efficiency of civil infrastructures.The field has undergone a profound transformation over the last few de...Structural Health Monitoring(SHM)plays a critical role in ensuring the safety,integrity,longevity and economic efficiency of civil infrastructures.The field has undergone a profound transformation over the last few decades,evolving from traditional methods—often reliant on visual inspections—to data-driven intelligent systems.This review paper analyzes this historical trajectory,beginning with the approaches that relied on modal parameters as primary damage indicators.The advent of advanced sensor technologies and increased computational power brings a significant change,making Machine Learning(ML)a viable and powerful tool for damage assessment.More recently,Deep Learning(DL)has emerged as a paradigm shift,allowing for more automated processing of large data sets(such as the structural vibration signals and other types of sensors)with excellent performance and accuracy,often surpassing previous methods.This paper systematically reviews these technological milestones—from traditional vibration-based methods to the current state-of-the-art in deep learning.Finally,it critically examines emerging trends—such as Digital Twins and Transformer-based architectures—and discusses future research directions that will shape the next generation of SHM systems for civil engineering.展开更多
Objective To develop a dual-branch deep learning framework for accurate multi-label classification of fundus diseases,addressing the key limitations of insufficient complementary feature extraction and inadequate cros...Objective To develop a dual-branch deep learning framework for accurate multi-label classification of fundus diseases,addressing the key limitations of insufficient complementary feature extraction and inadequate cross-modal feature fusion in existing automated diagnostic methods.Methods The fundus multi-label classification dataset with 12 disease categories(FMLC-12)dataset was constructed by integrating complementary samples from Ocular Disease Intelligent Recognition(ODIR)and Retinal Fundus Multi-Disease Image Dataset(RFMiD),yielding 6936 fundus images across 12 retinal pathology categories,and the framework was validated on both FMLC-12 and ODIR.Inspired by the holistic multi-regional assessment principle of the Five Wheels theory in traditional Chinese medicine(TCM)ophthalmology,the dualbranch multi-label network(DBMNet)was developed as a novel framework integrating complementary visual feature extraction with pathological correlation modeling.The architecture employed a TransNeXt backbone within a dual-branch design:one branch processed redgreen-blue(RGB)images to capture color-dependent features,such as vascular patterns and lesion morphology,while the other processed grayscale-converted images to enhance subtle textural details and contrast variations.A feature interaction module(FIM)effectively integrated the multi-scale features from both branches.Comprehensive ablation studies were conducted to evaluate the contributions of the dual-branch architecture and the FIM.The performance of DBMNet was compared against four state-of-the-art methods,including EfficientNet Ensemble,transfer learning-based convolutional neural network(CNN),BFENet,and EyeDeep-Net,using mean average precision(mAP),F1-score,and Cohen's kappa coefficient.Results The dual-branch architecture improved mAP by 15.44 percentage points over the single-branch TransNeXt baseline,increasing from 34.41%to 44.24%,and the addition of FIM further boosted mAP to 49.85%.On FMLC-12,DBMNet achieved an mAP of 49.85%,a Cohen’s kappa coefficient of 62.14%,and an F1-score of 70.21%.Compared with BFENet(mAP:45.42%,kappa:46.64%,F1-score:71.34%),DBMNet outperformed it by 4.43 percentage points in mAP and 15.50 percentage points in kappa,while BFENet achieved a marginally higher F1-score.On ODIR,DBMNet achieved an F1-score of 85.50%,comparable to state-of-the-art methods.Conclusion DBMNet effectively integrates RGB and grayscale visual modalities through a dual-branch architecture,significantly improving multi-label fundus disease classification.The framework not only addresses the issue of insufficient feature fusion in existing methods but also demonstrates outstanding performance in balancing detection across both common and rare diseases,providing a promising and clinically applicable pathway for standardized,intelligent fundus disease classification.展开更多
With the proliferation of Internet of Things(IoT)devices,securing these interconnected systems against cyberattacks has become a critical challenge.Traditional security paradigms often fail to cope with the scale and ...With the proliferation of Internet of Things(IoT)devices,securing these interconnected systems against cyberattacks has become a critical challenge.Traditional security paradigms often fail to cope with the scale and diversity of IoT network traffic.This paper presents a comparative benchmark of classic machine learning(ML)and state-of-the-art deep learning(DL)algorithms for IoT intrusion detection.Our methodology employs a twophased approach:a preliminary pilot study using a custom-generated dataset to establish baselines,followed by a comprehensive evaluation on the large-scale CICIoTDataset2023.We benchmarked algorithms including Random Forest,XGBoost,CNN,and StackedLSTM.The results indicate that while top-performingmodels frombothcategories achieve over 99%classification accuracy,this metric masks a crucial performance trade-off.We demonstrate that treebased ML ensembles exhibit superior precision(91%)in identifying benign traffic,making them effective at reducing false positives.Conversely,DL models demonstrate superior recall(96%),making them better suited for minimizing the interruption of legitimate traffic.We conclude that the selection of an optimal model is not merely a matter of maximizing accuracy but is a strategic choice dependent on the specific security priority either minimizing false alarms or ensuring service availability.Thiswork provides a practical framework for deploying context-aware security solutions in diverse IoT environments.展开更多
Online examinations have become a dominant assessment mode,increasing concerns over academic integrity.To address the critical challenge of detecting cheating behaviours,this study proposes a hybrid deep learning appr...Online examinations have become a dominant assessment mode,increasing concerns over academic integrity.To address the critical challenge of detecting cheating behaviours,this study proposes a hybrid deep learning approach that combines visual detection and temporal behaviour classification.The methodology utilises object detection models—You Only Look Once(YOLOv12),Faster Region-based Convolutional Neural Network(RCNN),and Single Shot Detector(SSD)MobileNet—integrated with classification models such as Convolutional Neural Networks(CNN),Bidirectional Gated Recurrent Unit(Bi-GRU),and CNN-LSTM(Long Short-Term Memory).Two distinct datasets were used:the Online Exam Proctoring(EOP)dataset from Michigan State University and the School of Computer Science,Duy Tan Unievrsity(SCS-DTU)dataset collected in a controlled classroom setting.A diverse set of cheating behaviours,including book usage,unauthorised interaction,internet access,and mobile phone use,was categorised.Comprehensive experiments evaluated the models based on accuracy,precision,recall,training time,inference speed,and memory usage.We evaluate nine detector-classifier pairings under a unified budget and score them via a calibrated harmonic mean of detection and classification accuracies,enabling deployment-oriented selection under latency and memory constraints.Macro-Precision/Recall/F1 and Receiver Operating Characteristic-Area Under the Curve(ROC-AUC)are reported for the top configurations,revealing consistent advantages of object-centric pipelines for fine-grained cheating cues.The highest overall score is achieved by YOLOv12+CNN(97.15%accuracy),while SSD-MobileNet+CNN provides the best speed-efficiency trade-off for edge devices.This research provides valuable insights into selecting and deploying appropriate deep learning models for maintaining exam integrity under varying resource constraints.展开更多
This systematic review aims to comprehensively examine and compare deep learning methods for brain tumor segmentation and classification using MRI and other imaging modalities,focusing on recent trends from 2022 to 20...This systematic review aims to comprehensively examine and compare deep learning methods for brain tumor segmentation and classification using MRI and other imaging modalities,focusing on recent trends from 2022 to 2025.The primary objective is to evaluate methodological advancements,model performance,dataset usage,and existing challenges in developing clinically robust AI systems.We included peer-reviewed journal articles and highimpact conference papers published between 2022 and 2025,written in English,that proposed or evaluated deep learning methods for brain tumor segmentation and/or classification.Excluded were non-open-access publications,books,and non-English articles.A structured search was conducted across Scopus,Google Scholar,Wiley,and Taylor&Francis,with the last search performed in August 2025.Risk of bias was not formally quantified but considered during full-text screening based on dataset diversity,validation methods,and availability of performance metrics.We used narrative synthesis and tabular benchmarking to compare performance metrics(e.g.,accuracy,Dice score)across model types(CNN,Transformer,Hybrid),imaging modalities,and datasets.A total of 49 studies were included(43 journal articles and 6 conference papers).These studies spanned over 9 public datasets(e.g.,BraTS,Figshare,REMBRANDT,MOLAB)and utilized a range of imaging modalities,predominantly MRI.Hybrid models,especially ResViT and UNetFormer,consistently achieved high performance,with classification accuracy exceeding 98%and segmentation Dice scores above 0.90 across multiple studies.Transformers and hybrid architectures showed increasing adoption post2023.Many studies lacked external validation and were evaluated only on a few benchmark datasets,raising concerns about generalizability and dataset bias.Few studies addressed clinical interpretability or uncertainty quantification.Despite promising results,particularly for hybrid deep learning models,widespread clinical adoption remains limited due to lack of validation,interpretability concerns,and real-world deployment barriers.展开更多
基金supported by Princess Nourah bint Abdulrahman University Researchers Supporting Project number(PNURSP2026R765),Princess Nourah bint Abdulrahman University,Riyadh,Saudi Arabia.
文摘Human Activity Recognition(HAR)is a novel area for computer vision.It has a great impact on healthcare,smart environments,and surveillance while is able to automatically detect human behavior.It plays a vital role in many applications,such as smart home,healthcare,human computer interaction,sports analysis,and especially,intelligent surveillance.In this paper,we propose a robust and efficient HAR system by leveraging deep learning paradigms,including pre-trained models,CNN architectures,and their average-weighted fusion.However,due to the diversity of human actions and various environmental influences,as well as a lack of data and resources,achieving high recognition accuracy remain elusive.In this work,a weighted average ensemble technique is employed to fuse three deep learning models:EfficientNet,ResNet50,and a custom CNN.The results of this study indicate that using a weighted average ensemble strategy for developing more effective HAR models may be a promising idea for detection and classification of human activities.Experiments by using the benchmark dataset proved that the proposed weighted ensemble approach outperformed existing approaches in terms of accuracy and other key performance measures.The combined average-weighted ensemble of pre-trained and CNN models obtained an accuracy of 98%,compared to 97%,96%,and 95%for the customized CNN,EfficientNet,and ResNet50 models,respectively.
基金supported by the Basic Science Research Program(2023R1A2C3004336,RS-202300243807)&Regional Leading Research Center(RS-202400405278)through the National Research Foundation of Korea(NRF)grant funded by the Korea Government(MSIT)。
文摘Wearable sensors integrated with deep learning techniques have the potential to revolutionize seamless human-machine interfaces for real-time health monitoring,clinical diagnosis,and robotic applications.Nevertheless,it remains a critical challenge to simultaneously achieve desirable mechanical and electrical performance along with biocompatibility,adhesion,self-healing,and environmental robustness with excellent sensing metrics.Herein,we report a multifunctional,anti-freezing,selfadhesive,and self-healable organogel pressure sensor composed of cobalt nanoparticle encapsulated nitrogen-doped carbon nanotubes(CoN CNT)embedded in a polyvinyl alcohol-gelatin(PVA/GLE)matrix.Fabricated using a binary solvent system of water and ethylene glycol(EG),the CoN CNT/PVA/GLE organogel exhibits excellent flexibility,biocompatibility,and temperature tolerance with remarkable environmental stability.Electrochemical impedance spectroscopy confirms near-stable performance across a broad humidity range(40%-95%RH).Freeze-tolerant conductivity under sub-zero conditions(-20℃)is attributed to the synergistic role of CoN CNT and EG,preserving mobility and network integrity.The Co N CNT/PVA/GLE organogel sensor exhibits high sensitivity of 5.75 k Pa^(-1)in the detection range from 0 to 20 k Pa,ideal for subtle biomechanical motion detection.A smart human-machine interface for English letter recognition using deep learning achieved 98%accuracy.The organogel sensor utility was extended to detect human gestures like finger bending,wrist motion,and throat vibration during speech.
基金supported by UKRI(EP/Z000025/1)Horizon Europe Programme under the MSCA grant for the ACMod project(101130271)。
文摘The exponential growth of video content has driven significant advancements in video summarization techniques in recent years.Breakthroughs in deep learning have been particularly transformative,enabling more effective detection of key information and creating new possibilities for video synopsis.To summarize recent progress and accelerate research in this field,this paper provides a comprehensive review of deep learning-based video summarization methods developed over the past decade.We begin by examining the research landscape of video abstraction technologies and identifying core challenges in video summarization.Subsequently,we systematically analyze prevailing deep learning frameworks and methodologies employed in current video summarization systems,offering researchers a clear roadmap of the field's evelution.Unlike previous review works,we first classify research papers based on the structural hierarchy of the video(from frame-level to shot-level to video-level),then further categorize them according to the summary backbone model(feature extraction and spatiotemporal modeling).This approach provides a more systematic and hierarchical organization of the documents.Following this comprehensive review,we summarize the benchmark datasets and evaluation metrics commonly employed in the field.Finally,we analyze persistent challenges and propose insightful directions for future research,providing a forward-looking perspective on video summarization technologies.This systematic literature review is of great reference value to new researchers exploring the fields of deep learning and video summarization.
文摘Modern manufacturing processes have become more reliant on automation because of the accelerated transition from Industry 3.0 to Industry 4.0.Manual inspection of products on assembly lines remains inefficient,prone to errors and lacks consistency,emphasizing the need for a reliable and automated inspection system.Leveraging both object detection and image segmentation approaches,this research proposes a vision-based solution for the detection of various kinds of tools in the toolkit using deep learning(DL)models.Two Intel RealSense D455f depth cameras were arranged in a top down configuration to capture both RGB and depth images of the toolkits.After applying multiple constraints and enhancing them through preprocessing and augmentation,a dataset consisting of 3300 annotated RGB-D photos was generated.Several DL models were selected through a comprehensive assessment of mean Average Precision(mAP),precision-recall equilibrium,inference latency(target≥30 FPS),and computational burden,resulting in a preference for YOLO and Region-based Convolutional Neural Networks(R-CNN)variants over ViT-based models due to the latter’s increased latency and resource requirements.YOLOV5,YOLOV8,YOLOV11,Faster R-CNN,and Mask R-CNN were trained on the annotated dataset and evaluated using key performance metrics(Recall,Accuracy,F1-score,and Precision).YOLOV11 demonstrated balanced excellence with 93.0%precision,89.9%recall,and a 90.6%F1-score in object detection,as well as 96.9%precision,95.3%recall,and a 96.5%F1-score in instance segmentation with an average inference time of 25 ms per frame(≈40 FPS),demonstrating real-time performance.Leveraging these results,a YOLOV11-based windows application was successfully deployed in a real-time assembly line environment,where it accurately processed live video streams to detect and segment tools within toolkits,demonstrating its practical effectiveness in industrial automation.The application is capable of precisely measuring socket dimensions by utilising edge detection techniques on YOLOv11 segmentation masks,in addition to detection and segmentation.This makes it possible to do specification-level quality control right on the assembly line,which improves the ability to examine things in real time.The implementation is a big step forward for intelligent manufacturing in the Industry 4.0 paradigm.It provides a scalable,efficient,and accurate way to do automated inspection and dimensional verification activities.
文摘Underwater pipeline inspection plays a vital role in the proactive maintenance and management of critical marine infrastructure and subaquatic systems.However,the inspection of underwater pipelines presents a challenge due to factors such as light scattering,absorption,restricted visibility,and ambient noise.The advancement of deep learning has introduced powerful techniques for processing large amounts of unstructured and imperfect data collected from underwater environments.This study evaluated the efficacy of the You Only Look Once(YOLO)algorithm,a real-time object detection and localization model based on convolutional neural networks,in identifying and classifying various types of pipeline defects in underwater settings.YOLOv8,the latest evolution in the YOLO family,integrates advanced capabilities,such as anchor-free detection,a cross-stage partial network backbone for efficient feature extraction,and a feature pyramid network+path aggregation network neck for robust multi-scale object detection,which make it particularly well-suited for complex underwater environments.Due to the lack of suitable open-access datasets for underwater pipeline defects,a custom dataset was captured using a remotely operated vehicle in a controlled environment.This application has the following assets available for use.Extensive experimentation demonstrated that YOLOv8 X-Large consistently outperformed other models in terms of pipe defect detection and classification and achieved a strong balance between precision and recall in identifying pipeline cracks,rust,corners,defective welds,flanges,tapes,and holes.This research establishes the baseline performance of YOLOv8 for underwater defect detection and showcases its potential to enhance the reliability and efficiency of pipeline inspection tasks in challenging underwater environments.
基金supported in part by the National Natural Science Foundation of China under Grant 52432012in part by the Shanghai Science and Technology Project with 25ZR1402508。
文摘The stator of the maglev track plays a crucial role in the operation of the maglev system.Currently,the efficiency of maglev track inspection is limited by several factors,including the large span of elevated structures,manual visual inspection,short inspection window times,and limited GPS positioning accuracy.To address these issues,this paper proposes a deep learning-based method for detecting and locating stator surface damage.This study establishes a maglev track stator surface image dataset,trains different object detection models,and compares their performance.Ultimately,YOLO and ByteTrack object tracking algorithms were chosen as the basic framework and enhanced to achieve automatic identification of high-speed maglev track stator surface damage images and track and count stator surface localization feature images.By matching the identified damaged images with their corresponding stator segment and beam segment sequence numbers,the location of the damage is pinpointed to the corresponding stator segment,enabling rapid and accurate identification and localization of complex damage to the maglev track stator surface.
基金funded by the National Key Research and Development Program of China(Grant No.2019YFD1001900)the HZAU-AGIS Cooperation Fund(Grant No.SZYJY2022006).
文摘Nondestructive measurement technology of phenotype can provide substantial phenotypic data support for applications such as seedling breeding,management,and quality testing.The current method of measuring seedling phenotypes mainly relies on manual measurement which is inefficient,subjective and destroys samples.Therefore,the paper proposes a nondestructive measurement method for the canopy phenotype of the watermelon plug seedlings based on deep learning.The Azure Kinect was used to shoot canopy color images,depth images,and RGB-D images of the watermelon plug seedlings.The Mask-RCNN network was used to classify,segment,and count the canopy leaves of the watermelon plug seedlings.To reduce the error of leaf area measurement caused by mutual occlusion of leaves,the leaves were repaired by CycleGAN,and the depth images were restored by image processing.Then,the Delaunay triangulation was adopted to measure the leaf area in the leaf point cloud.The YOLOX target detection network was used to identify the growing point position of each seedling on the plug tray.Then the depth differences between the growing point and the upper surface of the plug tray were calculated to obtain plant height.The experiment results show that the nondestructive measurement algorithm proposed in this paper achieves good measurement performance for the watermelon plug seedlings from the 1 true-leaf to 3 true-leaf stages.The average relative error of measurement is 2.33%for the number of true leaves,4.59%for the number of cotyledons,8.37%for the leaf area,and 3.27%for the plant height.The experiment results demonstrate that the proposed algorithm in this paper provides an effective solution for the nondestructive measurement of the canopy phenotype of the plug seedlings.
基金supported by the National Natural Science Foundation of China(Grant Nos.42130719 and 42177173)the Doctoral Direct Train Project of Chongqing Natural Science Foundation(Grant No.CSTB2023NSCQ-BSX0029).
文摘Underground engineering projects such as deep tunnel excavation often encounter rockburst disasters accompanied by numerous microseismic events.Rapid interpretation of microseismic signals is crucial for the timely identification of rockbursts.However,conventional processing encompasses multi-step workflows,including classification,denoising,picking,locating,and computational analysis,coupled with manual intervention,which collectively compromise the reliability of early warnings.To address these challenges,this study innovatively proposes the“microseismic stethoscope"-a multi-task machine learning and deep learning model designed for the automated processing of massive microseismic signals.This model efficiently extracts three key parameters that are necessary for recognizing rockburst disasters:rupture location,microseismic energy,and moment magnitude.Specifically,the model extracts raw waveform features from three dedicated sub-networks:a classifier for source zone classification,and two regressors for microseismic energy and moment magnitude estimation.This model demonstrates superior efficiency compared to traditional processing and semi-automated processing,reducing per-event processing time from 0.71 s to 0.49 s to merely 0.036 s.It concurrently achieves 98%accuracy in source zone classification,with microseismic energy and moment magnitude estimation errors of 0.13 and 0.05,respectively.This model has been well applied and validated in the Daxiagu Tunnel case in Sichuan,China.The application results indicate that the model is as accurate as traditional methods in determining source parameters,and thus can be used to identify potential geomechanical processes of rockburst disasters.By enhancing the signal processing reliability of microseismic events,the proposed model in this study presents a significant advancement in the identification of rockburst disasters.
基金supported by the National Research Foundation of Korea(NRF)grant funded by theKorea government(MSIT)(No.RS-2024-00405278)partially supported by the Jeju Industry-University Convergence District Project for Promoting Industry-Campus Cooperationfunded by the Ministry of Trade,Industry and Energy(MOTIE,Korea)[Project Name:Jeju Industry-University Convergence District Project for Promoting Industry-Campus Cooperation/Project Number:P0029950].
文摘Recent advances in deep learning have significantly improved flood detection and segmentation from aerial and satellite imagery.However,conventional convolutional neural networks(CNNs)often struggle in complex flood scenarios involving reflections,occlusions,or indistinct boundaries due to limited contextual modeling.To address these challenges,we propose a hybrid flood segmentation framework that integrates a Vision Transformer(ViT)encoder with a U-Net decoder,enhanced by a novel Flood-Aware Refinement Block(FARB).The FARB module improves boundary delineation and suppresses noise by combining residual smoothing with spatial-channel attention mechanisms.We evaluate our model on a UAV-acquired flood imagery dataset,demonstrating that the proposed ViTUNet+FARB architecture outperforms existing CNN and Transformer-based models in terms of accuracy and mean Intersection over Union(mIoU).Detailed ablation studies further validate the contribution of each component,confirming that the FARB design significantly enhances segmentation quality.To its better performance and computational efficiency,the proposed framework is well-suited for flood monitoring and disaster response applications,particularly in resource-constrained environments.
基金financially supported by the Open Project Program of Wuhan National Laboratory for Optoelectronics(No.2022WNLOKF009)the National Natural Science Foundation of China(No.62475216)+2 种基金the Key Research and Development Program of Shaanxi(No.2024GH-ZDXM-37)the Fujian Provincial Natural Science Foundation of China(No.2024J01060)the Startup Program of XMU,and the Fundamental Research Funds for the Central Universities.
文摘Microscopy imaging is fundamental in analyzing bacterial morphology and dynamics,offering critical insights into bacterial physiology and pathogenicity.Image segmentation techniques enable quantitative analysis of bacterial structures,facilitating precise measurement of morphological variations and population behaviors at single-cell resolution.This paper reviews advancements in bacterial image segmentation,emphasizing the shift from traditional thresholding and watershed methods to deep learning-driven approaches.Convolutional neural networks(CNNs),U-Net architectures,and three-dimensional(3D)frameworks excel at segmenting dense biofilms and resolving antibiotic-induced morphological changes.These methods combine automated feature extraction with physics-informed postprocessing.Despite progress,challenges persist in computational efficiency,cross-species generalizability,and integration with multimodal experimental workflows.Future progress will depend on improving model robustness across species and imaging modalities,integrating multimodal data for phenotype-function mapping,and developing standard pipelines that link computational tools with clinical diagnostics.These innovations will expand microbial phenotyping beyond structural analysis,enabling deeper insights into bacterial physiology and ecological interactions.
基金supported by the CRRC Original Technology TenYear Cultivation Program(Grant No.2022CYY007)。
文摘Deep learning and fatigue life prediction remain focal research areas in rail vehicle engineering.This study addresses the vibration fatigue of wheelset lifting lug in Chengdu Metro Line 1 bogies,aiming to develop a fatigue life prediction method for critical bogie components using deep learning models and measured track load spectra.Extensive field tests on Chengdu Metro Line 1 were conducted to acquire acceleration and stress response data of the wheelset lifting lug,generating training samples for the neural network system.Component stress responses were calculated via time-domain track acceleration and validated against in-situ stress measurements.Results show that neural network-fitted dynamic stress values exhibit excellent consistency with measured data,with errors constrained within 5%.This study validates the proposed small-sample deep learning approach as an effective and accurate solution for fatigue life prediction of critical bogie components under operational load conditions.
基金supported by the National Natural Science Foundation of China(Nos.52071057,52171247)the Liaoning Youth Elite Talent Program(No.XLYC220309)。
文摘Waves are important physical phenomena in an ocean,and their accurate prediction is essential for ocean engineering,maritime traffic,and marine early warning systems.This study focuses on the Qinhuangdao Sea area located in the Bohai Sea,China.Herein,we use on-site wind data to correct the reanalysis wind data obtained from the European Centre for Medium-Range Weather Forecasts(ECMWF),improving the accuracy of boundary conditions.Then,we use the Simulating WAves Nearshore(SWAN)model to simulate the regional wave field over time.A regional wave-parameter prediction model is then developed using a limited number of sampled data(covering only 2 years,2020–2021);the model is based on the Whale Optimization Algorithm(WOA),convolutional neural networks(CNNs),and long short-term memory(LSTM)neural networks.WOA is used to optimize the CNN and LSTM framework;in this framework,CNN extracts spatial features,and the LSTM network captures temporal features,enabling accurate short and long-term predictions of wave height,period,and direction.The experimental results showed that despite the small sample size,the model achieves a goodness of fit of 0.9957 for wave height prediction,0.9973 for period,and 0.9749 for wave direction in short-term forecasting.As the prediction step size increases,the accuracy of the model decreases.When the prediction step size reaches 9 h,the root mean square error for the prediction of wave height,period,and direction increases to 0.2060 m,0.4582 s,and32.5358°,respectively.The reliability and applicability of the model are further validated by the experimental results.Our findings highlighted the potential of the developed model in operational wave forecasting,even with a limited number of sampled data.
文摘Breast cancer screening programs rely heavily on mammography for early detection;however,diagnostic performance is strongly affected by inter-reader variability,breast density,and the limitations of conven-tional computer-aided detection systems.Recent advances in deep learning have enabled more robust and scalable solutions for large-scale screening,yet a systematic comparison of modern object detection architectures on nationally representative datasets remains limited.This study presents a comprehensive quantitative comparison of prominent deep learning–based object detection architectures for Artificial Intelligence-assisted mammography analysis using the MammosighTR dataset,developed within the Turkish National Breast Cancer Screening Program.The dataset comprises 12,740 patient cases collected between 2016 and 2022,annotated with BI-RADS categories,breast density levels,and lesion localization labels.A total of 31 models were evaluated,including One-Stage,Two-Stage,and Transformer-based architectures,under a unified experimental framework at both patient and breast levels.The results demonstrate that Two-Stage architectures consistently outperform One-Stage models,achieving approximately 2%–4%higher Macro F1-Scores and more balanced precision–recall trade-offs,with Double-Head R-CNN and Dynamic R-CNN yielding the highest overall performance(Macro F1≈0.84–0.86).This advantage is primarily attributed to the region proposal mechanism and improved class balance inherent to Two-Stage designs.One-Stage detectors exhibited higher sensitivity and faster inference,reaching Recall values above 0.88,but experienced minor reductions in Precision and overall accuracy(≈1%–2%)compared with Two-Stage models.Among Transformer-based architectures,Deformable DEtection TRansformer demonstrated strong robustness and consistency across datasets,achieving Macro F1-Scores comparable to CNN-based detectors(≈0.83–0.85)while exhibiting minimal performance degradation under distributional shifts.Breast density–based analysis revealed increased misclassification rates in medium-density categories(types B and C),whereas Transformer-based architectures maintained more stable performance in high-density type D tissue.These findings quantitatively confirm that both architectural design and tissue characteristics play a decisive role in diagnostic accuracy.Overall,the study provides a reproducible benchmark and highlights the potential of hybrid approaches that combine the accuracy of Two-Stage detectors with the contextual modeling capability of Transformer architectures for clinically reliable breast cancer screening systems.
文摘Wind turbine blade defect detection faces persistent challenges in separating small,low-contrast surface faults from complex backgrounds while maintaining reliability under variable illumination and viewpoints.Conven-tional image-processing pipelines struggle with scalability and robustness,and recent deep learning methods remain sensitive to class imbalance and acquisition variability.This paper introduces TurbineBladeDetNet,a convolutional architecture combining dual-attention mechanisms with multi-path feature extraction for detecting five distinct blade fault types.Our approach employs both channel-wise and spatial attention modules alongside an Albumentations-driven augmentation strategy to handle dataset imbalance and capture condition variability.The model achieves 97.14%accuracy,98.65%precision,and 98.68%recall,yielding a 98.66%F1-score with 0.0110 s inference time.Class-specific analysis shows uniformly high sensitivity and specificity;lightning damage reaches 99.80%for sensitivity,precision,and F1-score,and crack achieves perfect precision and specificity with a 98.94%F1-score.Comparative evaluation against recent wind-turbine inspection approaches indicates higher performance in both accuracy and F1-score.The resulting balance of sensitivity and specificity limits both missed defects and false alarms,supporting reliable deployment in routine unmanned aerial vehicle(UAV)inspection.
文摘The rapid growth of biomedical data,particularly multi-omics data including genomes,transcriptomics,proteomics,metabolomics,and epigenomics,medical research and clinical decision-making confront both new opportunities and obstacles.The huge and diversified nature of these datasets cannot always be managed using traditional data analysis methods.As a consequence,deep learning has emerged as a strong tool for analysing numerous omics data due to its ability to handle complex and non-linear relationships.This paper explores the fundamental concepts of deep learning and how they are used in multi-omics medical data mining.We demonstrate how autoencoders,variational autoencoders,multimodal models,attention mechanisms,transformers,and graph neural networks enable pattern analysis and recognition across all omics data.Deep learning has been found to be effective in illness classification,biomarker identification,gene network learning,and therapeutic efficacy prediction.We also consider critical problems like as data quality,model explainability,whether findings can be repeated,and computational power requirements.We now consider future elements of combining omics with clinical and imaging data,explainable AI,federated learning,and real-time diagnostics.Overall,this study emphasises the need of collaborating across disciplines to advance deep learning-based multi-omics research for precision medicine and comprehending complicated disorders.
基金The authors would like to thank CNPq(Conselho Nacional de Desenvolvimento Científico e Tecnológico)—grants 407256/2022-9,303550/2025-2,402533/2023-2 and 303982/2022-5FAPEMIG(Fundação de AmparoàPesquisa do Estado de Minas Gerais)—grants APQ-00032-24 and APD-01113-25 for their financial support.
文摘Structural Health Monitoring(SHM)plays a critical role in ensuring the safety,integrity,longevity and economic efficiency of civil infrastructures.The field has undergone a profound transformation over the last few decades,evolving from traditional methods—often reliant on visual inspections—to data-driven intelligent systems.This review paper analyzes this historical trajectory,beginning with the approaches that relied on modal parameters as primary damage indicators.The advent of advanced sensor technologies and increased computational power brings a significant change,making Machine Learning(ML)a viable and powerful tool for damage assessment.More recently,Deep Learning(DL)has emerged as a paradigm shift,allowing for more automated processing of large data sets(such as the structural vibration signals and other types of sensors)with excellent performance and accuracy,often surpassing previous methods.This paper systematically reviews these technological milestones—from traditional vibration-based methods to the current state-of-the-art in deep learning.Finally,it critically examines emerging trends—such as Digital Twins and Transformer-based architectures—and discusses future research directions that will shape the next generation of SHM systems for civil engineering.
基金Natural Science Foundation of Hunan Province(2025JJ90031)Key Research and Development Program of Hunan Province of China(23A0273)Hunan Provincial Administration of Traditional Chinese Medicine(A2023048).
文摘Objective To develop a dual-branch deep learning framework for accurate multi-label classification of fundus diseases,addressing the key limitations of insufficient complementary feature extraction and inadequate cross-modal feature fusion in existing automated diagnostic methods.Methods The fundus multi-label classification dataset with 12 disease categories(FMLC-12)dataset was constructed by integrating complementary samples from Ocular Disease Intelligent Recognition(ODIR)and Retinal Fundus Multi-Disease Image Dataset(RFMiD),yielding 6936 fundus images across 12 retinal pathology categories,and the framework was validated on both FMLC-12 and ODIR.Inspired by the holistic multi-regional assessment principle of the Five Wheels theory in traditional Chinese medicine(TCM)ophthalmology,the dualbranch multi-label network(DBMNet)was developed as a novel framework integrating complementary visual feature extraction with pathological correlation modeling.The architecture employed a TransNeXt backbone within a dual-branch design:one branch processed redgreen-blue(RGB)images to capture color-dependent features,such as vascular patterns and lesion morphology,while the other processed grayscale-converted images to enhance subtle textural details and contrast variations.A feature interaction module(FIM)effectively integrated the multi-scale features from both branches.Comprehensive ablation studies were conducted to evaluate the contributions of the dual-branch architecture and the FIM.The performance of DBMNet was compared against four state-of-the-art methods,including EfficientNet Ensemble,transfer learning-based convolutional neural network(CNN),BFENet,and EyeDeep-Net,using mean average precision(mAP),F1-score,and Cohen's kappa coefficient.Results The dual-branch architecture improved mAP by 15.44 percentage points over the single-branch TransNeXt baseline,increasing from 34.41%to 44.24%,and the addition of FIM further boosted mAP to 49.85%.On FMLC-12,DBMNet achieved an mAP of 49.85%,a Cohen’s kappa coefficient of 62.14%,and an F1-score of 70.21%.Compared with BFENet(mAP:45.42%,kappa:46.64%,F1-score:71.34%),DBMNet outperformed it by 4.43 percentage points in mAP and 15.50 percentage points in kappa,while BFENet achieved a marginally higher F1-score.On ODIR,DBMNet achieved an F1-score of 85.50%,comparable to state-of-the-art methods.Conclusion DBMNet effectively integrates RGB and grayscale visual modalities through a dual-branch architecture,significantly improving multi-label fundus disease classification.The framework not only addresses the issue of insufficient feature fusion in existing methods but also demonstrates outstanding performance in balancing detection across both common and rare diseases,providing a promising and clinically applicable pathway for standardized,intelligent fundus disease classification.
文摘With the proliferation of Internet of Things(IoT)devices,securing these interconnected systems against cyberattacks has become a critical challenge.Traditional security paradigms often fail to cope with the scale and diversity of IoT network traffic.This paper presents a comparative benchmark of classic machine learning(ML)and state-of-the-art deep learning(DL)algorithms for IoT intrusion detection.Our methodology employs a twophased approach:a preliminary pilot study using a custom-generated dataset to establish baselines,followed by a comprehensive evaluation on the large-scale CICIoTDataset2023.We benchmarked algorithms including Random Forest,XGBoost,CNN,and StackedLSTM.The results indicate that while top-performingmodels frombothcategories achieve over 99%classification accuracy,this metric masks a crucial performance trade-off.We demonstrate that treebased ML ensembles exhibit superior precision(91%)in identifying benign traffic,making them effective at reducing false positives.Conversely,DL models demonstrate superior recall(96%),making them better suited for minimizing the interruption of legitimate traffic.We conclude that the selection of an optimal model is not merely a matter of maximizing accuracy but is a strategic choice dependent on the specific security priority either minimizing false alarms or ensuring service availability.Thiswork provides a practical framework for deploying context-aware security solutions in diverse IoT environments.
文摘Online examinations have become a dominant assessment mode,increasing concerns over academic integrity.To address the critical challenge of detecting cheating behaviours,this study proposes a hybrid deep learning approach that combines visual detection and temporal behaviour classification.The methodology utilises object detection models—You Only Look Once(YOLOv12),Faster Region-based Convolutional Neural Network(RCNN),and Single Shot Detector(SSD)MobileNet—integrated with classification models such as Convolutional Neural Networks(CNN),Bidirectional Gated Recurrent Unit(Bi-GRU),and CNN-LSTM(Long Short-Term Memory).Two distinct datasets were used:the Online Exam Proctoring(EOP)dataset from Michigan State University and the School of Computer Science,Duy Tan Unievrsity(SCS-DTU)dataset collected in a controlled classroom setting.A diverse set of cheating behaviours,including book usage,unauthorised interaction,internet access,and mobile phone use,was categorised.Comprehensive experiments evaluated the models based on accuracy,precision,recall,training time,inference speed,and memory usage.We evaluate nine detector-classifier pairings under a unified budget and score them via a calibrated harmonic mean of detection and classification accuracies,enabling deployment-oriented selection under latency and memory constraints.Macro-Precision/Recall/F1 and Receiver Operating Characteristic-Area Under the Curve(ROC-AUC)are reported for the top configurations,revealing consistent advantages of object-centric pipelines for fine-grained cheating cues.The highest overall score is achieved by YOLOv12+CNN(97.15%accuracy),while SSD-MobileNet+CNN provides the best speed-efficiency trade-off for edge devices.This research provides valuable insights into selecting and deploying appropriate deep learning models for maintaining exam integrity under varying resource constraints.
文摘This systematic review aims to comprehensively examine and compare deep learning methods for brain tumor segmentation and classification using MRI and other imaging modalities,focusing on recent trends from 2022 to 2025.The primary objective is to evaluate methodological advancements,model performance,dataset usage,and existing challenges in developing clinically robust AI systems.We included peer-reviewed journal articles and highimpact conference papers published between 2022 and 2025,written in English,that proposed or evaluated deep learning methods for brain tumor segmentation and/or classification.Excluded were non-open-access publications,books,and non-English articles.A structured search was conducted across Scopus,Google Scholar,Wiley,and Taylor&Francis,with the last search performed in August 2025.Risk of bias was not formally quantified but considered during full-text screening based on dataset diversity,validation methods,and availability of performance metrics.We used narrative synthesis and tabular benchmarking to compare performance metrics(e.g.,accuracy,Dice score)across model types(CNN,Transformer,Hybrid),imaging modalities,and datasets.A total of 49 studies were included(43 journal articles and 6 conference papers).These studies spanned over 9 public datasets(e.g.,BraTS,Figshare,REMBRANDT,MOLAB)and utilized a range of imaging modalities,predominantly MRI.Hybrid models,especially ResViT and UNetFormer,consistently achieved high performance,with classification accuracy exceeding 98%and segmentation Dice scores above 0.90 across multiple studies.Transformers and hybrid architectures showed increasing adoption post2023.Many studies lacked external validation and were evaluated only on a few benchmark datasets,raising concerns about generalizability and dataset bias.Few studies addressed clinical interpretability or uncertainty quantification.Despite promising results,particularly for hybrid deep learning models,widespread clinical adoption remains limited due to lack of validation,interpretability concerns,and real-world deployment barriers.
