As urban landscapes evolve and vehicular volumes soar,traditional traffic monitoring systems struggle to scale,often failing under the complexities of dense,dynamic,and occluded environments.This paper introduces a no...As urban landscapes evolve and vehicular volumes soar,traditional traffic monitoring systems struggle to scale,often failing under the complexities of dense,dynamic,and occluded environments.This paper introduces a novel,unified deep learning framework for vehicle detection,tracking,counting,and classification in aerial imagery designed explicitly for modern smart city infrastructure demands.Our approach begins with adaptive histogram equalization to optimize aerial image clarity,followed by a cutting-edge scene parsing technique using Mask2Former,enabling robust segmentation even in visually congested settings.Vehicle detection leverages the latest YOLOv11 architecture,delivering superior accuracy in aerial contexts by addressing occlusion,scale variance,and fine-grained object differentiation.We incorporate the highly efficient ByteTrack algorithm for tracking,enabling seamless identity preservation across frames.Vehicle counting is achieved through an unsupervised DBSCAN-based method,ensuring adaptability to varying traffic densities.We further introduce a hybrid feature extraction module combining Convolutional Neural Networks(CNNs)with Zernike Moments,capturing both deep semantic and geometric signatures of vehicles.The final classification is powered by NASNet,a neural architecture search-optimized model,ensuring high accuracy across diverse vehicle types and orientations.Extensive evaluations of the VAID benchmark dataset demonstrate the system’s outstanding performance,achieving 96%detection,94%tracking,and 96.4%classification accuracy.On the UAVDT dataset,the system attains 95%detection,93%tracking,and 95%classification accuracy,confirming its robustness across diverse aerial traffic scenarios.These results establish new benchmarks in aerial traffic analysis and validate the framework’s scalability,making it a powerful and adaptable solution for next-generation intelligent transportation systems and urban surveillance.展开更多
Intelligent vehicle applications provide convenience but raise privacy and security concerns.Misuse of sensitive data,including vehicle location,and facial recognition information,poses a threat to user privacy.Hence,...Intelligent vehicle applications provide convenience but raise privacy and security concerns.Misuse of sensitive data,including vehicle location,and facial recognition information,poses a threat to user privacy.Hence,traffic classification is vital for promptly overseeing and controlling applications with sensitive information.In this paper,we propose ETNet,a framework that combines multiple features and leverages self-attention mechanisms to learn deep relationships between packets.ET-Net employs a multisimilarity triplet network to extract features from raw bytes,and exploits self-attention to capture long-range dependencies within packets in a session and contextual information features.Additionally,we utilizing the loss function to more effectively integrate information acquired from both byte sequences and their corresponding lengths.Through simulated evaluations on datasets with similar attributes,ET-Net demonstrates the ability to finely distinguish between nine categories of applications,achieving superior results compared to existing methods.展开更多
Unmanned Aerial Vehicles(UAVs)have become indispensable for intelligent traffic monitoring,particularly in low-light conditions,where traditional surveillance systems struggle.This study presents a novel deep learning...Unmanned Aerial Vehicles(UAVs)have become indispensable for intelligent traffic monitoring,particularly in low-light conditions,where traditional surveillance systems struggle.This study presents a novel deep learning-based framework for nighttime aerial vehicle detection and classification that addresses critical challenges of poor illumination,noise,and occlusions.Our pipeline integrates MSRCR enhancement with OPTICS segmentation to overcome low-light challenges,while YOLOv10 enables accurate vehicle localization.The framework employs GLOH and Dense-SIFT for discriminative feature extraction,optimized using the Whale Optimization Algorithm to enhance classification performance.A Swin Transformer-based classifier provides the final categorization,leveraging hierarchical attention mechanisms for robust performance.Extensive experimentation validates our approach,achieving detection mAP@0.5 scores of 91.5%(UAVDT)and 89.7%(VisDrone),alongside classification accuracies of 95.50%and 92.67%,respectively.These results outperform state-of-the-art methods by up to 5.10%in accuracy and 4.2%in mAP,demonstrating the framework’s effectiveness for real-time aerial surveillance and intelligent traffic management in challenging nighttime environments.展开更多
In recent decades,the proliferation of email communication has markedly escalated,resulting in a concomitant surge in spam emails that congest networks and presenting security risks.This study introduces an innovative...In recent decades,the proliferation of email communication has markedly escalated,resulting in a concomitant surge in spam emails that congest networks and presenting security risks.This study introduces an innovative spam detection method utilizing the Horse Herd Optimization Algorithm(HHOA),designed for binary classification within multi⁃objective framework.The method proficiently identifies essential features,minimizing redundancy and improving classification precision.The suggested HHOA attained an impressive accuracy of 97.21%on the Kaggle email dataset,with precision of 94.30%,recall of 90.50%,and F1⁃score of 92.80%.Compared to conventional techniques,such as Support Vector Machine(93.89%accuracy),Random Forest(96.14%accuracy),and K⁃Nearest Neighbours(92.08%accuracy),HHOA exhibited enhanced performance with reduced computing complexity.The suggested method demonstrated enhanced feature selection efficiency,decreasing the number of selected features while maintaining high classification accuracy.The results underscore the efficacy of HHOA in spam identification and indicate its potential for further applications in practical email filtering systems.展开更多
Visual diagnosis of skin cancer is challenging due to subtle inter-class similarities,variations in skin texture,the presence of hair,and inconsistent illumination.Deep learning models have shown promise in assisting ...Visual diagnosis of skin cancer is challenging due to subtle inter-class similarities,variations in skin texture,the presence of hair,and inconsistent illumination.Deep learning models have shown promise in assisting early detection,yet their performance is often limited by the severe class imbalance present in dermoscopic datasets.This paper proposes CANNSkin,a skin cancer classification framework that integrates a convolutional autoencoder with latent-space oversampling to address this imbalance.The autoencoder is trained to reconstruct lesion images,and its latent embeddings are used as features for classification.To enhance minority-class representation,the Synthetic Minority Oversampling Technique(SMOTE)is applied directly to the latent vectors before classifier training.The encoder and classifier are first trained independently and later fine-tuned end-to-end.On the HAM10000 dataset,CANNSkin achieves an accuracy of 93.01%,a macro-F1 of 88.54%,and an ROC–AUC of 98.44%,demonstrating strong robustness across ten test subsets.Evaluation on the more complex ISIC 2019 dataset further confirms the model’s effectiveness,where CANNSkin achieves 94.27%accuracy,93.95%precision,94.09%recall,and 99.02%F1-score,supported by high reconstruction fidelity(PSNR 35.03 dB,SSIM 0.86).These results demonstrate the effectiveness of our proposed latent-space balancing and fine-tuned representation learning as a new benchmark method for robust and accurate skin cancer classification across heterogeneous datasets.展开更多
Arrhythmias are a frequently occurring phenomenon in clinical practice,but how to accurately dis-tinguish subtle rhythm abnormalities remains an ongoing difficulty faced by the entire research community when conductin...Arrhythmias are a frequently occurring phenomenon in clinical practice,but how to accurately dis-tinguish subtle rhythm abnormalities remains an ongoing difficulty faced by the entire research community when conducting ECG-based studies.From a review of existing studies,two main factors appear to contribute to this problem:the uneven distribution of arrhythmia classes and the limited expressiveness of features learned by current models.To overcome these limitations,this study proposes a dual-path multimodal framework,termed DM-EHC(Dual-Path Multimodal ECG Heartbeat Classifier),for ECG-based heartbeat classification.The proposed framework links 1D ECG temporal features with 2D time–frequency features.By setting up the dual paths described above,the model can process more dimensions of feature information.The MIT-BIH arrhythmia database was selected as the baseline dataset for the experiments.Experimental results show that the proposed method outperforms single modalities and performs better for certain specific types of arrhythmias.The model achieved mean precision,recall,and F1 score of 95.14%,92.26%,and 93.65%,respectively.These results indicate that the framework is robust and has potential value in automated arrhythmia classification.展开更多
Near-Earth objects are important not only in studying the early formation of the Solar System,but also because they pose a serious hazard to humanity when they make close approaches to the Earth.Study of their physica...Near-Earth objects are important not only in studying the early formation of the Solar System,but also because they pose a serious hazard to humanity when they make close approaches to the Earth.Study of their physical properties can provide useful information on their origin,evolution,and hazard to human beings.However,it remains challenging to investigate small,newly discovered,near-Earth objects because of our limited observational window.This investigation seeks to determine the visible colors of near-Earth asteroids(NEAs),perform an initial taxonomic classification based on visible colors and analyze possible correlations between the distribution of taxonomic classification and asteroid size or orbital parameters.Observations were performed in the broadband BVRI Johnson−Cousins photometric system,applied to images from the Yaoan High Precision Telescope and the 1.88 m telescope at the Kottamia Astronomical Observatory.We present new photometric observations of 84 near-Earth asteroids,and classify 80 of them taxonomically,based on their photometric colors.We find that nearly half(46.3%)of the objects in our sample can be classified as S-complex,26.3%as C-complex,6%as D-complex,and 15.0%as X-complex;the remaining belong to the A-or V-types.Additionally,we identify three P-type NEAs in our sample,according to the Tholen scheme.The fractional abundances of the C/X-complex members with absolute magnitude H≥17.0 were more than twice as large as those with H<17.0.However,the fractions of C-and S-complex members with diameters≤1 km and>1 km are nearly equal,while X-complex members tend to have sub-kilometer diameters.In our sample,the C/D-complex objects are predominant among those with a Jovian Tisserand parameter of T_(J)<3.1.These bodies could have a cometary origin.C-and S-complex members account for a considerable proportion of the asteroids that are potentially hazardous.展开更多
Graph Neural Networks(GNNs)have proven highly effective for graph classification across diverse fields such as social networks,bioinformatics,and finance,due to their capability to learn complex graph structures.Howev...Graph Neural Networks(GNNs)have proven highly effective for graph classification across diverse fields such as social networks,bioinformatics,and finance,due to their capability to learn complex graph structures.However,despite their success,GNNs remain vulnerable to adversarial attacks that can significantly degrade their classification accuracy.Existing adversarial attack strategies primarily rely on label information to guide the attacks,which limits their applicability in scenarios where such information is scarce or unavailable.This paper introduces an innovative unsupervised attack method for graph classification,which operates without relying on label information,thereby enhancing its applicability in a broad range of scenarios.Specifically,our method first leverages a graph contrastive learning loss to learn high-quality graph embeddings by comparing different stochastic augmented views of the graphs.To effectively perturb the graphs,we then introduce an implicit estimator that measures the impact of various modifications on graph structures.The proposed strategy identifies and flips edges with the top-K highest scores,determined by the estimator,to maximize the degradation of the model’s performance.In addition,to defend against such attack,we propose a lightweight regularization-based defense mechanism that is specifically tailored to mitigate the structural perturbations introduced by our attack strategy.It enhances model robustness by enforcing embedding consistency and edge-level smoothness during training.We conduct experiments on six public TU graph classification datasets:NCI1,NCI109,Mutagenicity,ENZYMES,COLLAB,and DBLP_v1,to evaluate the effectiveness of our attack and defense strategies.Under an attack budget of 3,the maximum reduction in model accuracy reaches 6.67%on the Graph Convolutional Network(GCN)and 11.67%on the Graph Attention Network(GAT)across different datasets,indicating that our unsupervised method induces degradation comparable to state-of-the-art supervised attacks.Meanwhile,our defense achieves the highest accuracy recovery of 3.89%(GCN)and 5.00%(GAT),demonstrating improved robustness against structural perturbations.展开更多
Unmanned Aerial Vehicles(UAVs)are increasingly employed in traffic surveillance,urban planning,and infrastructure monitoring due to their cost-effectiveness,flexibility,and high-resolution imaging.However,vehicle dete...Unmanned Aerial Vehicles(UAVs)are increasingly employed in traffic surveillance,urban planning,and infrastructure monitoring due to their cost-effectiveness,flexibility,and high-resolution imaging.However,vehicle detection and classification in aerial imagery remain challenging due to scale variations from fluctuating UAV altitudes,frequent occlusions in dense traffic,and environmental noise,such as shadows and lighting inconsistencies.Traditional methods,including sliding-window searches and shallow learning techniques,struggle with computational inefficiency and robustness under dynamic conditions.To address these limitations,this study proposes a six-stage hierarchical framework integrating radiometric calibration,deep learning,and classical feature engineering.The workflow begins with radiometric calibration to normalize pixel intensities and mitigate sensor noise,followed by Conditional Random Field(CRF)segmentation to isolate vehicles.YOLOv9,equipped with a bi-directional feature pyramid network(BiFPN),ensures precise multi-scale object detection.Hybrid feature extraction employs Maximally Stable Extremal Regions(MSER)for stable contour detection,Binary Robust Independent Elementary Features(BRIEF)for texture encoding,and Affine-SIFT(ASIFT)for viewpoint invariance.Quadratic Discriminant Analysis(QDA)enhances feature discrimination,while a Probabilistic Neural Network(PNN)performs Bayesian probability-based classification.Tested on the Roundabout Aerial Imagery(15,474 images,985K instances)and AU-AIR(32,823 instances,7 classes)datasets,the model achieves state-of-the-art accuracy of 95.54%and 94.14%,respectively.Its superior performance in detecting small-scale vehicles and resolving occlusions highlights its potential for intelligent traffic systems.Future work will extend testing to nighttime and adverse weather conditions while optimizing real-time UAV inference.展开更多
To achieve low-carbon regulation of electric vehicle(EV)charging loads under the“dual carbon”goals,this paper proposes a coordinated scheduling strategy that integrates dynamic carbon factor prediction and multiobje...To achieve low-carbon regulation of electric vehicle(EV)charging loads under the“dual carbon”goals,this paper proposes a coordinated scheduling strategy that integrates dynamic carbon factor prediction and multiobjective optimization.First,a dual-convolution enhanced improved Crossformer prediction model is constructed,which employs parallel 1×1 global and 3×3 local convolutionmodules(Integrated Convolution Block,ICB)formultiscale feature extraction,combinedwith anAdaptive Spectral Block(ASB)to enhance time-series fluctuationmodeling.Based on high-precision predictions,a carbon-electricity cost joint optimization model is further designed to balance economic,environmental,and grid-friendly objectives.The model’s superiority was validated through a case study using real-world data from a renewable-heavy grid.Simulation results show that the proposed multi-objective strategy demonstrated a superior balance compared to baseline and benchmark models,achieving a 15.8%reduction in carbon emissions and a 5.2%reduction in economic costs,while still providing a substantial 22.2%reduction in the peak-valley difference.Its balanced performance significantly outperformed both a single-objective strategy and a state-of-the-art Model Predictive Control(MPC)benchmark,highlighting the advantage of a global optimization approach.This study provides theoretical and technical pathways for dynamic carbon factor-driven EV charging optimization.展开更多
Skin diseases affect millions worldwide.Early detection is key to preventing disfigurement,lifelong disability,or death.Dermoscopic images acquired in primary-care settings show high intra-class visual similarity and ...Skin diseases affect millions worldwide.Early detection is key to preventing disfigurement,lifelong disability,or death.Dermoscopic images acquired in primary-care settings show high intra-class visual similarity and severe class imbalance,and occasional imaging artifacts can create ambiguity for state-of-the-art convolutional neural networks(CNNs).We frame skin lesion recognition as graph-based reasoning and,to ensure fair evaluation and avoid data leakage,adopt a strict lesion-level partitioning strategy.Each image is first over-segmented using SLIC(Simple Linear Iterative Clustering)to produce perceptually homogeneous superpixels.These superpixels form the nodes of a region-adjacency graph whose edges encode spatial continuity.Node attributes are 1280-dimensional embeddings extracted with a lightweight yet expressive EfficientNet-B0 backbone,providing strong representational power at modest computational cost.The resulting graphs are processed by a five-layer Graph Attention Network(GAT)that learns to weight inter-node relationships dynamically and aggregates multi-hop context before classifying lesions into seven classes with a log-softmax output.Extensive experiments on the DermaMNIST benchmark show the proposed pipeline achieves 88.35%accuracy and 98.04%AUC,outperforming contemporary CNNs,AutoML approaches,and alternative graph neural networks.An ablation study indicates EfficientNet-B0 produces superior node descriptors compared with ResNet-18 and DenseNet,and that roughly five GAT layers strike a good balance between being too shallow and over-deep while avoiding oversmoothing.The method requires no data augmentation or external metadata,making it a drop-in upgrade for clinical computer-aided diagnosis systems.展开更多
With the recent increase in data volume and diversity,traditional text representation techniques are struggling to capture context,particularly in environments with sparse data.To address these challenges,this study p...With the recent increase in data volume and diversity,traditional text representation techniques are struggling to capture context,particularly in environments with sparse data.To address these challenges,this study proposes a new model,the Masked Joint Representation Model(MJRM).MJRM approximates the original hypothesis by leveraging multiple elements in a limited context.It dynamically adapts to changes in characteristics based on data distribution through three main components.First,masking-based representation learning,termed selective dynamic masking,integrates topic modeling and sentiment clustering to generate and train multiple instances across different data subsets,whose predictions are then aggregated with optimized weights.This design alleviates sparsity,suppresses noise,and preserves contextual structures.Second,regularization-based improvements are applied.Third,techniques for addressing sparse data are used to perform final inference.As a result,MJRM improves performance by up to 4%compared to existing AI techniques.In our experiments,we analyzed the contribution of each factor,demonstrating that masking,dynamic learning,and aggregating multiple instances complement each other to improve performance.This demonstrates that a masking-based multi-learning strategy is effective for context-aware sparse text classification,and can be useful even in challenging situations such as data shortage or data distribution variations.We expect that the approach can be extended to diverse fields such as sentiment analysis,spam filtering,and domain-specific document classification.展开更多
Rapidly-exploring Random Tree(RRT)and its variants have become foundational in path-planning research,yet in complex three-dimensional off-road environments their uniform blind sampling and limited safety guarantees l...Rapidly-exploring Random Tree(RRT)and its variants have become foundational in path-planning research,yet in complex three-dimensional off-road environments their uniform blind sampling and limited safety guarantees lead to slow convergence and force an unfavorable trade-off between path quality and traversal safety.To address these challenges,we introduce HS-APF-RRT*,a novel algorithm that fuses layered sampling,an enhanced Artificial Potential Field(APF),and a dynamic neighborhood-expansion mechanism.First,the workspace is hierarchically partitioned into macro,meso,and micro sampling layers,progressively biasing random samples toward safer,lower-energy regions.Second,we augment the traditional APF by incorporating a slope-dependent repulsive term,enabling stronger avoidance of steep obstacles.Third,a dynamic expansion strategy adaptively switches between 8 and 16 connected neighborhoods based on local obstacle density,striking an effective balance between search efficiency and collision-avoidance precision.In simulated off-road scenarios,HS-APF-RRT*is benchmarked against RRT*,GoalBiased RRT*,and APF-RRT*,and demonstrates significantly faster convergence,lower path-energy consumption,and enhanced safety margins.展开更多
Container transportation is pivotal in global trade due to its efficiency,safety,and cost-effectiveness.However,structural defects—particularly in grapple slots—can result in cargo damage,financial loss,and elevated...Container transportation is pivotal in global trade due to its efficiency,safety,and cost-effectiveness.However,structural defects—particularly in grapple slots—can result in cargo damage,financial loss,and elevated safety risks,including container drops during lifting operations.Timely and accurate inspection before and after transit is therefore essential.Traditional inspection methods rely heavily on manual observation of internal and external surfaces,which are time-consuming,resource-intensive,and prone to subjective errors.Container roofs pose additional challenges due to limited visibility,while grapple slots are especially vulnerable to wear from frequent use.This study proposes a two-stage automated detection framework targeting defects in container roof grapple slots.In the first stage,YOLOv7 is employed to localize grapple slot regions with high precision.In the second stage,ResNet50 classifies the extracted slots as either intact or defective.The results from both stages are integrated into a human-machine interface for real-time visualization and user verification.Experimental evaluations demonstrate that YOLOv7 achieves a 99%detection rate at 100 frames per second(FPS),while ResNet50 attains 87%classification accuracy at 34 FPS.Compared to some state of the arts,the proposed system offers significant speed,reliability,and usability improvements,enabling efficient defect identification and visual reconfirmation via the interface.展开更多
Re-entry gliding vehicles exhibit high maneuverability,making trajectory prediction a key factor in the effectiveness of defense systems.To overcome the limited fitting accuracy of existing methods and their poor adap...Re-entry gliding vehicles exhibit high maneuverability,making trajectory prediction a key factor in the effectiveness of defense systems.To overcome the limited fitting accuracy of existing methods and their poor adaptability to maneuver mode mutations,a trajectory prediction method is proposed that integrates online maneuver mode identification with dynamic modeling.Characteristic parameters are extracted from tracking data for parameterized modeling,enabling real-time identification of maneuver modes.In addition,a maneuver detection mechanism based on higher-order cumulants is introduced to detect lateral maneuver mutations and optimize the use of historical data.Simulation results show that the proposed method achieves accurate trajectory prediction during the glide phase and maintains high accuracy under maneuver mutations,significantly enhancing the prediction performance of both three-dimensional trajectories and ground tracks.展开更多
Evaluating the adversarial robustness of classification algorithms in machine learning is a crucial domain.However,current methods lack measurable and interpretable metrics.To address this issue,this paper introduces ...Evaluating the adversarial robustness of classification algorithms in machine learning is a crucial domain.However,current methods lack measurable and interpretable metrics.To address this issue,this paper introduces a visual evaluation index named confidence centroid skewing quadrilateral,which is based on a classification confidence-based confusion matrix,offering a quantitative and visual comparison of the adversarial robustness among different classification algorithms,and enhances intuitiveness and interpretability of attack impacts.We first conduct a validity test and sensitive analysis of the method.Then,prove its effectiveness through the experiments of five classification algorithms including artificial neural network(ANN),logistic regression(LR),support vector machine(SVM),convolutional neural network(CNN)and transformer against three adversarial attacks such as fast gradient sign method(FGSM),DeepFool,and projected gradient descent(PGD)attack.展开更多
Legal case classification involves the categorization of legal documents into predefined categories,which facilitates legal information retrieval and case management.However,real-world legal datasets often suffer from...Legal case classification involves the categorization of legal documents into predefined categories,which facilitates legal information retrieval and case management.However,real-world legal datasets often suffer from class imbalances due to the uneven distribution of case types across legal domains.This leads to biased model performance,in the form of high accuracy for overrepresented categories and underperformance for minority classes.To address this issue,in this study,we propose a data augmentation method that masks unimportant terms within a document selectively while preserving key terms fromthe perspective of the legal domain.This approach enhances data diversity and improves the generalization capability of conventional models.Our experiments demonstrate consistent improvements achieved by the proposed augmentation strategy in terms of accuracy and F1 score across all models,validating the effectiveness of the proposed method in legal case classification.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
With the increasing complexity of logistics operations,traditional static vehicle routing models are no longer sufficient.In practice,customer demands often arise dynamically,and multi-depot systems are commonly used ...With the increasing complexity of logistics operations,traditional static vehicle routing models are no longer sufficient.In practice,customer demands often arise dynamically,and multi-depot systems are commonly used to improve efficiency.This paper first introduces a vehicle routing problem with the goal of minimizing operating costs in a multi-depot environment with dynamic demand.New customers appear in the delivery process at any time and are periodically optimized according to time slices.Then,we propose a scheduling system TS-DPU based on an improved ant colony algorithm TS-ACO to solve this problem.The classical ant colony algorithm uses spatial distance to select nodes,while TS-ACO considers the impact of both temporal and spatial distance on node selection.Meanwhile,we adopt Cordeau’s Multi-Depot Vehicle Routing Problem with Time Windows(MDVRPTW)dataset to evaluate the performance of our system.According to the experimental results,TS-ACO,which considers spatial and temporal distance,is more effective than the classical ACO,which only considers spatial distance.展开更多
Traffic at urban intersections frequently encounters unexpected obstructions,resulting in congestion due to uncooperative and priority-based driving behavior.This paper presents an optimal right-turn coordination syst...Traffic at urban intersections frequently encounters unexpected obstructions,resulting in congestion due to uncooperative and priority-based driving behavior.This paper presents an optimal right-turn coordination system for Connected and Automated Vehicles(CAVs)at single-lane intersections,particularly in the context of left-hand side driving on roads.The goal is to facilitate smooth right turns for certain vehicles without creating bottlenecks.We consider that all approaching vehicles share relevant information through vehicular communications.The Intersection Coordination Unit(ICU)processes this information and communicates the optimal crossing or turning times to the vehicles.The primary objective of this coordination is to minimize overall traffic delays,which also helps improve the fuel consumption of vehicles.By considering information from upcoming vehicles at the intersection,the coordination system solves an optimization problem to determine the best timing for executing right turns,ultimately minimizing the total delay for all vehicles.The proposed coordination system is evaluated at a typical urban intersection,and its performance is compared to traditional traffic systems.Numerical simulation results indicate that the proposed coordination system significantly enhances the average traffic speed and fuel consumption compared to the traditional traffic system in various scenarios.展开更多
基金funded by the Open Access Initiative of the University of Bremen and the DFG via SuUB BremenThe authors extend their appreciation to the Deanship of Research and Graduate Studies at King Khalid University for funding this work through Large Group Project under grant number(RGP2/367/46)+1 种基金This research is supported and funded by Princess Nourah bint Abdulrahman University Researchers Supporting Project number(PNURSP2025R410)Princess Nourah bint Abdulrahman University,Riyadh,Saudi Arabia.
文摘As urban landscapes evolve and vehicular volumes soar,traditional traffic monitoring systems struggle to scale,often failing under the complexities of dense,dynamic,and occluded environments.This paper introduces a novel,unified deep learning framework for vehicle detection,tracking,counting,and classification in aerial imagery designed explicitly for modern smart city infrastructure demands.Our approach begins with adaptive histogram equalization to optimize aerial image clarity,followed by a cutting-edge scene parsing technique using Mask2Former,enabling robust segmentation even in visually congested settings.Vehicle detection leverages the latest YOLOv11 architecture,delivering superior accuracy in aerial contexts by addressing occlusion,scale variance,and fine-grained object differentiation.We incorporate the highly efficient ByteTrack algorithm for tracking,enabling seamless identity preservation across frames.Vehicle counting is achieved through an unsupervised DBSCAN-based method,ensuring adaptability to varying traffic densities.We further introduce a hybrid feature extraction module combining Convolutional Neural Networks(CNNs)with Zernike Moments,capturing both deep semantic and geometric signatures of vehicles.The final classification is powered by NASNet,a neural architecture search-optimized model,ensuring high accuracy across diverse vehicle types and orientations.Extensive evaluations of the VAID benchmark dataset demonstrate the system’s outstanding performance,achieving 96%detection,94%tracking,and 96.4%classification accuracy.On the UAVDT dataset,the system attains 95%detection,93%tracking,and 95%classification accuracy,confirming its robustness across diverse aerial traffic scenarios.These results establish new benchmarks in aerial traffic analysis and validate the framework’s scalability,making it a powerful and adaptable solution for next-generation intelligent transportation systems and urban surveillance.
基金supported by National Key Research and Development Program of China(2022YFB3104903)S&T Program of Hebei(No.SZX2020034).
文摘Intelligent vehicle applications provide convenience but raise privacy and security concerns.Misuse of sensitive data,including vehicle location,and facial recognition information,poses a threat to user privacy.Hence,traffic classification is vital for promptly overseeing and controlling applications with sensitive information.In this paper,we propose ETNet,a framework that combines multiple features and leverages self-attention mechanisms to learn deep relationships between packets.ET-Net employs a multisimilarity triplet network to extract features from raw bytes,and exploits self-attention to capture long-range dependencies within packets in a session and contextual information features.Additionally,we utilizing the loss function to more effectively integrate information acquired from both byte sequences and their corresponding lengths.Through simulated evaluations on datasets with similar attributes,ET-Net demonstrates the ability to finely distinguish between nine categories of applications,achieving superior results compared to existing methods.
基金supported through Princess Nourah bint Abdulrahman University Researchers Supporting Project number(PNURSP2025R508)Princess Nourah bint Abdulrahman University,Riyadh,Saudi Arabia。
文摘Unmanned Aerial Vehicles(UAVs)have become indispensable for intelligent traffic monitoring,particularly in low-light conditions,where traditional surveillance systems struggle.This study presents a novel deep learning-based framework for nighttime aerial vehicle detection and classification that addresses critical challenges of poor illumination,noise,and occlusions.Our pipeline integrates MSRCR enhancement with OPTICS segmentation to overcome low-light challenges,while YOLOv10 enables accurate vehicle localization.The framework employs GLOH and Dense-SIFT for discriminative feature extraction,optimized using the Whale Optimization Algorithm to enhance classification performance.A Swin Transformer-based classifier provides the final categorization,leveraging hierarchical attention mechanisms for robust performance.Extensive experimentation validates our approach,achieving detection mAP@0.5 scores of 91.5%(UAVDT)and 89.7%(VisDrone),alongside classification accuracies of 95.50%and 92.67%,respectively.These results outperform state-of-the-art methods by up to 5.10%in accuracy and 4.2%in mAP,demonstrating the framework’s effectiveness for real-time aerial surveillance and intelligent traffic management in challenging nighttime environments.
文摘In recent decades,the proliferation of email communication has markedly escalated,resulting in a concomitant surge in spam emails that congest networks and presenting security risks.This study introduces an innovative spam detection method utilizing the Horse Herd Optimization Algorithm(HHOA),designed for binary classification within multi⁃objective framework.The method proficiently identifies essential features,minimizing redundancy and improving classification precision.The suggested HHOA attained an impressive accuracy of 97.21%on the Kaggle email dataset,with precision of 94.30%,recall of 90.50%,and F1⁃score of 92.80%.Compared to conventional techniques,such as Support Vector Machine(93.89%accuracy),Random Forest(96.14%accuracy),and K⁃Nearest Neighbours(92.08%accuracy),HHOA exhibited enhanced performance with reduced computing complexity.The suggested method demonstrated enhanced feature selection efficiency,decreasing the number of selected features while maintaining high classification accuracy.The results underscore the efficacy of HHOA in spam identification and indicate its potential for further applications in practical email filtering systems.
基金supported and funded by the Deanship of Scientific Research at Imam Mohammad Ibn Saud Islamic University(IMSIU)(grant number IMSIU-DDRSP2601).
文摘Visual diagnosis of skin cancer is challenging due to subtle inter-class similarities,variations in skin texture,the presence of hair,and inconsistent illumination.Deep learning models have shown promise in assisting early detection,yet their performance is often limited by the severe class imbalance present in dermoscopic datasets.This paper proposes CANNSkin,a skin cancer classification framework that integrates a convolutional autoencoder with latent-space oversampling to address this imbalance.The autoencoder is trained to reconstruct lesion images,and its latent embeddings are used as features for classification.To enhance minority-class representation,the Synthetic Minority Oversampling Technique(SMOTE)is applied directly to the latent vectors before classifier training.The encoder and classifier are first trained independently and later fine-tuned end-to-end.On the HAM10000 dataset,CANNSkin achieves an accuracy of 93.01%,a macro-F1 of 88.54%,and an ROC–AUC of 98.44%,demonstrating strong robustness across ten test subsets.Evaluation on the more complex ISIC 2019 dataset further confirms the model’s effectiveness,where CANNSkin achieves 94.27%accuracy,93.95%precision,94.09%recall,and 99.02%F1-score,supported by high reconstruction fidelity(PSNR 35.03 dB,SSIM 0.86).These results demonstrate the effectiveness of our proposed latent-space balancing and fine-tuned representation learning as a new benchmark method for robust and accurate skin cancer classification across heterogeneous datasets.
基金supported by the Innovative Human Resource Development for Local Intel-lectualization program through the Institute of Information&Communications Technology Planning&Evaluation(IITP)grant funded by the Korea government(MSIT)(No.IITP-2026-2020-0-01741)the research fund of Hanyang University(HY-2025-1110).
文摘Arrhythmias are a frequently occurring phenomenon in clinical practice,but how to accurately dis-tinguish subtle rhythm abnormalities remains an ongoing difficulty faced by the entire research community when conducting ECG-based studies.From a review of existing studies,two main factors appear to contribute to this problem:the uneven distribution of arrhythmia classes and the limited expressiveness of features learned by current models.To overcome these limitations,this study proposes a dual-path multimodal framework,termed DM-EHC(Dual-Path Multimodal ECG Heartbeat Classifier),for ECG-based heartbeat classification.The proposed framework links 1D ECG temporal features with 2D time–frequency features.By setting up the dual paths described above,the model can process more dimensions of feature information.The MIT-BIH arrhythmia database was selected as the baseline dataset for the experiments.Experimental results show that the proposed method outperforms single modalities and performs better for certain specific types of arrhythmias.The model achieved mean precision,recall,and F1 score of 95.14%,92.26%,and 93.65%,respectively.These results indicate that the framework is robust and has potential value in automated arrhythmia classification.
基金funded by the China National Space Administration(KJSP2023020105)supported by the National Key R&D Program of China(Grant No.2023YFA1608100)+2 种基金the NSFC(Grant No.62227901)the Minor Planet Foundationsupported by the Egyptian Science,Technology&Innovation Funding Authority(STDF)under Grant No.48102.
文摘Near-Earth objects are important not only in studying the early formation of the Solar System,but also because they pose a serious hazard to humanity when they make close approaches to the Earth.Study of their physical properties can provide useful information on their origin,evolution,and hazard to human beings.However,it remains challenging to investigate small,newly discovered,near-Earth objects because of our limited observational window.This investigation seeks to determine the visible colors of near-Earth asteroids(NEAs),perform an initial taxonomic classification based on visible colors and analyze possible correlations between the distribution of taxonomic classification and asteroid size or orbital parameters.Observations were performed in the broadband BVRI Johnson−Cousins photometric system,applied to images from the Yaoan High Precision Telescope and the 1.88 m telescope at the Kottamia Astronomical Observatory.We present new photometric observations of 84 near-Earth asteroids,and classify 80 of them taxonomically,based on their photometric colors.We find that nearly half(46.3%)of the objects in our sample can be classified as S-complex,26.3%as C-complex,6%as D-complex,and 15.0%as X-complex;the remaining belong to the A-or V-types.Additionally,we identify three P-type NEAs in our sample,according to the Tholen scheme.The fractional abundances of the C/X-complex members with absolute magnitude H≥17.0 were more than twice as large as those with H<17.0.However,the fractions of C-and S-complex members with diameters≤1 km and>1 km are nearly equal,while X-complex members tend to have sub-kilometer diameters.In our sample,the C/D-complex objects are predominant among those with a Jovian Tisserand parameter of T_(J)<3.1.These bodies could have a cometary origin.C-and S-complex members account for a considerable proportion of the asteroids that are potentially hazardous.
基金funded by the National Key Research and Development Program of China(Grant No.2024YFE0209000)the NSFC(Grant No.U23B2019).
文摘Graph Neural Networks(GNNs)have proven highly effective for graph classification across diverse fields such as social networks,bioinformatics,and finance,due to their capability to learn complex graph structures.However,despite their success,GNNs remain vulnerable to adversarial attacks that can significantly degrade their classification accuracy.Existing adversarial attack strategies primarily rely on label information to guide the attacks,which limits their applicability in scenarios where such information is scarce or unavailable.This paper introduces an innovative unsupervised attack method for graph classification,which operates without relying on label information,thereby enhancing its applicability in a broad range of scenarios.Specifically,our method first leverages a graph contrastive learning loss to learn high-quality graph embeddings by comparing different stochastic augmented views of the graphs.To effectively perturb the graphs,we then introduce an implicit estimator that measures the impact of various modifications on graph structures.The proposed strategy identifies and flips edges with the top-K highest scores,determined by the estimator,to maximize the degradation of the model’s performance.In addition,to defend against such attack,we propose a lightweight regularization-based defense mechanism that is specifically tailored to mitigate the structural perturbations introduced by our attack strategy.It enhances model robustness by enforcing embedding consistency and edge-level smoothness during training.We conduct experiments on six public TU graph classification datasets:NCI1,NCI109,Mutagenicity,ENZYMES,COLLAB,and DBLP_v1,to evaluate the effectiveness of our attack and defense strategies.Under an attack budget of 3,the maximum reduction in model accuracy reaches 6.67%on the Graph Convolutional Network(GCN)and 11.67%on the Graph Attention Network(GAT)across different datasets,indicating that our unsupervised method induces degradation comparable to state-of-the-art supervised attacks.Meanwhile,our defense achieves the highest accuracy recovery of 3.89%(GCN)and 5.00%(GAT),demonstrating improved robustness against structural perturbations.
基金supported through Princess Nourah bint Abdulrahman University Researchers Supporting Project number(PNURSP2025R508)Princess Nourah bint Abdulrahman University,Riyadh,Saudi ArabiaThe research team thanks the Deanship of Graduate Studies and Scientific Research at Najran University for supporting the research project through the Nama’a program,with the project code NU/GP/SERC/13/18-5.
文摘Unmanned Aerial Vehicles(UAVs)are increasingly employed in traffic surveillance,urban planning,and infrastructure monitoring due to their cost-effectiveness,flexibility,and high-resolution imaging.However,vehicle detection and classification in aerial imagery remain challenging due to scale variations from fluctuating UAV altitudes,frequent occlusions in dense traffic,and environmental noise,such as shadows and lighting inconsistencies.Traditional methods,including sliding-window searches and shallow learning techniques,struggle with computational inefficiency and robustness under dynamic conditions.To address these limitations,this study proposes a six-stage hierarchical framework integrating radiometric calibration,deep learning,and classical feature engineering.The workflow begins with radiometric calibration to normalize pixel intensities and mitigate sensor noise,followed by Conditional Random Field(CRF)segmentation to isolate vehicles.YOLOv9,equipped with a bi-directional feature pyramid network(BiFPN),ensures precise multi-scale object detection.Hybrid feature extraction employs Maximally Stable Extremal Regions(MSER)for stable contour detection,Binary Robust Independent Elementary Features(BRIEF)for texture encoding,and Affine-SIFT(ASIFT)for viewpoint invariance.Quadratic Discriminant Analysis(QDA)enhances feature discrimination,while a Probabilistic Neural Network(PNN)performs Bayesian probability-based classification.Tested on the Roundabout Aerial Imagery(15,474 images,985K instances)and AU-AIR(32,823 instances,7 classes)datasets,the model achieves state-of-the-art accuracy of 95.54%and 94.14%,respectively.Its superior performance in detecting small-scale vehicles and resolving occlusions highlights its potential for intelligent traffic systems.Future work will extend testing to nighttime and adverse weather conditions while optimizing real-time UAV inference.
基金Supported by State Grid Corporation of China Science and Technology Project:Research on Key Technologies for Intelligent Carbon Metrology in Vehicle-to-Grid Interaction(Project Number:B3018524000Q).
文摘To achieve low-carbon regulation of electric vehicle(EV)charging loads under the“dual carbon”goals,this paper proposes a coordinated scheduling strategy that integrates dynamic carbon factor prediction and multiobjective optimization.First,a dual-convolution enhanced improved Crossformer prediction model is constructed,which employs parallel 1×1 global and 3×3 local convolutionmodules(Integrated Convolution Block,ICB)formultiscale feature extraction,combinedwith anAdaptive Spectral Block(ASB)to enhance time-series fluctuationmodeling.Based on high-precision predictions,a carbon-electricity cost joint optimization model is further designed to balance economic,environmental,and grid-friendly objectives.The model’s superiority was validated through a case study using real-world data from a renewable-heavy grid.Simulation results show that the proposed multi-objective strategy demonstrated a superior balance compared to baseline and benchmark models,achieving a 15.8%reduction in carbon emissions and a 5.2%reduction in economic costs,while still providing a substantial 22.2%reduction in the peak-valley difference.Its balanced performance significantly outperformed both a single-objective strategy and a state-of-the-art Model Predictive Control(MPC)benchmark,highlighting the advantage of a global optimization approach.This study provides theoretical and technical pathways for dynamic carbon factor-driven EV charging optimization.
基金funded by the Deanship of Graduate Studies and Scientific Research at Jouf University under grant No.(DGSSR-2025-02-01296).
文摘Skin diseases affect millions worldwide.Early detection is key to preventing disfigurement,lifelong disability,or death.Dermoscopic images acquired in primary-care settings show high intra-class visual similarity and severe class imbalance,and occasional imaging artifacts can create ambiguity for state-of-the-art convolutional neural networks(CNNs).We frame skin lesion recognition as graph-based reasoning and,to ensure fair evaluation and avoid data leakage,adopt a strict lesion-level partitioning strategy.Each image is first over-segmented using SLIC(Simple Linear Iterative Clustering)to produce perceptually homogeneous superpixels.These superpixels form the nodes of a region-adjacency graph whose edges encode spatial continuity.Node attributes are 1280-dimensional embeddings extracted with a lightweight yet expressive EfficientNet-B0 backbone,providing strong representational power at modest computational cost.The resulting graphs are processed by a five-layer Graph Attention Network(GAT)that learns to weight inter-node relationships dynamically and aggregates multi-hop context before classifying lesions into seven classes with a log-softmax output.Extensive experiments on the DermaMNIST benchmark show the proposed pipeline achieves 88.35%accuracy and 98.04%AUC,outperforming contemporary CNNs,AutoML approaches,and alternative graph neural networks.An ablation study indicates EfficientNet-B0 produces superior node descriptors compared with ResNet-18 and DenseNet,and that roughly five GAT layers strike a good balance between being too shallow and over-deep while avoiding oversmoothing.The method requires no data augmentation or external metadata,making it a drop-in upgrade for clinical computer-aided diagnosis systems.
基金supported by the SungKyunKwan University and the BK21 FOUR(Graduate School Innovation)funded by the Ministry of Education(MOE,Korea)and National Research Foundation of Korea(NRF).
文摘With the recent increase in data volume and diversity,traditional text representation techniques are struggling to capture context,particularly in environments with sparse data.To address these challenges,this study proposes a new model,the Masked Joint Representation Model(MJRM).MJRM approximates the original hypothesis by leveraging multiple elements in a limited context.It dynamically adapts to changes in characteristics based on data distribution through three main components.First,masking-based representation learning,termed selective dynamic masking,integrates topic modeling and sentiment clustering to generate and train multiple instances across different data subsets,whose predictions are then aggregated with optimized weights.This design alleviates sparsity,suppresses noise,and preserves contextual structures.Second,regularization-based improvements are applied.Third,techniques for addressing sparse data are used to perform final inference.As a result,MJRM improves performance by up to 4%compared to existing AI techniques.In our experiments,we analyzed the contribution of each factor,demonstrating that masking,dynamic learning,and aggregating multiple instances complement each other to improve performance.This demonstrates that a masking-based multi-learning strategy is effective for context-aware sparse text classification,and can be useful even in challenging situations such as data shortage or data distribution variations.We expect that the approach can be extended to diverse fields such as sentiment analysis,spam filtering,and domain-specific document classification.
基金supported in part by 14th Five Year National Key R&D Program Project(Project Number:2023YFB3211001)the National Natural Science Foundation of China(62273339,U24A201397).
文摘Rapidly-exploring Random Tree(RRT)and its variants have become foundational in path-planning research,yet in complex three-dimensional off-road environments their uniform blind sampling and limited safety guarantees lead to slow convergence and force an unfavorable trade-off between path quality and traversal safety.To address these challenges,we introduce HS-APF-RRT*,a novel algorithm that fuses layered sampling,an enhanced Artificial Potential Field(APF),and a dynamic neighborhood-expansion mechanism.First,the workspace is hierarchically partitioned into macro,meso,and micro sampling layers,progressively biasing random samples toward safer,lower-energy regions.Second,we augment the traditional APF by incorporating a slope-dependent repulsive term,enabling stronger avoidance of steep obstacles.Third,a dynamic expansion strategy adaptively switches between 8 and 16 connected neighborhoods based on local obstacle density,striking an effective balance between search efficiency and collision-avoidance precision.In simulated off-road scenarios,HS-APF-RRT*is benchmarked against RRT*,GoalBiased RRT*,and APF-RRT*,and demonstrates significantly faster convergence,lower path-energy consumption,and enhanced safety margins.
文摘Container transportation is pivotal in global trade due to its efficiency,safety,and cost-effectiveness.However,structural defects—particularly in grapple slots—can result in cargo damage,financial loss,and elevated safety risks,including container drops during lifting operations.Timely and accurate inspection before and after transit is therefore essential.Traditional inspection methods rely heavily on manual observation of internal and external surfaces,which are time-consuming,resource-intensive,and prone to subjective errors.Container roofs pose additional challenges due to limited visibility,while grapple slots are especially vulnerable to wear from frequent use.This study proposes a two-stage automated detection framework targeting defects in container roof grapple slots.In the first stage,YOLOv7 is employed to localize grapple slot regions with high precision.In the second stage,ResNet50 classifies the extracted slots as either intact or defective.The results from both stages are integrated into a human-machine interface for real-time visualization and user verification.Experimental evaluations demonstrate that YOLOv7 achieves a 99%detection rate at 100 frames per second(FPS),while ResNet50 attains 87%classification accuracy at 34 FPS.Compared to some state of the arts,the proposed system offers significant speed,reliability,and usability improvements,enabling efficient defect identification and visual reconfirmation via the interface.
基金supported by the National Natural Science Foundation of China(12302056)the Postdoctoral Fellowship Program of China Postdoctoral Science Foundation(GZC20233445)。
文摘Re-entry gliding vehicles exhibit high maneuverability,making trajectory prediction a key factor in the effectiveness of defense systems.To overcome the limited fitting accuracy of existing methods and their poor adaptability to maneuver mode mutations,a trajectory prediction method is proposed that integrates online maneuver mode identification with dynamic modeling.Characteristic parameters are extracted from tracking data for parameterized modeling,enabling real-time identification of maneuver modes.In addition,a maneuver detection mechanism based on higher-order cumulants is introduced to detect lateral maneuver mutations and optimize the use of historical data.Simulation results show that the proposed method achieves accurate trajectory prediction during the glide phase and maintains high accuracy under maneuver mutations,significantly enhancing the prediction performance of both three-dimensional trajectories and ground tracks.
文摘Evaluating the adversarial robustness of classification algorithms in machine learning is a crucial domain.However,current methods lack measurable and interpretable metrics.To address this issue,this paper introduces a visual evaluation index named confidence centroid skewing quadrilateral,which is based on a classification confidence-based confusion matrix,offering a quantitative and visual comparison of the adversarial robustness among different classification algorithms,and enhances intuitiveness and interpretability of attack impacts.We first conduct a validity test and sensitive analysis of the method.Then,prove its effectiveness through the experiments of five classification algorithms including artificial neural network(ANN),logistic regression(LR),support vector machine(SVM),convolutional neural network(CNN)and transformer against three adversarial attacks such as fast gradient sign method(FGSM),DeepFool,and projected gradient descent(PGD)attack.
基金supported by the Institute of Information&Communications Technology Planning&Evaluation(IITP)grant funded by the Korea government(MSIT)[RS-2021-II211341,Artificial Intelligence Graduate School Program(Chung-Ang University)],and by the Chung-Ang University Graduate Research Scholarship in 2024.
文摘Legal case classification involves the categorization of legal documents into predefined categories,which facilitates legal information retrieval and case management.However,real-world legal datasets often suffer from class imbalances due to the uneven distribution of case types across legal domains.This leads to biased model performance,in the form of high accuracy for overrepresented categories and underperformance for minority classes.To address this issue,in this study,we propose a data augmentation method that masks unimportant terms within a document selectively while preserving key terms fromthe perspective of the legal domain.This approach enhances data diversity and improves the generalization capability of conventional models.Our experiments demonstrate consistent improvements achieved by the proposed augmentation strategy in terms of accuracy and F1 score across all models,validating the effectiveness of the proposed method in legal case classification.
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.
基金supported by the Startup Foundation for Introducing Talent of Nanjing University of Information Science and Technology.
文摘With the increasing complexity of logistics operations,traditional static vehicle routing models are no longer sufficient.In practice,customer demands often arise dynamically,and multi-depot systems are commonly used to improve efficiency.This paper first introduces a vehicle routing problem with the goal of minimizing operating costs in a multi-depot environment with dynamic demand.New customers appear in the delivery process at any time and are periodically optimized according to time slices.Then,we propose a scheduling system TS-DPU based on an improved ant colony algorithm TS-ACO to solve this problem.The classical ant colony algorithm uses spatial distance to select nodes,while TS-ACO considers the impact of both temporal and spatial distance on node selection.Meanwhile,we adopt Cordeau’s Multi-Depot Vehicle Routing Problem with Time Windows(MDVRPTW)dataset to evaluate the performance of our system.According to the experimental results,TS-ACO,which considers spatial and temporal distance,is more effective than the classical ACO,which only considers spatial distance.
基金supported by the Japan Society for the Promotion of Science(JSPS)Grants-in-Aid for Scientific Research(C)23K03898.
文摘Traffic at urban intersections frequently encounters unexpected obstructions,resulting in congestion due to uncooperative and priority-based driving behavior.This paper presents an optimal right-turn coordination system for Connected and Automated Vehicles(CAVs)at single-lane intersections,particularly in the context of left-hand side driving on roads.The goal is to facilitate smooth right turns for certain vehicles without creating bottlenecks.We consider that all approaching vehicles share relevant information through vehicular communications.The Intersection Coordination Unit(ICU)processes this information and communicates the optimal crossing or turning times to the vehicles.The primary objective of this coordination is to minimize overall traffic delays,which also helps improve the fuel consumption of vehicles.By considering information from upcoming vehicles at the intersection,the coordination system solves an optimization problem to determine the best timing for executing right turns,ultimately minimizing the total delay for all vehicles.The proposed coordination system is evaluated at a typical urban intersection,and its performance is compared to traditional traffic systems.Numerical simulation results indicate that the proposed coordination system significantly enhances the average traffic speed and fuel consumption compared to the traditional traffic system in various scenarios.
