Dear Editor,The letter proposes a tensor low-rank orthogonal compression(TLOC)model for a convolutional neural network(CNN),which facilitates its efficient and highly-accurate low-rank representation.Model compression...Dear Editor,The letter proposes a tensor low-rank orthogonal compression(TLOC)model for a convolutional neural network(CNN),which facilitates its efficient and highly-accurate low-rank representation.Model compression is crucial for deploying deep neural network(DNN)models on resource-constrained embedded devices.展开更多
Distributed Denial of Service(DDoS)attacks are one of the severe threats to network infrastructure,sometimes bypassing traditional diagnosis algorithms because of their evolving complexity.PresentMachine Learning(ML)t...Distributed Denial of Service(DDoS)attacks are one of the severe threats to network infrastructure,sometimes bypassing traditional diagnosis algorithms because of their evolving complexity.PresentMachine Learning(ML)techniques for DDoS attack diagnosis normally apply network traffic statistical features such as packet sizes and inter-arrival times.However,such techniques sometimes fail to capture complicated relations among various traffic flows.In this paper,we present a new multi-scale ensemble strategy given the Graph Neural Networks(GNNs)for improving DDoS detection.Our technique divides traffic into macro-and micro-level elements,letting various GNN models to get the two corase-scale anomalies and subtle,stealthy attack models.Through modeling network traffic as graph-structured data,GNNs efficiently learn intricate relations among network entities.The proposed ensemble learning algorithm combines the results of several GNNs to improve generalization,robustness,and scalability.Extensive experiments on three benchmark datasets—UNSW-NB15,CICIDS2017,and CICDDoS2019—show that our approach outperforms traditional machine learning and deep learning models in detecting both high-rate and low-rate(stealthy)DDoS attacks,with significant improvements in accuracy and recall.These findings demonstrate the suggested method’s applicability and robustness for real-world implementation in contexts where several DDoS patterns coexist.展开更多
Since the advent of smart contracts,security vulnerabilities have remained a persistent challenge,compromsing both the reliability of contract execution and the overall stability of the virtual currency market.Consequ...Since the advent of smart contracts,security vulnerabilities have remained a persistent challenge,compromsing both the reliability of contract execution and the overall stability of the virtual currency market.Consequently,the academic community has devoted increasing attention to these security risks.However,conventional approaches to vulnerability detection frequently exhibit limited accuracy.To address this limitation,the present study introduces a novel vulnerability detection framework called GNNSE that integrates symbolic execution with graph neural networks(GNNs).The proposedmethod first constructs semantic graphs to comprehensively capture the control flow and data flow dependencies within smart contracts.These graphs are subsequently processed using GNNs to efficiently identify contracts with a high likelihood of vulnerabilities.For these high-risk contracts,symbolic execution is employed to perform fine-grained,path-level analysis,thereby improving overall detection precision.Experimental results on a dataset comprising 10,079 contracts demonstrate that the proposed method achieves detection precisions of 93.58% for reentrancy vulnerabilities and 92.73% for timestamp-dependent vulnerabilities.展开更多
The adjoint method is widely used in gradient-based optimization with high-dimensional design variables.However,the cost of solving the adjoint equations in each iteration is comparable to that of solving the flow fie...The adjoint method is widely used in gradient-based optimization with high-dimensional design variables.However,the cost of solving the adjoint equations in each iteration is comparable to that of solving the flow field,resulting in expensive computational costs.To improve the efficiency of solving adjoint equations,we propose a physics-constrained graph neural networks for solving adjoint equations,named ADJ-PCGN.ADJ-PCGN establishes a mapping relationship between flow characteristics and adjoint vector based on data,serving as a replacement for the computationally expensive numerical solution of adjoint equations.A physics-based graph structure and message-passing mechanism are designed to endow its strong fitting and generalization capabilities.Taking transonic drag reduction and maximum lift-drag ratio of the airfoil as examples,results indicate that ADJ-PCGN attains a similar optimal shape as the classical direct adjoint loop method.In addition,ADJ-PCGN demonstrates strong generalization capabilities across different mesh topologies,mesh densities,and out-of-distribution conditions.It holds the potential to become a universal model for aerodynamic shape optimization involving states,geometries,and meshes.展开更多
Convolutional neural networks(CNNs)have shown remarkable success across numerous tasks such as image classification,yet the theoretical understanding of their convergence remains underdeveloped compared to their empir...Convolutional neural networks(CNNs)have shown remarkable success across numerous tasks such as image classification,yet the theoretical understanding of their convergence remains underdeveloped compared to their empirical achievements.In this paper,the first filter learning framework with convergence-guaranteed learning laws for end-to-end learning of deep CNNs is proposed.Novel update laws with convergence analysis are formulated based on the mathematical representation of each layer in convolutional neural networks.The proposed learning laws enable concurrent updates of weights across all layers of the deep convolutional neural network and the analysis shows that the training errors converge to certain bounds which are dependent on the approximation errors.Case studies are conducted on benchmark datasets and the results show that the proposed concurrent filter learning framework guarantees the convergence and offers more consistent and reliable results during training with a trade-off in performance compared to stochastic gradient descent methods.This framework represents a significant step towards enhancing the reliability and effectiveness of deep convolutional neural network by developing a theoretical analysis which allows practical implementation of the learning laws with automatic tuning of the learning rate to guarantee the convergence during training.展开更多
Rapid quantification of seismic-induced damage immediately following an earthquake is critical for determining whether a structure is safe for continued occupation or requires evacuation.This study proposes a novel da...Rapid quantification of seismic-induced damage immediately following an earthquake is critical for determining whether a structure is safe for continued occupation or requires evacuation.This study proposes a novel damage identification method that utilizes limited strain data points,significantly reducing installation,maintenance,and data analysis costs compared to traditional distributed sensor networks.The approach integrates finite element(FE)modeling to generate capacity curves through pushover analysis,incorporates noise-augmented datasets for Artificial Neural Network(ANN)training,and classifies structural conditions into four damage levels:Operational(OP),Immediate Occupancy(IO),Life Safety(LS),and Collapse Prevention(CP).To evaluate the method’s accuracy and efficiency,it was applied to two reinforced concrete(RC)frames;a single-story frame tested experimentally under cyclic loading and a three-story frame analyzed under various lateral load patterns.Strain data from selected beam and column ends were used as ANN inputs,while the corresponding damage classes served as outputs.Confusion matrix results demonstrated high true positive rates(>85%for the single-story and>90%for the three-story frame),even with a reduced number of sensors.The model also exhibited strong robustness to White Gaussian Noise(SNR=2.5-5 dB)and generalized effectively to nonlinear time-history analyses under scaled ground motions(PGA=0.1-1.0 g).Feature selection using the MRMR and ANOVA algorithms further enhanced computational efficiency.Overall,the proposed ANN-based framework has strong potential for real-time structural health monitoring applications.展开更多
This paper introduces a fuzzy C-means-based pooling layer for convolutional neural networks that explicitly models local uncertainty and ambiguity.Conventional pooling operations,such as max and average,apply rigid ag...This paper introduces a fuzzy C-means-based pooling layer for convolutional neural networks that explicitly models local uncertainty and ambiguity.Conventional pooling operations,such as max and average,apply rigid aggregation and often discard fine-grained boundary information.In contrast,our method computes soft membershipswithin each receptive field and aggregates cluster-wise responses throughmembership-weighted pooling,thereby preserving informative structure while reducing dimensionality.Being differentiable,the proposed layer operates as standard two-dimensional pooling.We evaluate our approach across various CNN backbones and open datasets,including CIFAR-10/100,STL-10,LFW,and ImageNette,and further probe small training set restrictions on MNIST and Fashion-MNIST.In these settings,the proposed pooling consistently improves accuracy and weighted F1 over conventional baselines,with particularly strong gains when training data are scarce.Even with less than 1%of the training set,ourmethodmaintains reliable performance,indicating improved sample efficiency and robustness to noisy or ambiguous local patterns.Overall,integrating soft memberships into the pooling operator provides a practical and generalizable inductive bias that enhances robustness and generalization in modern CNN pipelines.展开更多
An efficient data-driven numerical framework is developed for transient heat conduction analysis in thin-walled structures.The proposed approach integrates spectral time discretization with neural network approximatio...An efficient data-driven numerical framework is developed for transient heat conduction analysis in thin-walled structures.The proposed approach integrates spectral time discretization with neural network approximation,forming a spectral-integrated neural network(SINN)scheme tailored for problems characterized by long-time evolution.Temporal derivatives are treated through a spectral integration strategy based on orthogonal polynomial expansions,which significantly alleviates stability constraints associated with conventional time-marching schemes.A fully connected neural network is employed to approximate the temperature-related variables,while governing equa-tions and boundary conditions are enforced through a physics-informed loss formulation.Numerical investigations demonstrate that the proposed method maintains high accuracy even when large time steps are adopted,where standard numerical solvers often suffer from instability or excessive computational cost.Moreover,the framework exhibits strong robustness for ultrathin configurations with extreme aspect ratios,achieving relative errors on the order of 10−5 or lower.These results indicate that the SINN framework provides a reliable and efficient alternative for transient thermal analysis of thin-walled structures under challenging computational conditions.展开更多
In this paper,we investigate data-driven bright soliton solutions of the nonlocal reverse-time nonlinear Schrodinger(NLS)equation and the parameter identification using the physically informed neural networks(PINNs)al...In this paper,we investigate data-driven bright soliton solutions of the nonlocal reverse-time nonlinear Schrodinger(NLS)equation and the parameter identification using the physically informed neural networks(PINNs)algorithm.Accurate simulations and comparative analyses of relative and absolute errors are performed for two-soliton and four-soliton solutions including linear solitary waves and periodic waves.In the training process,the standard PINNs scheme is employed for linear solitary wave solutions,while the prior information is added at local sharp regions for periodic wave solutions due to the complicated collision behaviors.For the parameter identification,we accurately recognize the nonlinear coefficients of the nonlocal NLS equation from known solutions with different noises.These results reinforce the application of deep learning with the PINNs framework to successfully study nonlocal integrable systems.展开更多
Physics-informed neural networks(PINNs)have emerged as a promising class of scientific machine learning techniques that integrate governing physical laws into neural network training.Their ability to enforce different...Physics-informed neural networks(PINNs)have emerged as a promising class of scientific machine learning techniques that integrate governing physical laws into neural network training.Their ability to enforce differential equations,constitutive relations,and boundary conditions within the loss function provides a physically grounded alternative to traditional data-driven models,particularly for solid and structural mechanics,where data are often limited or noisy.This review offers a comprehensive assessment of recent developments in PINNs,combining bibliometric analysis,theoretical foundations,application-oriented insights,and methodological innovations.A biblio-metric survey indicates a rapid increase in publications on PINNs since 2018,with prominent research clusters focused on numerical methods,structural analysis,and forecasting.Building upon this trend,the review consolidates advance-ments across five principal application domains,including forward structural analysis,inverse modeling and parameter identification,structural and topology optimization,assessment of structural integrity,and manufacturing processes.These applications are propelled by substantial methodological advancements,encompassing rigorous enforcement of boundary conditions,modified loss functions,adaptive training,domain decomposition strategies,multi-fidelity and transfer learning approaches,as well as hybrid finite element–PINN integration.These advances address recurring challenges in solid mechanics,such as high-order governing equations,material heterogeneity,complex geometries,localized phenomena,and limited experimental data.Despite remaining challenges in computational cost,scalability,and experimental validation,PINNs are increasingly evolving into specialized,physics-aware tools for practical solid and structural mechanics applications.展开更多
In this paper,a class of discontinuous Cohen-Grossberg neural networks with timevarying delays is considered.Firstly,under the extended Filippov differential inclusions framework,the problem of periodic solutions of t...In this paper,a class of discontinuous Cohen-Grossberg neural networks with timevarying delays is considered.Firstly,under the extended Filippov differential inclusions framework,the problem of periodic solutions of the considered neural networks with more relaxed conditions imposed on the amplification functions is analyzed by using set-valued mapping and Kakutani's fixed point theorem,which has rarely been used to study such problem.Secondly,the fixed-time synchronization of the error system of the considered neural networks is also investigated by designing a novel control strategy,which can improve not only the previous ones with sign function greatly,but also can reduce the chattering phenomenon.Finally,two numerical examples are presented to further illustrate the validity of the obtained results.展开更多
Advances in Alzheimer's disease(AD)research have deepened our understanding,yet the mechanisms driving its progression remain unclear.Although a range of in vivo biomarkers is now available(e.g.,measurements of am...Advances in Alzheimer's disease(AD)research have deepened our understanding,yet the mechanisms driving its progression remain unclear.Although a range of in vivo biomarkers is now available(e.g.,measurements of amyloidbeta(Aβ)and ta u accumulation-the molecular hallmarks of AD-structural magnetic resonance imaging(MRI),assessments of brain metabolism,and,more recently,blood-based markers),a definitive diagnosis of AD continues to be challenging.For example,Frisoni et al.展开更多
Physics-informed neural networks(PINNs),as a novel artificial intelligence method for solving partial differential equations,are applicable to solve both forward and inverse problems.This study evaluates the performan...Physics-informed neural networks(PINNs),as a novel artificial intelligence method for solving partial differential equations,are applicable to solve both forward and inverse problems.This study evaluates the performance of PINNs in solving the temperature diffusion equation of the seawater across six scenarios,including forward and inverse problems under three different boundary conditions.Results demonstrate that PINNs achieved consistently higher accuracy with the Dirichlet and Neumann boundary conditions compared to the Robin boundary condition for both forward and inverse problems.Inaccurate weighting of terms in the loss function can reduce model accuracy.Additionally,the sensitivity of model performance to the positioning of sampling points varied between different boundary conditions.In particular,the model under the Dirichlet boundary condition exhibited superior robustness to variations in point positions during the solutions of inverse problems.In contrast,for the Neumann and Robin boundary conditions,accuracy declines when points were sampled from identical positions or at the same time.Subsequently,the Argo observations were used to reconstruct the vertical diffusion of seawater temperature in the north-central Pacific for the applicability of PINNs in the real ocean.The PINNs successfully captured the vertical diffusion characteristics of seawater temperature,reflected the seasonal changes of vertical temperature under different topographic conditions,and revealed the influence of topography on the temperature diffusion coefficient.The PINNs were proved effective in solving the temperature diffusion equation of seawater with limited data,providing a promising technique for simulating or predicting ocean phenomena using sparse observations.展开更多
critical for guiding treatment and improving patient outcomes.Traditional molecular subtyping via immuno-histochemistry(IHC)test is invasive,time-consuming,and may not fully represent tumor heterogeneity.This study pr...critical for guiding treatment and improving patient outcomes.Traditional molecular subtyping via immuno-histochemistry(IHC)test is invasive,time-consuming,and may not fully represent tumor heterogeneity.This study proposes a non-invasive approach using digital mammography images and deep learning algorithm for classifying breast cancer molecular subtypes.Four pretrained models,including two Convolutional Neural Networks(MobileNet_V3_Large and VGG-16)and two Vision Transformers(ViT_B_16 and ViT_Base_Patch16_Clip_224)were fine-tuned to classify images into HER2-enriched,Luminal,Normal-like,and Triple Negative subtypes.Hyperparameter tuning,including learning rate adjustment and layer freezing strategies,was applied to optimize performance.Among the evaluated models,ViT_Base_Patch16_Clip_224 achieved the highest test accuracy(94.44%),with equally high precision,recall,and F1-score of 0.94,demonstrating excellent generalization.MobileNet_V3_Large achieved the same accuracy but showed less training stability.In contrast,VGG-16 recorded the lowest performance,indicating a limitation in its generalizability for this classification task.The study also highlighted the superior performance of the Vision Transformer models over CNNs,particularly due to their ability to capture global contextual features and the benefit of CLIP-based pretraining in ViT_Base_Patch16_Clip_224.To enhance clinical applicability,a graphical user interface(GUI)named“BCMS Dx”was developed for streamlined subtype prediction.Deep learning applied to mammography has proven effective for accurate and non-invasive molecular subtyping.The proposed Vision Transformer-based model and supporting GUI offer a promising direction for augmenting diagnostic workflows,minimizing the need for invasive procedures,and advancing personalized breast cancer management.展开更多
Physics-informed neural networks(PINNs)have been shown as powerful tools for solving partial differential equations(PDEs)by embedding physical laws into the network training.Despite their remarkable results,complicate...Physics-informed neural networks(PINNs)have been shown as powerful tools for solving partial differential equations(PDEs)by embedding physical laws into the network training.Despite their remarkable results,complicated problems such as irregular boundary conditions(BCs)and discontinuous or high-frequency behaviors remain persistent challenges for PINNs.For these reasons,we propose a novel two-phase framework,where a neural network is first trained to represent shape functions that can capture the irregularity of BCs in the first phase,and then these neural network-based shape functions are used to construct boundary shape functions(BSFs)that exactly satisfy both essential and natural BCs in PINNs in the second phase.This scheme is integrated into both the strong-form and energy PINN approaches,thereby improving the quality of solution prediction in the cases of irregular BCs.In addition,this study examines the benefits and limitations of these approaches in handling discontinuous and high-frequency problems.Overall,our method offers a unified and flexible solution framework that addresses key limitations of existing PINN methods with higher accuracy and stability for general PDE problems in solid mechanics.展开更多
This study proposes a novel forecasting framework that simultaneously captures the strong periodicity and irregular meteorological fluctuations inherent in solar radiation time series.Existing approaches typically def...This study proposes a novel forecasting framework that simultaneously captures the strong periodicity and irregular meteorological fluctuations inherent in solar radiation time series.Existing approaches typically define inter-regional correlations using either simple correlation coefficients or distance-based measures when applying spatio-temporal graph neural networks(STGNNs).However,such definitions are prone to generating spurious correlations due to the dominance of periodic structures.To address this limitation,we adopt the Elastic-Band Transform(EBT)to decompose solar radiation into periodic and amplitude-modulated components,which are then modeled independently with separate graph neural networks.The periodic component,characterized by strong nationwide correlations,is learned with a relatively simple architecture,whereas the amplitude-modulated component is modeled with more complex STGNNs that capture climatological similarities between regions.The predictions from the two components are subsequently recombined to yield final forecasts that integrate both periodic patterns and aperiodic variability.The proposed framework is validated with multiple STGNN architectures,and experimental results demonstrate improved predictive accuracy and interpretability compared to conventional methods.展开更多
Inflammatory bowel disease(IBD)is increasing globally,with risk factors still poorly understood and influenced by both genetic and environmental factors.The role of atmospheric pollutants,particularly precursor organi...Inflammatory bowel disease(IBD)is increasing globally,with risk factors still poorly understood and influenced by both genetic and environmental factors.The role of atmospheric pollutants,particularly precursor organic pollutants contributing to<2.5μm size particulate matter(PM_(2.5)),remains unclear.In this multi-decadal global study,we investigated their contribution to IBD prevalence using data from the Global Burden of Disease(GBD,1990–2019),NASA’s MERRA-2,and AERONET datasets.A graph neural network(GNN)modeled spatio-temporal dependencies and incorporated immune dysfunction and socio-economic disparities.The dataset was split into 75%training and 25%testing,achieving mean squared errors of 4.3%and 4.6%respectively,with strong predictive validity(R2=0.87).A 10%global increase in organics was associated with a rise in odds ratio(OR)by 0.21(95%CI:0.12–0.29,p<0.001),compared to a smaller OR increase of 0.04(95%CI:0.01–0.09,p<0.001)for PM_(2.5).Regional disparities were evident,with Sub-Saharan Africa exhibiting higher odds ratios(OR=1.25;95%CI:1.09–1.43,p<0.01)than North America(OR=1.08;95%CI:1.03–1.24,p<0.05)at an organic burden of 5μg/m^(3).However,this trend reversed at higher exposure(25μg/m^(3)),where the OR for North America approaches 2,while Sub-Saharan Africa plateaued near 1.5.Notably,particles under 100 nm posed the greatest risk.Concluding,organic pollutants play a disproportionate and size-dependent role in IBD prevalence,with significant regional variability.This underscores the need to consider organics as a distinct environmental risk factor in IBD epidemiology.展开更多
In this study,artificial neural networks(ANNs)were implemented to determine design parameters for an impressed current cathodic protection(ICCP)prototype.An ASTM A36 steel plate was tested in 3.5%NaCl solution,seawate...In this study,artificial neural networks(ANNs)were implemented to determine design parameters for an impressed current cathodic protection(ICCP)prototype.An ASTM A36 steel plate was tested in 3.5%NaCl solution,seawater,and NS4 using electrochemical impedance spectroscopy(EIS)to monitor the evolution of the substrate surface,which affects the current required to reach the protection potential(Eprot).Experimental data were collected as training datasets and analyzed using statistical methods,including box plots and correlation matrices.Subsequently,ANNs were applied to predict the current demand at different exposure times,enabling the estimation of electrochemical parameters(limiting voltage values)that can be used to optimize a self-regulating ICCP system.The obtained electrochemical parameters were then used,through Particle Swarm Optimization(PSO),to fine-tune an ANN-based proportional-integral-derivative(PID)controller for the ICCP system.展开更多
Near-infrared image sensors are widely used in fields such as material identification,machine vision,and autonomous driving.Lead sulfide colloidal quantum dot-based infrared photodiodes can be integrated with sil⁃icon...Near-infrared image sensors are widely used in fields such as material identification,machine vision,and autonomous driving.Lead sulfide colloidal quantum dot-based infrared photodiodes can be integrated with sil⁃icon-based readout circuits in a single step.Based on this,we propose a photodiode based on an n-i-p structure,which removes the buffer layer and further simplifies the manufacturing process of quantum dot image sensors,thus reducing manufacturing costs.Additionally,for the noise complexity in quantum dot image sensors when capturing images,traditional denoising and non-uniformity methods often do not achieve optimal denoising re⁃sults.For the noise and stripe-type non-uniformity commonly encountered in infrared quantum dot detector imag⁃es,a network architecture has been developed that incorporates multiple key modules.This network combines channel attention and spatial attention mechanisms,dynamically adjusting the importance of feature maps to en⁃hance the ability to distinguish between noise and details.Meanwhile,the residual dense feature fusion module further improves the network's ability to process complex image structures through hierarchical feature extraction and fusion.Furthermore,the pyramid pooling module effectively captures information at different scales,improv⁃ing the network's multi-scale feature representation ability.Through the collaborative effect of these modules,the network can better handle various mixed noise and image non-uniformity issues.Experimental results show that it outperforms the traditional U-Net network in denoising and image correction tasks.展开更多
Deep neural networks(DNNs)are effective in solving both forward and inverse problems for nonlinear partial differential equations(PDEs).However,conventional DNNs are not effective in handling problems such as delay di...Deep neural networks(DNNs)are effective in solving both forward and inverse problems for nonlinear partial differential equations(PDEs).However,conventional DNNs are not effective in handling problems such as delay differential equations(DDEs)and delay integrodifferential equations(DIDEs)with constant delays,primarily due to their low regularity at delayinduced breaking points.In this paper,a DNN method that combines multi-task learning(MTL)which is proposed to solve both the forward and inverse problems of DIDEs.The core idea of this approach is to divide the original equation into multiple tasks based on the delay,using auxiliary outputs to represent the integral terms,followed by the use of MTL to seamlessly incorporate the properties at the breaking points into the loss function.Furthermore,given the increased training dificulty associated with multiple tasks and outputs,we employ a sequential training scheme to reduce training complexity and provide reference solutions for subsequent tasks.This approach significantly enhances the approximation accuracy of solving DIDEs with DNNs,as demonstrated by comparisons with traditional DNN methods.We validate the effectiveness of this method through several numerical experiments,test various parameter sharing structures in MTL and compare the testing results of these structures.Finally,this method is implemented to solve the inverse problem of nonlinear DIDE and the results show that the unknown parameters of DIDE can be discovered with sparse or noisy data.展开更多
基金supported by the Science and Technology Innovation Key R&D Program of Chongqing(CSTB2025TIAD-STX0032)National Key Research and Development Program of China(2024YFF0908200)+1 种基金the Chongqing Technology Innovation and Application Development Special Key Project(CSTB2024TIAD-KPX0018)the Southwest University Graduate Student Research Innovation(SWUB24051)。
文摘Dear Editor,The letter proposes a tensor low-rank orthogonal compression(TLOC)model for a convolutional neural network(CNN),which facilitates its efficient and highly-accurate low-rank representation.Model compression is crucial for deploying deep neural network(DNN)models on resource-constrained embedded devices.
文摘Distributed Denial of Service(DDoS)attacks are one of the severe threats to network infrastructure,sometimes bypassing traditional diagnosis algorithms because of their evolving complexity.PresentMachine Learning(ML)techniques for DDoS attack diagnosis normally apply network traffic statistical features such as packet sizes and inter-arrival times.However,such techniques sometimes fail to capture complicated relations among various traffic flows.In this paper,we present a new multi-scale ensemble strategy given the Graph Neural Networks(GNNs)for improving DDoS detection.Our technique divides traffic into macro-and micro-level elements,letting various GNN models to get the two corase-scale anomalies and subtle,stealthy attack models.Through modeling network traffic as graph-structured data,GNNs efficiently learn intricate relations among network entities.The proposed ensemble learning algorithm combines the results of several GNNs to improve generalization,robustness,and scalability.Extensive experiments on three benchmark datasets—UNSW-NB15,CICIDS2017,and CICDDoS2019—show that our approach outperforms traditional machine learning and deep learning models in detecting both high-rate and low-rate(stealthy)DDoS attacks,with significant improvements in accuracy and recall.These findings demonstrate the suggested method’s applicability and robustness for real-world implementation in contexts where several DDoS patterns coexist.
基金supported by the National Key Research and Development Program of China(2020YFB1005704).
文摘Since the advent of smart contracts,security vulnerabilities have remained a persistent challenge,compromsing both the reliability of contract execution and the overall stability of the virtual currency market.Consequently,the academic community has devoted increasing attention to these security risks.However,conventional approaches to vulnerability detection frequently exhibit limited accuracy.To address this limitation,the present study introduces a novel vulnerability detection framework called GNNSE that integrates symbolic execution with graph neural networks(GNNs).The proposedmethod first constructs semantic graphs to comprehensively capture the control flow and data flow dependencies within smart contracts.These graphs are subsequently processed using GNNs to efficiently identify contracts with a high likelihood of vulnerabilities.For these high-risk contracts,symbolic execution is employed to perform fine-grained,path-level analysis,thereby improving overall detection precision.Experimental results on a dataset comprising 10,079 contracts demonstrate that the proposed method achieves detection precisions of 93.58% for reentrancy vulnerabilities and 92.73% for timestamp-dependent vulnerabilities.
基金supported by the National Natural Science Foundation of China(Grant No.12272316).
文摘The adjoint method is widely used in gradient-based optimization with high-dimensional design variables.However,the cost of solving the adjoint equations in each iteration is comparable to that of solving the flow field,resulting in expensive computational costs.To improve the efficiency of solving adjoint equations,we propose a physics-constrained graph neural networks for solving adjoint equations,named ADJ-PCGN.ADJ-PCGN establishes a mapping relationship between flow characteristics and adjoint vector based on data,serving as a replacement for the computationally expensive numerical solution of adjoint equations.A physics-based graph structure and message-passing mechanism are designed to endow its strong fitting and generalization capabilities.Taking transonic drag reduction and maximum lift-drag ratio of the airfoil as examples,results indicate that ADJ-PCGN attains a similar optimal shape as the classical direct adjoint loop method.In addition,ADJ-PCGN demonstrates strong generalization capabilities across different mesh topologies,mesh densities,and out-of-distribution conditions.It holds the potential to become a universal model for aerodynamic shape optimization involving states,geometries,and meshes.
基金supported by the Ministry of Education(MOE)Singapore,Academic Research Fund(AcRF)Tier 1(RG65/22)。
文摘Convolutional neural networks(CNNs)have shown remarkable success across numerous tasks such as image classification,yet the theoretical understanding of their convergence remains underdeveloped compared to their empirical achievements.In this paper,the first filter learning framework with convergence-guaranteed learning laws for end-to-end learning of deep CNNs is proposed.Novel update laws with convergence analysis are formulated based on the mathematical representation of each layer in convolutional neural networks.The proposed learning laws enable concurrent updates of weights across all layers of the deep convolutional neural network and the analysis shows that the training errors converge to certain bounds which are dependent on the approximation errors.Case studies are conducted on benchmark datasets and the results show that the proposed concurrent filter learning framework guarantees the convergence and offers more consistent and reliable results during training with a trade-off in performance compared to stochastic gradient descent methods.This framework represents a significant step towards enhancing the reliability and effectiveness of deep convolutional neural network by developing a theoretical analysis which allows practical implementation of the learning laws with automatic tuning of the learning rate to guarantee the convergence during training.
基金funded by UTM Fundamental Research Grant(PY/2024/01221,Cost centre no.:Q.J130000.3822.23H73)HiCoE Grant Scheme(Cost centre no.:R.J130000.7822.4J738)。
文摘Rapid quantification of seismic-induced damage immediately following an earthquake is critical for determining whether a structure is safe for continued occupation or requires evacuation.This study proposes a novel damage identification method that utilizes limited strain data points,significantly reducing installation,maintenance,and data analysis costs compared to traditional distributed sensor networks.The approach integrates finite element(FE)modeling to generate capacity curves through pushover analysis,incorporates noise-augmented datasets for Artificial Neural Network(ANN)training,and classifies structural conditions into four damage levels:Operational(OP),Immediate Occupancy(IO),Life Safety(LS),and Collapse Prevention(CP).To evaluate the method’s accuracy and efficiency,it was applied to two reinforced concrete(RC)frames;a single-story frame tested experimentally under cyclic loading and a three-story frame analyzed under various lateral load patterns.Strain data from selected beam and column ends were used as ANN inputs,while the corresponding damage classes served as outputs.Confusion matrix results demonstrated high true positive rates(>85%for the single-story and>90%for the three-story frame),even with a reduced number of sensors.The model also exhibited strong robustness to White Gaussian Noise(SNR=2.5-5 dB)and generalized effectively to nonlinear time-history analyses under scaled ground motions(PGA=0.1-1.0 g).Feature selection using the MRMR and ANOVA algorithms further enhanced computational efficiency.Overall,the proposed ANN-based framework has strong potential for real-time structural health monitoring applications.
文摘This paper introduces a fuzzy C-means-based pooling layer for convolutional neural networks that explicitly models local uncertainty and ambiguity.Conventional pooling operations,such as max and average,apply rigid aggregation and often discard fine-grained boundary information.In contrast,our method computes soft membershipswithin each receptive field and aggregates cluster-wise responses throughmembership-weighted pooling,thereby preserving informative structure while reducing dimensionality.Being differentiable,the proposed layer operates as standard two-dimensional pooling.We evaluate our approach across various CNN backbones and open datasets,including CIFAR-10/100,STL-10,LFW,and ImageNette,and further probe small training set restrictions on MNIST and Fashion-MNIST.In these settings,the proposed pooling consistently improves accuracy and weighted F1 over conventional baselines,with particularly strong gains when training data are scarce.Even with less than 1%of the training set,ourmethodmaintains reliable performance,indicating improved sample efficiency and robustness to noisy or ambiguous local patterns.Overall,integrating soft memberships into the pooling operator provides a practical and generalizable inductive bias that enhances robustness and generalization in modern CNN pipelines.
基金supported by the National Natural Science Foundation of China(Nos.12422207 and 12372199).
文摘An efficient data-driven numerical framework is developed for transient heat conduction analysis in thin-walled structures.The proposed approach integrates spectral time discretization with neural network approximation,forming a spectral-integrated neural network(SINN)scheme tailored for problems characterized by long-time evolution.Temporal derivatives are treated through a spectral integration strategy based on orthogonal polynomial expansions,which significantly alleviates stability constraints associated with conventional time-marching schemes.A fully connected neural network is employed to approximate the temperature-related variables,while governing equa-tions and boundary conditions are enforced through a physics-informed loss formulation.Numerical investigations demonstrate that the proposed method maintains high accuracy even when large time steps are adopted,where standard numerical solvers often suffer from instability or excessive computational cost.Moreover,the framework exhibits strong robustness for ultrathin configurations with extreme aspect ratios,achieving relative errors on the order of 10−5 or lower.These results indicate that the SINN framework provides a reliable and efficient alternative for transient thermal analysis of thin-walled structures under challenging computational conditions.
基金supported by the National Natural Science Foundation of China(Grant Nos.12171217 and 12375003)the Zhejiang Provincial Natural Science Foundation of China(Grant No.LMS 25A010013)。
文摘In this paper,we investigate data-driven bright soliton solutions of the nonlocal reverse-time nonlinear Schrodinger(NLS)equation and the parameter identification using the physically informed neural networks(PINNs)algorithm.Accurate simulations and comparative analyses of relative and absolute errors are performed for two-soliton and four-soliton solutions including linear solitary waves and periodic waves.In the training process,the standard PINNs scheme is employed for linear solitary wave solutions,while the prior information is added at local sharp regions for periodic wave solutions due to the complicated collision behaviors.For the parameter identification,we accurately recognize the nonlinear coefficients of the nonlocal NLS equation from known solutions with different noises.These results reinforce the application of deep learning with the PINNs framework to successfully study nonlocal integrable systems.
基金funded by National Research Council of Thailand(contract No.N42A671047).
文摘Physics-informed neural networks(PINNs)have emerged as a promising class of scientific machine learning techniques that integrate governing physical laws into neural network training.Their ability to enforce differential equations,constitutive relations,and boundary conditions within the loss function provides a physically grounded alternative to traditional data-driven models,particularly for solid and structural mechanics,where data are often limited or noisy.This review offers a comprehensive assessment of recent developments in PINNs,combining bibliometric analysis,theoretical foundations,application-oriented insights,and methodological innovations.A biblio-metric survey indicates a rapid increase in publications on PINNs since 2018,with prominent research clusters focused on numerical methods,structural analysis,and forecasting.Building upon this trend,the review consolidates advance-ments across five principal application domains,including forward structural analysis,inverse modeling and parameter identification,structural and topology optimization,assessment of structural integrity,and manufacturing processes.These applications are propelled by substantial methodological advancements,encompassing rigorous enforcement of boundary conditions,modified loss functions,adaptive training,domain decomposition strategies,multi-fidelity and transfer learning approaches,as well as hybrid finite element–PINN integration.These advances address recurring challenges in solid mechanics,such as high-order governing equations,material heterogeneity,complex geometries,localized phenomena,and limited experimental data.Despite remaining challenges in computational cost,scalability,and experimental validation,PINNs are increasingly evolving into specialized,physics-aware tools for practical solid and structural mechanics applications.
基金Supported by the National Natural Science Foundation of China(62576008)University Annual Scientific Research Plan of Anhui Province(2022AH030023)。
文摘In this paper,a class of discontinuous Cohen-Grossberg neural networks with timevarying delays is considered.Firstly,under the extended Filippov differential inclusions framework,the problem of periodic solutions of the considered neural networks with more relaxed conditions imposed on the amplification functions is analyzed by using set-valued mapping and Kakutani's fixed point theorem,which has rarely been used to study such problem.Secondly,the fixed-time synchronization of the error system of the considered neural networks is also investigated by designing a novel control strategy,which can improve not only the previous ones with sign function greatly,but also can reduce the chattering phenomenon.Finally,two numerical examples are presented to further illustrate the validity of the obtained results.
文摘Advances in Alzheimer's disease(AD)research have deepened our understanding,yet the mechanisms driving its progression remain unclear.Although a range of in vivo biomarkers is now available(e.g.,measurements of amyloidbeta(Aβ)and ta u accumulation-the molecular hallmarks of AD-structural magnetic resonance imaging(MRI),assessments of brain metabolism,and,more recently,blood-based markers),a definitive diagnosis of AD continues to be challenging.For example,Frisoni et al.
基金Supported by the National Key Research and Development Program of China(No.2023YFC3008200)the Independent Research Project of Southern Marine Science and Engineering Guangdong Laboratory(Zhuhai)(No.SML2022SP505)。
文摘Physics-informed neural networks(PINNs),as a novel artificial intelligence method for solving partial differential equations,are applicable to solve both forward and inverse problems.This study evaluates the performance of PINNs in solving the temperature diffusion equation of the seawater across six scenarios,including forward and inverse problems under three different boundary conditions.Results demonstrate that PINNs achieved consistently higher accuracy with the Dirichlet and Neumann boundary conditions compared to the Robin boundary condition for both forward and inverse problems.Inaccurate weighting of terms in the loss function can reduce model accuracy.Additionally,the sensitivity of model performance to the positioning of sampling points varied between different boundary conditions.In particular,the model under the Dirichlet boundary condition exhibited superior robustness to variations in point positions during the solutions of inverse problems.In contrast,for the Neumann and Robin boundary conditions,accuracy declines when points were sampled from identical positions or at the same time.Subsequently,the Argo observations were used to reconstruct the vertical diffusion of seawater temperature in the north-central Pacific for the applicability of PINNs in the real ocean.The PINNs successfully captured the vertical diffusion characteristics of seawater temperature,reflected the seasonal changes of vertical temperature under different topographic conditions,and revealed the influence of topography on the temperature diffusion coefficient.The PINNs were proved effective in solving the temperature diffusion equation of seawater with limited data,providing a promising technique for simulating or predicting ocean phenomena using sparse observations.
基金funded by the Ministry of Higher Education(MoHE)Malaysia through the Fundamental Research Grant Scheme—Early Career Researcher(FRGS-EC),grant number FRGSEC/1/2024/ICT02/UNIMAP/02/8.
文摘critical for guiding treatment and improving patient outcomes.Traditional molecular subtyping via immuno-histochemistry(IHC)test is invasive,time-consuming,and may not fully represent tumor heterogeneity.This study proposes a non-invasive approach using digital mammography images and deep learning algorithm for classifying breast cancer molecular subtypes.Four pretrained models,including two Convolutional Neural Networks(MobileNet_V3_Large and VGG-16)and two Vision Transformers(ViT_B_16 and ViT_Base_Patch16_Clip_224)were fine-tuned to classify images into HER2-enriched,Luminal,Normal-like,and Triple Negative subtypes.Hyperparameter tuning,including learning rate adjustment and layer freezing strategies,was applied to optimize performance.Among the evaluated models,ViT_Base_Patch16_Clip_224 achieved the highest test accuracy(94.44%),with equally high precision,recall,and F1-score of 0.94,demonstrating excellent generalization.MobileNet_V3_Large achieved the same accuracy but showed less training stability.In contrast,VGG-16 recorded the lowest performance,indicating a limitation in its generalizability for this classification task.The study also highlighted the superior performance of the Vision Transformer models over CNNs,particularly due to their ability to capture global contextual features and the benefit of CLIP-based pretraining in ViT_Base_Patch16_Clip_224.To enhance clinical applicability,a graphical user interface(GUI)named“BCMS Dx”was developed for streamlined subtype prediction.Deep learning applied to mammography has proven effective for accurate and non-invasive molecular subtyping.The proposed Vision Transformer-based model and supporting GUI offer a promising direction for augmenting diagnostic workflows,minimizing the need for invasive procedures,and advancing personalized breast cancer management.
基金Project supported by the Basic Science Research Program through the National Research Foundation(NRF)of Korea funded by the Ministry of Science and ICT(No.RS-2024-00337001)。
文摘Physics-informed neural networks(PINNs)have been shown as powerful tools for solving partial differential equations(PDEs)by embedding physical laws into the network training.Despite their remarkable results,complicated problems such as irregular boundary conditions(BCs)and discontinuous or high-frequency behaviors remain persistent challenges for PINNs.For these reasons,we propose a novel two-phase framework,where a neural network is first trained to represent shape functions that can capture the irregularity of BCs in the first phase,and then these neural network-based shape functions are used to construct boundary shape functions(BSFs)that exactly satisfy both essential and natural BCs in PINNs in the second phase.This scheme is integrated into both the strong-form and energy PINN approaches,thereby improving the quality of solution prediction in the cases of irregular BCs.In addition,this study examines the benefits and limitations of these approaches in handling discontinuous and high-frequency problems.Overall,our method offers a unified and flexible solution framework that addresses key limitations of existing PINN methods with higher accuracy and stability for general PDE problems in solid mechanics.
基金supported by Basic Science Research Program through the National Research Foundation of Korea(NRF)funded by the Ministry of Education(RS-2023-00249743).
文摘This study proposes a novel forecasting framework that simultaneously captures the strong periodicity and irregular meteorological fluctuations inherent in solar radiation time series.Existing approaches typically define inter-regional correlations using either simple correlation coefficients or distance-based measures when applying spatio-temporal graph neural networks(STGNNs).However,such definitions are prone to generating spurious correlations due to the dominance of periodic structures.To address this limitation,we adopt the Elastic-Band Transform(EBT)to decompose solar radiation into periodic and amplitude-modulated components,which are then modeled independently with separate graph neural networks.The periodic component,characterized by strong nationwide correlations,is learned with a relatively simple architecture,whereas the amplitude-modulated component is modeled with more complex STGNNs that capture climatological similarities between regions.The predictions from the two components are subsequently recombined to yield final forecasts that integrate both periodic patterns and aperiodic variability.The proposed framework is validated with multiple STGNN architectures,and experimental results demonstrate improved predictive accuracy and interpretability compared to conventional methods.
文摘Inflammatory bowel disease(IBD)is increasing globally,with risk factors still poorly understood and influenced by both genetic and environmental factors.The role of atmospheric pollutants,particularly precursor organic pollutants contributing to<2.5μm size particulate matter(PM_(2.5)),remains unclear.In this multi-decadal global study,we investigated their contribution to IBD prevalence using data from the Global Burden of Disease(GBD,1990–2019),NASA’s MERRA-2,and AERONET datasets.A graph neural network(GNN)modeled spatio-temporal dependencies and incorporated immune dysfunction and socio-economic disparities.The dataset was split into 75%training and 25%testing,achieving mean squared errors of 4.3%and 4.6%respectively,with strong predictive validity(R2=0.87).A 10%global increase in organics was associated with a rise in odds ratio(OR)by 0.21(95%CI:0.12–0.29,p<0.001),compared to a smaller OR increase of 0.04(95%CI:0.01–0.09,p<0.001)for PM_(2.5).Regional disparities were evident,with Sub-Saharan Africa exhibiting higher odds ratios(OR=1.25;95%CI:1.09–1.43,p<0.01)than North America(OR=1.08;95%CI:1.03–1.24,p<0.05)at an organic burden of 5μg/m^(3).However,this trend reversed at higher exposure(25μg/m^(3)),where the OR for North America approaches 2,while Sub-Saharan Africa plateaued near 1.5.Notably,particles under 100 nm posed the greatest risk.Concluding,organic pollutants play a disproportionate and size-dependent role in IBD prevalence,with significant regional variability.This underscores the need to consider organics as a distinct environmental risk factor in IBD epidemiology.
文摘In this study,artificial neural networks(ANNs)were implemented to determine design parameters for an impressed current cathodic protection(ICCP)prototype.An ASTM A36 steel plate was tested in 3.5%NaCl solution,seawater,and NS4 using electrochemical impedance spectroscopy(EIS)to monitor the evolution of the substrate surface,which affects the current required to reach the protection potential(Eprot).Experimental data were collected as training datasets and analyzed using statistical methods,including box plots and correlation matrices.Subsequently,ANNs were applied to predict the current demand at different exposure times,enabling the estimation of electrochemical parameters(limiting voltage values)that can be used to optimize a self-regulating ICCP system.The obtained electrochemical parameters were then used,through Particle Swarm Optimization(PSO),to fine-tune an ANN-based proportional-integral-derivative(PID)controller for the ICCP system.
基金Supported by the National key research and development program in the 14th five year plan 2021YFA1200700)the National Natural Science Foundation of China(62535018,62431025,62561160113)the Natural Science Foundation of Shanghai(23ZR1473400).
文摘Near-infrared image sensors are widely used in fields such as material identification,machine vision,and autonomous driving.Lead sulfide colloidal quantum dot-based infrared photodiodes can be integrated with sil⁃icon-based readout circuits in a single step.Based on this,we propose a photodiode based on an n-i-p structure,which removes the buffer layer and further simplifies the manufacturing process of quantum dot image sensors,thus reducing manufacturing costs.Additionally,for the noise complexity in quantum dot image sensors when capturing images,traditional denoising and non-uniformity methods often do not achieve optimal denoising re⁃sults.For the noise and stripe-type non-uniformity commonly encountered in infrared quantum dot detector imag⁃es,a network architecture has been developed that incorporates multiple key modules.This network combines channel attention and spatial attention mechanisms,dynamically adjusting the importance of feature maps to en⁃hance the ability to distinguish between noise and details.Meanwhile,the residual dense feature fusion module further improves the network's ability to process complex image structures through hierarchical feature extraction and fusion.Furthermore,the pyramid pooling module effectively captures information at different scales,improv⁃ing the network's multi-scale feature representation ability.Through the collaborative effect of these modules,the network can better handle various mixed noise and image non-uniformity issues.Experimental results show that it outperforms the traditional U-Net network in denoising and image correction tasks.
文摘Deep neural networks(DNNs)are effective in solving both forward and inverse problems for nonlinear partial differential equations(PDEs).However,conventional DNNs are not effective in handling problems such as delay differential equations(DDEs)and delay integrodifferential equations(DIDEs)with constant delays,primarily due to their low regularity at delayinduced breaking points.In this paper,a DNN method that combines multi-task learning(MTL)which is proposed to solve both the forward and inverse problems of DIDEs.The core idea of this approach is to divide the original equation into multiple tasks based on the delay,using auxiliary outputs to represent the integral terms,followed by the use of MTL to seamlessly incorporate the properties at the breaking points into the loss function.Furthermore,given the increased training dificulty associated with multiple tasks and outputs,we employ a sequential training scheme to reduce training complexity and provide reference solutions for subsequent tasks.This approach significantly enhances the approximation accuracy of solving DIDEs with DNNs,as demonstrated by comparisons with traditional DNN methods.We validate the effectiveness of this method through several numerical experiments,test various parameter sharing structures in MTL and compare the testing results of these structures.Finally,this method is implemented to solve the inverse problem of nonlinear DIDE and the results show that the unknown parameters of DIDE can be discovered with sparse or noisy data.
