Accurate early classification of elephant flows(elephants)is important for network management and resource optimization.Elephant models,mainly based on the byte count of flows,can always achieve high accuracy,but not ...Accurate early classification of elephant flows(elephants)is important for network management and resource optimization.Elephant models,mainly based on the byte count of flows,can always achieve high accuracy,but not in a time-efficient manner.The time efficiency becomes even worse when the flows to be classified are sampled by flow entry timeout over Software-Defined Networks(SDNs)to achieve a better resource efficiency.This paper addresses this situation by combining co-training and Reinforcement Learning(RL)to enable a closed-loop classification approach that divides the entire classification process into episodes,each involving two elephant models.One predicts elephants and is retrained by a selection of flows automatically labeled online by the other.RL is used to formulate a reward function that estimates the values of the possible actions based on the current states of both models and further adjusts the ratio of flows to be labeled in each phase.Extensive evaluation based on real traffic traces shows that the proposed approach can stably predict elephants using the packets received in the first 10% of their lifetime with an accuracy of over 80%,and using only about 10% more control channel bandwidth than the baseline over the evolved SDNs.展开更多
Rational allocation of water flow energy in river networks is essential to addressing water-related issues in river network areas.However,current methods of calculating the spatiotemporal distribution of flow energy i...Rational allocation of water flow energy in river networks is essential to addressing water-related issues in river network areas.However,current methods of calculating the spatiotemporal distribution of flow energy in river networks lack precision and efficiency.This paper introduces a novel hydrodynamic representation,the energy flow rate,defined as the product of the flow rate and kinetic energy head,to quantify the kinetic energy stored and transported in river networks.A linear equation system for the energy flow rate in a river network has been theoretically derived,enabling rapid calculations under steady flow conditions.A simplified equation is proposed to describe the exponential decay of the energy flow rate,accompanied by potential energy conversion.The coefficients in the linear equation system are determined using control equations at flow confluence and diversion nodes.This study provides foundational insights that can be used to develop new hydrodynamic modeling strategies to regulate water flow energy and achieve coordinated management of water-related issues in river networks.展开更多
Zero Trust Network(ZTN)enhances network security through strict authentication and access control.However,in the ZTN,optimizing flow control to improve the quality of service is still facing challenges.Software Define...Zero Trust Network(ZTN)enhances network security through strict authentication and access control.However,in the ZTN,optimizing flow control to improve the quality of service is still facing challenges.Software Defined Network(SDN)provides solutions through centralized control and dynamic resource allocation,but the existing scheduling methods based on Deep Reinforcement Learning(DRL)are insufficient in terms of convergence speed and dynamic optimization capability.To solve these problems,this paper proposes DRL-AMIR,which is an efficient flow scheduling method for software defined ZTN.This method constructs a flow scheduling optimization model that comprehensively considers service delay,bandwidth occupation,and path hops.Additionally,it balances the differentiated requirements of delay-critical K-flows,bandwidth-intensive D-flows,and background B-flows through adaptiveweighting.Theproposed framework employs a customized state space comprising node labels,link bandwidth,delaymetrics,and path length.It incorporates an action space derived fromnode weights and a hybrid reward function that integrates both single-step and multi-step excitation mechanisms.Based on these components,a hierarchical architecture is designed,effectively integrating the data plane,control plane,and knowledge plane.In particular,the adaptive expert mechanism is introduced,which triggers the shortest path algorithm in the training process to accelerate convergence,reduce trial and error costs,and maintain stability.Experiments across diverse real-world network topologies demonstrate that DRL-AMIR achieves a 15–20%reduction in K-flow transmission delays,a 10–15%improvement in link bandwidth utilization compared to SPR,QoSR,and DRSIR,and a 30%faster convergence speed via adaptive expert mechanisms.展开更多
Accurate traffic flow prediction has a profound impact on modern traffic management. Traffic flow has complex spatial-temporal correlations and periodicity, which poses difficulties for precise prediction. To address ...Accurate traffic flow prediction has a profound impact on modern traffic management. Traffic flow has complex spatial-temporal correlations and periodicity, which poses difficulties for precise prediction. To address this problem, a Multi-head Self-attention and Spatial-Temporal Graph Convolutional Network (MSSTGCN) for multiscale traffic flow prediction is proposed. Firstly, to capture the hidden traffic periodicity of traffic flow, traffic flow is divided into three kinds of periods, including hourly, daily, and weekly data. Secondly, a graph attention residual layer is constructed to learn the global spatial features across regions. Local spatial-temporal dependence is captured by using a T-GCN module. Thirdly, a transformer layer is introduced to learn the long-term dependence in time. A position embedding mechanism is introduced to label position information for all traffic sequences. Thus, this multi-head self-attention mechanism can recognize the sequence order and allocate weights for different time nodes. Experimental results on four real-world datasets show that the MSSTGCN performs better than the baseline methods and can be successfully adapted to traffic prediction tasks.展开更多
The numerical calculation method has greatly promoted the process of optimal design of scramjet,but it still needs extremely heavy calculation for the model with complex thermochemical reaction.Data-driven deep learni...The numerical calculation method has greatly promoted the process of optimal design of scramjet,but it still needs extremely heavy calculation for the model with complex thermochemical reaction.Data-driven deep learning relies heavily on a large amount of data in the face of complex nonlinear features.Therefore,combining“data-driven model”and“Navier-Stokes equation”,an intelligent prediction model of supersonic combustion flow process is constructed.This algorithm integrates the theory priors of combustion flow into the neural network model,and uses convolutional grouping and rearrangement to reduce the feature redundancy calculation,so as to achieve high-precision and high-efficiency prediction of velocity,density,pressure and temperature fields.This study makes a comprehensive comparison from two aspects of performance and efficiency.Unsteady scramjet multi-physical field dataset is constructed under different incoming Mach number conditions.The experimental results show that compared with other methods,the proposed algorithm can achieve the maximum Peak Signal-to-Noise Ratio(PSNR)improvement of 38.75%and Learned Perceptual Image Patch Similarity(LPIPS)improvement of 68.13%in predicting the average quality of images,and the computational cost of the model is reduced by 30.36%compared with other models.In addition,the high model can also effectively predict the unknown incoming flow condition.展开更多
The presence of circles in the network maximum flow problem increases the complexity of the preflow algorithm.This study proposes a novel two-stage preflow algorithm to address this issue.First,this study proves that ...The presence of circles in the network maximum flow problem increases the complexity of the preflow algorithm.This study proposes a novel two-stage preflow algorithm to address this issue.First,this study proves that at least one zero-flow arc must be present when the flow of the network reaches its maximum value.This result indicates that the maximum flow of the network will remain constant if a zero-flow arc within a circle is removed;therefore,the maximum flow of each network without circles can be calculated.The first stage involves identifying the zero-flow arc in the circle when the network flow reaches its maximum.The second stage aims to remove the zero-flow arc identified and modified in the first stage,thereby producing a new network without circles.The maximum flow of the original looped network can be obtained by solving the maximum flow of the newly generated acyclic network.Finally,an example is provided to demonstrate the validity and feasibility of this algorithm.This algorithm not only improves computational efficiency but also provides new perspectives and tools for solving similar network optimization problems.展开更多
This research introduces a spectrum-based physics-informed neural network(SP-PINN)model to significantly improve the accuracy of calculation of two-phase flow parameters,surpassing existing methods that have limitatio...This research introduces a spectrum-based physics-informed neural network(SP-PINN)model to significantly improve the accuracy of calculation of two-phase flow parameters,surpassing existing methods that have limitations in global and continuous data sampling.SP-PINNs address the challenges of traditional methods in terms of continuous sampling by integrating the spectral analysis and pressure correction into the Navier-Stokes(N-S)equations,enhancing the predictive accuracy especially in critical regions like gas-phase boundaries and velocity peaks.The novel introduction of a pressure-correction module within SP-PINNs mitigates prediction errors,achieving a substantial reduction to 1‰compared with the conventional physics-informed neural network(PINN)approaches.Experimental applications validate the model’s ability to accurately and rapidly predict flow parameters with different sampling time intervals,with the computation time of predicting unsampled data less than 0.01 s.Such advancements signify a 100-fold improvement over traditional DNS calculations,underscoring the model’s potential in the real-time calculation and analysis of multiphase flow dynamics.展开更多
With the widespread implementation of distributed generation(DG)and the integration of soft open point(SOP)into the distribution network(DN),the latter is steadily transitioning into a flexible distribution network(FD...With the widespread implementation of distributed generation(DG)and the integration of soft open point(SOP)into the distribution network(DN),the latter is steadily transitioning into a flexible distribution network(FDN),the calculation of carbon flow distribution in FDN is more difficult.To this end,this study constructs a model for low-carbon optimal operations within the FDN on the basis of enhanced carbon emission flow(CEF).First,the carbon emission characteristics of FDNs are scrutinized and an improved method for calculating carbon flow within these networks is proposed.Subsequently,a model for optimizing low-carbon operations within FDNs is formulated based on the refined CEF,which merges the specificities of DG and intelligent SOP.Finally,this model is scrutinized using an upgraded IEEE 33-node distribution system,a comparative analysis of the cases reveals that when DG and SOP are operated in a coordinated manner in the FDN,with the cost of electricity generation was reduced by 40.63 percent and the cost of carbon emissions by 10.18 percent.The findings indicate that the judicious optimization of areas exhibiting higher carbon flow rates can effectively enhance the economic efficiency of DN operations and curtail the carbon emissions of the overall network.展开更多
Two actual rocks drilled from a typical ultra-deep hydrocarbon reservoir in the Tarim Basin are selected to conduct in-situ stress-loading micro-focus CT scanning experiments.The gray images of rock microstructure at ...Two actual rocks drilled from a typical ultra-deep hydrocarbon reservoir in the Tarim Basin are selected to conduct in-situ stress-loading micro-focus CT scanning experiments.The gray images of rock microstructure at different stress loading stages are obtained.The U-Net fully convolutional neural network is utilized to achieve fine semantic segmentation of rock skeleton,pore space,and microfractures based on CT slice images of deep rocks.The three-dimensional digital rock models of deformed multiscale fractured-porous media at different stress loading stages are thereafter reconstructed,and the equivalent fracture-pore network models are finally extracted to explore the underlying mechanisms of gas-water two-phase flow at the pore-scale.Results indicate that,in the process of insitu stress loading,both the deep rocks have experienced three stages:linear elastic deformation,nonlinear plastic deformation,and shear failure.The micro-mechanical behavior greatly affects the dynamic deformation of rock microstructure and gas-water two-phase flow.In the linear elastic deformation stage,with the increase in in-situ stress,both the deep rocks are gradually compacted,leading to decreases in average pore radius,pore throat ratio,tortuosity,and water-phase relative permeability,while the coordination number nearly remains unchanged.In the plastic deformation stage,the synergistic influence of rock compaction and existence of micro-fractures typically exert a great effect on pore-throat topological properties and gas-water relative permeability.In the shear failure stage,due to the generation and propagation of micro-fractures inside the deep rock,the topological connectivity becomes better,fluid flow paths increase,and flow conductivity is promoted,thus leading to sharp increases in average pore radius and coordination number,rapid decreases in pore throat ratio and tortuosity,as well as remarkable improvement in relative permeability of gas phase and waterphase.展开更多
The global clustering of inventive talent shapes innovation capacity and drives economic growth.For China,this process is especially crucial in sustaining its development momentum.This paper draws on data from the EPO...The global clustering of inventive talent shapes innovation capacity and drives economic growth.For China,this process is especially crucial in sustaining its development momentum.This paper draws on data from the EPO Worldwide Patent Statistical Database(PATSTAT)to extract global inventive talent mobility information and analyzes the spatial structural evolution of the global inventive talent flow network.The study finds that this network is undergoing a multi-polar transformation,characterized by the rising importance of a few central countries-such as the United States,Germany,and China-and the increasing marginalization of many peripheral countries.In response to this typical phenomenon,the paper constructs an endogenous migration model and conducts empirical testing using the Temporal Exponential Random Graph Model(TERGM).The results reveal several endogenous mechanisms driving global inventive talent flows,including reciprocity,path dependence,convergence effects,transitivity,and cyclic structures,all of which contribute to the network’s multi-polar trend.In addition,differences in regional industrial structures significantly influence talent mobility choices and are a decisive factor in the formation of poles within the multi-polar landscape.Based on these findings,it is suggested that efforts be made to foster two-way channels for talent exchange between China and other global innovation hubs,in order to enhance international collaboration and knowledge flow.We should aim to reduce the migration costs and institutional barriers faced by R&D personnel,thereby encouraging greater mobility of high-skilled talent.Furthermore,the government is advised to strategically leverage regional strengths in high-tech industries as a lever to capture competitive advantages in emerging technologies and products,ultimately strengthening the country’s position in the global innovation landscape.展开更多
Physics-informed neural networks(PINNs)have prevailed as differentiable simulators to investigate flow in porous media.Despite recent progress PINNs have achieved,practical geotechnical scenarios cannot be readily sim...Physics-informed neural networks(PINNs)have prevailed as differentiable simulators to investigate flow in porous media.Despite recent progress PINNs have achieved,practical geotechnical scenarios cannot be readily simulated because conventional PINNs fail in discontinuous heterogeneous porous media or multi-layer strata when labeled data are missing.This work aims to develop a universal network structure to encode the mass continuity equation and Darcy’s law without labeled data.The finite element approximation,which can decompose a complex heterogeneous domain into simpler ones,is adopted to build the differentiable network.Without conventional DNNs,physics-encoded finite element network(PEFEN)can avoid spectral bias and learn high-frequency functions with sharp/steep gradients.PEFEN rigorously encodes Dirichlet and Neumann boundary conditions without training.Benefiting from its discretized formulation,the discontinuous heterogeneous hydraulic conductivity is readily embedded into the network.Three typical cases are reproduced to corroborate PEFEN’s superior performance over conventional PINNs and the PINN with mixed formulation.PEFEN is sparse and demonstrated to be capable of dealing with heterogeneity with much fewer training iterations(less than 1/30)than the improved PINN with mixed formulation.Thus,PEFEN saves energy and contributes to low-carbon AI for science.The last two cases focus on common geotechnical settings of impermeable sheet pile in singlelayer and multi-layer strata.PEFEN solves these cases with high accuracy,circumventing costly labeled data,extra computational burden,and additional treatment.Thus,this study warrants the further development and application of PEFEN as a novel differentiable network in porous flow of practical geotechnical engineering.展开更多
Unsupervised methods based on density representation have shown their abilities in anomaly detection,but detection performance still needs to be improved.Specifically,approaches using normalizing flows can accurately ...Unsupervised methods based on density representation have shown their abilities in anomaly detection,but detection performance still needs to be improved.Specifically,approaches using normalizing flows can accurately evaluate sample distributions,mapping normal features to the normal distribution and anomalous features outside it.Consequently,this paper proposes a Normalizing Flow-based Bidirectional Mapping Residual Network(NF-BMR).It utilizes pre-trained Convolutional Neural Networks(CNN)and normalizing flows to construct discriminative source and target domain feature spaces.Additionally,to better learn feature information in both domain spaces,we propose the Bidirectional Mapping Residual Network(BMR),which maps sample features to these two spaces for anomaly detection.The two detection spaces effectively complement each other’s deficiencies and provide a comprehensive feature evaluation from two perspectives,which leads to the improvement of detection performance.Comparative experimental results on the MVTec AD and DAGM datasets against the Bidirectional Pre-trained Feature Mapping Network(B-PFM)and other state-of-the-art methods demonstrate that the proposed approach achieves superior performance.On the MVTec AD dataset,NF-BMR achieves an average AUROC of 98.7%for all 15 categories.Especially,it achieves 100%optimal detection performance in five categories.On the DAGM dataset,the average AUROC across ten categories is 98.7%,which is very close to supervised methods.展开更多
Analyzing rock mass seepage using the discrete fracture network(DFN)flow model poses challenges when dealing with complex fracture networks.This paper presents a novel DFN flow model that incorporates the actual conne...Analyzing rock mass seepage using the discrete fracture network(DFN)flow model poses challenges when dealing with complex fracture networks.This paper presents a novel DFN flow model that incorporates the actual connections of large-scale fractures.Notably,this model efficiently manages over 20,000 fractures without necessitating adjustments to the DFN geometry.All geometric analyses,such as identifying connected fractures,dividing the two-dimensional domain into closed loops,triangulating arbitrary loops,and refining triangular elements,are fully automated.The analysis processes are comprehensively introduced,and core algorithms,along with their pseudo-codes,are outlined and explained to assist readers in their programming endeavors.The accuracy of geometric analyses is validated through topological graphs representing the connection relationships between fractures.In practical application,the proposed model is employed to assess the water-sealing effectiveness of an underground storage cavern project.The analysis results indicate that the existing design scheme can effectively prevent the stored oil from leaking in the presence of both dense and sparse fractures.Furthermore,following extensive modification and optimization,the scale and precision of model computation suggest that the proposed model and developed codes can meet the requirements of engineering applications.展开更多
VPNs are vital for safeguarding communication routes in the continually changing cybersecurity world.However,increasing network attack complexity and variety require increasingly advanced algorithms to recognize and c...VPNs are vital for safeguarding communication routes in the continually changing cybersecurity world.However,increasing network attack complexity and variety require increasingly advanced algorithms to recognize and categorizeVPNnetwork data.We present a novelVPNnetwork traffic flowclassificationmethod utilizing Artificial Neural Networks(ANN).This paper aims to provide a reliable system that can identify a virtual private network(VPN)traffic fromintrusion attempts,data exfiltration,and denial-of-service assaults.We compile a broad dataset of labeled VPN traffic flows from various apps and usage patterns.Next,we create an ANN architecture that can handle encrypted communication and distinguish benign from dangerous actions.To effectively process and categorize encrypted packets,the neural network model has input,hidden,and output layers.We use advanced feature extraction approaches to improve the ANN’s classification accuracy by leveraging network traffic’s statistical and behavioral properties.We also use cutting-edge optimizationmethods to optimize network characteristics and performance.The suggested ANN-based categorization method is extensively tested and analyzed.Results show the model effectively classifies VPN traffic types.We also show that our ANN-based technique outperforms other approaches in precision,recall,and F1-score with 98.79%accuracy.This study improves VPN security and protects against new cyberthreats.Classifying VPNtraffic flows effectively helps enterprises protect sensitive data,maintain network integrity,and respond quickly to security problems.This study advances network security and lays the groundwork for ANN-based cybersecurity solutions.展开更多
Purpose:This paper aims to address the limitations in existing research on the evolution of knowledge flow networks by proposing a meso-level institutional field knowledge flow network evolution model(IKM).The purpose...Purpose:This paper aims to address the limitations in existing research on the evolution of knowledge flow networks by proposing a meso-level institutional field knowledge flow network evolution model(IKM).The purpose is to simulate the construction process of a knowledge flow network using knowledge organizations as units and to investigate its effectiveness in replicating institutional field knowledge flow networks.Design/Methodology/Approach:The IKM model enhances the preferential attachment and growth observed in scale-free BA networks,while incorporating three adjustment parameters to simulate the selection of connection targets and the types of nodes involved in the network evolution process Using the PageRank algorithm to calculate the significance of nodes within the knowledge flow network.To compare its performance,the BA and DMS models are also employed for simulating the network.Pearson coefficient analysis is conducted on the simulated networks generated by the IKM,BA and DMS models,as well as on the actual network.Findings:The research findings demonstrate that the IKM model outperforms the BA and DMS models in replicating the institutional field knowledge flow network.It provides comprehensive insights into the evolution mechanism of knowledge flow networks in the scientific research realm.The model also exhibits potential applicability to other knowledge networks that involve knowledge organizations as node units.Research Limitations:This study has some limitations.Firstly,it primarily focuses on the evolution of knowledge flow networks within the field of physics,neglecting other fields.Additionally,the analysis is based on a specific set of data,which may limit the generalizability of the findings.Future research could address these limitations by exploring knowledge flow networks in diverse fields and utilizing broader datasets.Practical Implications:The proposed IKM model offers practical implications for the construction and analysis of knowledge flow networks within institutions.It provides a valuable tool for understanding and managing knowledge exchange between knowledge organizations.The model can aid in optimizing knowledge flow and enhancing collaboration within organizations.Originality/value:This research highlights the significance of meso-level studies in understanding knowledge organization and its impact on knowledge flow networks.The IKM model demonstrates its effectiveness in replicating institutional field knowledge flow networks and offers practical implications for knowledge management in institutions.Moreover,the model has the potential to be applied to other knowledge networks,which are formed by knowledge organizations as node units.展开更多
Recent advances in deep neural networks have shed new light on physics,engineering,and scientific computing.Reconciling the data-centered viewpoint with physical simulation is one of the research hotspots.The physicsi...Recent advances in deep neural networks have shed new light on physics,engineering,and scientific computing.Reconciling the data-centered viewpoint with physical simulation is one of the research hotspots.The physicsinformedneural network(PINN)is currently the most general framework,which is more popular due to theconvenience of constructing NNs and excellent generalization ability.The automatic differentiation(AD)-basedPINN model is suitable for the homogeneous scientific problem;however,it is unclear how AD can enforce fluxcontinuity across boundaries between cells of different properties where spatial heterogeneity is represented bygrid cells with different physical properties.In this work,we propose a criss-cross physics-informed convolutionalneural network(CC-PINN)learning architecture,aiming to learn the solution of parametric PDEs with spatialheterogeneity of physical properties.To achieve the seamless enforcement of flux continuity and integration ofphysicalmeaning into CNN,a predefined 2D convolutional layer is proposed to accurately express transmissibilitybetween adjacent cells.The efficacy of the proposedmethodwas evaluated through predictions of several petroleumreservoir problems with spatial heterogeneity and compared against state-of-the-art(PINN)through numericalanalysis as a benchmark,which demonstrated the superiority of the proposed method over the PINN.展开更多
Traffic flow prediction plays a key role in the construction of intelligent transportation system.However,due to its complex spatio-temporal dependence and its uncertainty,the research becomes very challenging.Most of...Traffic flow prediction plays a key role in the construction of intelligent transportation system.However,due to its complex spatio-temporal dependence and its uncertainty,the research becomes very challenging.Most of the existing studies are based on graph neural networks that model traffic flow graphs and try to use fixed graph structure to deal with the relationship between nodes.However,due to the time-varying spatial correlation of the traffic network,there is no fixed node relationship,and these methods cannot effectively integrate the temporal and spatial features.This paper proposes a novel temporal-spatial dynamic graph convolutional network(TSADGCN).The dynamic time warping algorithm(DTW)is introduced to calculate the similarity of traffic flow sequence among network nodes in the time dimension,and the spatiotemporal graph of traffic flow is constructed to capture the spatiotemporal characteristics and dependencies of traffic flow.By combining graph attention network and time attention network,a spatiotemporal convolution block is constructed to capture spatiotemporal characteristics of traffic data.Experiments on open data sets PEMSD4 and PEMSD8 show that TSADGCN has higher prediction accuracy than well-known traffic flow prediction algorithms.展开更多
As one of the core modules for air traffic flow management,Air Traffic Flow Prediction(ATFP)in the Multi-Airport System(MAS)is a prerequisite for demand and capacity balance in the complex meteorological environment.D...As one of the core modules for air traffic flow management,Air Traffic Flow Prediction(ATFP)in the Multi-Airport System(MAS)is a prerequisite for demand and capacity balance in the complex meteorological environment.Due to the challenge of implicit interaction mechanism among traffic flow,airspace capacity and weather impact,the Weather-aware ATFP(Wa-ATFP)is still a nontrivial issue.In this paper,a novel Multi-faceted Spatio-Temporal Graph Convolutional Network(MSTGCN)is proposed to address the Wa-ATFP within the complex operations of MAS.Firstly,a spatio-temporal graph is constructed with three different nodes,including airport,route,and fix to describe the topology structure of MAS.Secondly,a weather-aware multi-faceted fusion module is proposed to integrate the feature of air traffic flow and the auxiliary features of capacity and weather,which can effectively address the complex impact of severe weather,e.g.,thunderstorms.Thirdly,to capture the latent connections of nodes,an adaptive graph connection constructor is designed.The experimental results with the real-world operational dataset in Guangdong-Hong Kong-Macao Greater Bay Area,China,validate that the proposed approach outperforms the state-of-the-art machine-learning and deep-learning based baseline approaches in performance.展开更多
Due to the rapid evolution of Advanced Persistent Threats(APTs)attacks,the emergence of new and rare attack samples,and even those never seen before,make it challenging for traditional rule-based detection methods to ...Due to the rapid evolution of Advanced Persistent Threats(APTs)attacks,the emergence of new and rare attack samples,and even those never seen before,make it challenging for traditional rule-based detection methods to extract universal rules for effective detection.With the progress in techniques such as transfer learning and meta-learning,few-shot network attack detection has progressed.However,challenges in few-shot network attack detection arise from the inability of time sequence flow features to adapt to the fixed length input requirement of deep learning,difficulties in capturing rich information from original flow in the case of insufficient samples,and the challenge of high-level abstract representation.To address these challenges,a few-shot network attack detection based on NFHP(Network Flow Holographic Picture)-RN(ResNet)is proposed.Specifically,leveraging inherent properties of images such as translation invariance,rotation invariance,scale invariance,and illumination invariance,network attack traffic features and contextual relationships are intuitively represented in NFHP.In addition,an improved RN network model is employed for high-level abstract feature extraction,ensuring that the extracted high-level abstract features maintain the detailed characteristics of the original traffic behavior,regardless of changes in background traffic.Finally,a meta-learning model based on the self-attention mechanism is constructed,achieving the detection of novel APT few-shot network attacks through the empirical generalization of high-level abstract feature representations of known-class network attack behaviors.Experimental results demonstrate that the proposed method can learn high-level abstract features of network attacks across different traffic detail granularities.Comparedwith state-of-the-artmethods,it achieves favorable accuracy,precision,recall,and F1 scores for the identification of unknown-class network attacks through cross-validation onmultiple datasets.展开更多
Traffic flow forecasting plays a crucial role and is the key technology to realize dynamic traffic guidance and active traffic control in intelligent traffic systems(ITS).Aiming at the complex local and global spatial...Traffic flow forecasting plays a crucial role and is the key technology to realize dynamic traffic guidance and active traffic control in intelligent traffic systems(ITS).Aiming at the complex local and global spatial-temporal dynamic characteristics of traffic flow,this paper proposes a new traffic flow forecasting model spatial-temporal attention graph neural network(STA-GNN)by combining at-tention mechanism(AM)and spatial-temporal convolutional network.The model learns the hidden dynamic local spatial correlations of the traffic network by combining the dynamic adjacency matrix constructed by the graph learning layer with the graph convolutional network(GCN).The local tem-poral correlations of traffic flow at different scales are extracted by stacking multiple convolutional kernels in temporal convolutional network(TCN).And the global spatial-temporal dependencies of long-time sequences of traffic flow are captured by the spatial-temporal attention mechanism(STAtt),which enhances the global spatial-temporal modeling and the representational ability of model.The experimental results on two datasets,METR-LA and PEMS-BAY,show the proposed STA-GNN model outperforms the common baseline models in forecasting accuracy.展开更多
基金supported by the National Natural Science Foundation of China(61962016)the Ministry of Science and Technology of China(G2022033002L)+1 种基金National Natural Science Foundation of Guangxi(2022JJA170057)Guangxi Education Department’s Project on Improving the Basic Research Ability of Young and Middleaged Teachers in Universities(2023ky0812,Research on Statistical Network Delay Predictions in Large-scale SDNs).
文摘Accurate early classification of elephant flows(elephants)is important for network management and resource optimization.Elephant models,mainly based on the byte count of flows,can always achieve high accuracy,but not in a time-efficient manner.The time efficiency becomes even worse when the flows to be classified are sampled by flow entry timeout over Software-Defined Networks(SDNs)to achieve a better resource efficiency.This paper addresses this situation by combining co-training and Reinforcement Learning(RL)to enable a closed-loop classification approach that divides the entire classification process into episodes,each involving two elephant models.One predicts elephants and is retrained by a selection of flows automatically labeled online by the other.RL is used to formulate a reward function that estimates the values of the possible actions based on the current states of both models and further adjusts the ratio of flows to be labeled in each phase.Extensive evaluation based on real traffic traces shows that the proposed approach can stably predict elephants using the packets received in the first 10% of their lifetime with an accuracy of over 80%,and using only about 10% more control channel bandwidth than the baseline over the evolved SDNs.
基金supported by the National Natural Science Foundation of China(Grant No.U2340221)the National Key R&D Programof China(Grant No.2022YFC3202602)+1 种基金the NaturalScience Foundation of Jiangsu Province(Grant No.BK20230036)the 111 Project(Grant No.B17015)。
文摘Rational allocation of water flow energy in river networks is essential to addressing water-related issues in river network areas.However,current methods of calculating the spatiotemporal distribution of flow energy in river networks lack precision and efficiency.This paper introduces a novel hydrodynamic representation,the energy flow rate,defined as the product of the flow rate and kinetic energy head,to quantify the kinetic energy stored and transported in river networks.A linear equation system for the energy flow rate in a river network has been theoretically derived,enabling rapid calculations under steady flow conditions.A simplified equation is proposed to describe the exponential decay of the energy flow rate,accompanied by potential energy conversion.The coefficients in the linear equation system are determined using control equations at flow confluence and diversion nodes.This study provides foundational insights that can be used to develop new hydrodynamic modeling strategies to regulate water flow energy and achieve coordinated management of water-related issues in river networks.
基金supported in part by Scientific Research Fund of Zhejiang Provincial Education Department under Grant Y202351110in part by Huzhou Science and Technology Plan Project under Grant 2024YZ23+1 种基金in part by Research Fund of National Key Laboratory of Advanced Communication Networks under Grant SCX23641X004in part by Postgraduate Research and Innovation Project of Huzhou University under Grant 2024KYCX50.
文摘Zero Trust Network(ZTN)enhances network security through strict authentication and access control.However,in the ZTN,optimizing flow control to improve the quality of service is still facing challenges.Software Defined Network(SDN)provides solutions through centralized control and dynamic resource allocation,but the existing scheduling methods based on Deep Reinforcement Learning(DRL)are insufficient in terms of convergence speed and dynamic optimization capability.To solve these problems,this paper proposes DRL-AMIR,which is an efficient flow scheduling method for software defined ZTN.This method constructs a flow scheduling optimization model that comprehensively considers service delay,bandwidth occupation,and path hops.Additionally,it balances the differentiated requirements of delay-critical K-flows,bandwidth-intensive D-flows,and background B-flows through adaptiveweighting.Theproposed framework employs a customized state space comprising node labels,link bandwidth,delaymetrics,and path length.It incorporates an action space derived fromnode weights and a hybrid reward function that integrates both single-step and multi-step excitation mechanisms.Based on these components,a hierarchical architecture is designed,effectively integrating the data plane,control plane,and knowledge plane.In particular,the adaptive expert mechanism is introduced,which triggers the shortest path algorithm in the training process to accelerate convergence,reduce trial and error costs,and maintain stability.Experiments across diverse real-world network topologies demonstrate that DRL-AMIR achieves a 15–20%reduction in K-flow transmission delays,a 10–15%improvement in link bandwidth utilization compared to SPR,QoSR,and DRSIR,and a 30%faster convergence speed via adaptive expert mechanisms.
基金supported by the National Natural Science Foundation of China(Grant Nos.62472149,62376089,62202147)Hubei Provincial Science and Technology Plan Project(2023BCB04100).
文摘Accurate traffic flow prediction has a profound impact on modern traffic management. Traffic flow has complex spatial-temporal correlations and periodicity, which poses difficulties for precise prediction. To address this problem, a Multi-head Self-attention and Spatial-Temporal Graph Convolutional Network (MSSTGCN) for multiscale traffic flow prediction is proposed. Firstly, to capture the hidden traffic periodicity of traffic flow, traffic flow is divided into three kinds of periods, including hourly, daily, and weekly data. Secondly, a graph attention residual layer is constructed to learn the global spatial features across regions. Local spatial-temporal dependence is captured by using a T-GCN module. Thirdly, a transformer layer is introduced to learn the long-term dependence in time. A position embedding mechanism is introduced to label position information for all traffic sequences. Thus, this multi-head self-attention mechanism can recognize the sequence order and allocate weights for different time nodes. Experimental results on four real-world datasets show that the MSSTGCN performs better than the baseline methods and can be successfully adapted to traffic prediction tasks.
基金supported by the Program of Key Projects of Foundation Strengthening Plan,China(No.2022-JCJQ-ZD114-12-03)the Graduate Student Innovation Fund Lighthouse Program of Southwest University of Science and Technology,China(No.24ycx3009)。
文摘The numerical calculation method has greatly promoted the process of optimal design of scramjet,but it still needs extremely heavy calculation for the model with complex thermochemical reaction.Data-driven deep learning relies heavily on a large amount of data in the face of complex nonlinear features.Therefore,combining“data-driven model”and“Navier-Stokes equation”,an intelligent prediction model of supersonic combustion flow process is constructed.This algorithm integrates the theory priors of combustion flow into the neural network model,and uses convolutional grouping and rearrangement to reduce the feature redundancy calculation,so as to achieve high-precision and high-efficiency prediction of velocity,density,pressure and temperature fields.This study makes a comprehensive comparison from two aspects of performance and efficiency.Unsteady scramjet multi-physical field dataset is constructed under different incoming Mach number conditions.The experimental results show that compared with other methods,the proposed algorithm can achieve the maximum Peak Signal-to-Noise Ratio(PSNR)improvement of 38.75%and Learned Perceptual Image Patch Similarity(LPIPS)improvement of 68.13%in predicting the average quality of images,and the computational cost of the model is reduced by 30.36%compared with other models.In addition,the high model can also effectively predict the unknown incoming flow condition.
基金The National Natural Science Foundation of China(No.72001107,72271120)the Fundamental Research Funds for the Central Universities(No.NS2024047,NP2024106)the China Postdoctoral Science Foundation(No.2020T130297,2019M660119).
文摘The presence of circles in the network maximum flow problem increases the complexity of the preflow algorithm.This study proposes a novel two-stage preflow algorithm to address this issue.First,this study proves that at least one zero-flow arc must be present when the flow of the network reaches its maximum value.This result indicates that the maximum flow of the network will remain constant if a zero-flow arc within a circle is removed;therefore,the maximum flow of each network without circles can be calculated.The first stage involves identifying the zero-flow arc in the circle when the network flow reaches its maximum.The second stage aims to remove the zero-flow arc identified and modified in the first stage,thereby producing a new network without circles.The maximum flow of the original looped network can be obtained by solving the maximum flow of the newly generated acyclic network.Finally,an example is provided to demonstrate the validity and feasibility of this algorithm.This algorithm not only improves computational efficiency but also provides new perspectives and tools for solving similar network optimization problems.
基金Supported by the National Natural Science Foundation of China(No.62304022)。
文摘This research introduces a spectrum-based physics-informed neural network(SP-PINN)model to significantly improve the accuracy of calculation of two-phase flow parameters,surpassing existing methods that have limitations in global and continuous data sampling.SP-PINNs address the challenges of traditional methods in terms of continuous sampling by integrating the spectral analysis and pressure correction into the Navier-Stokes(N-S)equations,enhancing the predictive accuracy especially in critical regions like gas-phase boundaries and velocity peaks.The novel introduction of a pressure-correction module within SP-PINNs mitigates prediction errors,achieving a substantial reduction to 1‰compared with the conventional physics-informed neural network(PINN)approaches.Experimental applications validate the model’s ability to accurately and rapidly predict flow parameters with different sampling time intervals,with the computation time of predicting unsampled data less than 0.01 s.Such advancements signify a 100-fold improvement over traditional DNS calculations,underscoring the model’s potential in the real-time calculation and analysis of multiphase flow dynamics.
基金supported in part by National Natural Science Foundation of China under Grant 52007026.
文摘With the widespread implementation of distributed generation(DG)and the integration of soft open point(SOP)into the distribution network(DN),the latter is steadily transitioning into a flexible distribution network(FDN),the calculation of carbon flow distribution in FDN is more difficult.To this end,this study constructs a model for low-carbon optimal operations within the FDN on the basis of enhanced carbon emission flow(CEF).First,the carbon emission characteristics of FDNs are scrutinized and an improved method for calculating carbon flow within these networks is proposed.Subsequently,a model for optimizing low-carbon operations within FDNs is formulated based on the refined CEF,which merges the specificities of DG and intelligent SOP.Finally,this model is scrutinized using an upgraded IEEE 33-node distribution system,a comparative analysis of the cases reveals that when DG and SOP are operated in a coordinated manner in the FDN,with the cost of electricity generation was reduced by 40.63 percent and the cost of carbon emissions by 10.18 percent.The findings indicate that the judicious optimization of areas exhibiting higher carbon flow rates can effectively enhance the economic efficiency of DN operations and curtail the carbon emissions of the overall network.
基金supported by the National Natural Science Foundation of China(No.52174043)the Beijing Natural Science Foundation(No.3242019)+1 种基金the CNPC Innovation Foundation(No.2022DQ02-0208)the State Key Laboratory of Deep Oil and Gas(No.SKLD0G2024-KFZD-06).
文摘Two actual rocks drilled from a typical ultra-deep hydrocarbon reservoir in the Tarim Basin are selected to conduct in-situ stress-loading micro-focus CT scanning experiments.The gray images of rock microstructure at different stress loading stages are obtained.The U-Net fully convolutional neural network is utilized to achieve fine semantic segmentation of rock skeleton,pore space,and microfractures based on CT slice images of deep rocks.The three-dimensional digital rock models of deformed multiscale fractured-porous media at different stress loading stages are thereafter reconstructed,and the equivalent fracture-pore network models are finally extracted to explore the underlying mechanisms of gas-water two-phase flow at the pore-scale.Results indicate that,in the process of insitu stress loading,both the deep rocks have experienced three stages:linear elastic deformation,nonlinear plastic deformation,and shear failure.The micro-mechanical behavior greatly affects the dynamic deformation of rock microstructure and gas-water two-phase flow.In the linear elastic deformation stage,with the increase in in-situ stress,both the deep rocks are gradually compacted,leading to decreases in average pore radius,pore throat ratio,tortuosity,and water-phase relative permeability,while the coordination number nearly remains unchanged.In the plastic deformation stage,the synergistic influence of rock compaction and existence of micro-fractures typically exert a great effect on pore-throat topological properties and gas-water relative permeability.In the shear failure stage,due to the generation and propagation of micro-fractures inside the deep rock,the topological connectivity becomes better,fluid flow paths increase,and flow conductivity is promoted,thus leading to sharp increases in average pore radius and coordination number,rapid decreases in pore throat ratio and tortuosity,as well as remarkable improvement in relative permeability of gas phase and waterphase.
基金supported by the Major Project of the National Social Science Fund of China,titled“Design Path Selection for the Mechanism of New and Old Growth Driver Conversion”(Grant No.18ZDA077)by the Joint Special Major Research Project of the Yangtze River Delta Economics and Social Development Research Center at Nanjing University and the Collaborative Innovation Center for China Economy(CICCE),titled“Practicing Innovation in China’s Development Economics for the Yangtze River Delta:From Industrial Clusters to Technological Clusters”(Grant No.CYD2022006).
文摘The global clustering of inventive talent shapes innovation capacity and drives economic growth.For China,this process is especially crucial in sustaining its development momentum.This paper draws on data from the EPO Worldwide Patent Statistical Database(PATSTAT)to extract global inventive talent mobility information and analyzes the spatial structural evolution of the global inventive talent flow network.The study finds that this network is undergoing a multi-polar transformation,characterized by the rising importance of a few central countries-such as the United States,Germany,and China-and the increasing marginalization of many peripheral countries.In response to this typical phenomenon,the paper constructs an endogenous migration model and conducts empirical testing using the Temporal Exponential Random Graph Model(TERGM).The results reveal several endogenous mechanisms driving global inventive talent flows,including reciprocity,path dependence,convergence effects,transitivity,and cyclic structures,all of which contribute to the network’s multi-polar trend.In addition,differences in regional industrial structures significantly influence talent mobility choices and are a decisive factor in the formation of poles within the multi-polar landscape.Based on these findings,it is suggested that efforts be made to foster two-way channels for talent exchange between China and other global innovation hubs,in order to enhance international collaboration and knowledge flow.We should aim to reduce the migration costs and institutional barriers faced by R&D personnel,thereby encouraging greater mobility of high-skilled talent.Furthermore,the government is advised to strategically leverage regional strengths in high-tech industries as a lever to capture competitive advantages in emerging technologies and products,ultimately strengthening the country’s position in the global innovation landscape.
基金supported by the National Natural Science Foundation of China(Grant Nos.42272338 and 41827807)Department of Transportation of Zhejiang Province,China(Grant No.202213).
文摘Physics-informed neural networks(PINNs)have prevailed as differentiable simulators to investigate flow in porous media.Despite recent progress PINNs have achieved,practical geotechnical scenarios cannot be readily simulated because conventional PINNs fail in discontinuous heterogeneous porous media or multi-layer strata when labeled data are missing.This work aims to develop a universal network structure to encode the mass continuity equation and Darcy’s law without labeled data.The finite element approximation,which can decompose a complex heterogeneous domain into simpler ones,is adopted to build the differentiable network.Without conventional DNNs,physics-encoded finite element network(PEFEN)can avoid spectral bias and learn high-frequency functions with sharp/steep gradients.PEFEN rigorously encodes Dirichlet and Neumann boundary conditions without training.Benefiting from its discretized formulation,the discontinuous heterogeneous hydraulic conductivity is readily embedded into the network.Three typical cases are reproduced to corroborate PEFEN’s superior performance over conventional PINNs and the PINN with mixed formulation.PEFEN is sparse and demonstrated to be capable of dealing with heterogeneity with much fewer training iterations(less than 1/30)than the improved PINN with mixed formulation.Thus,PEFEN saves energy and contributes to low-carbon AI for science.The last two cases focus on common geotechnical settings of impermeable sheet pile in singlelayer and multi-layer strata.PEFEN solves these cases with high accuracy,circumventing costly labeled data,extra computational burden,and additional treatment.Thus,this study warrants the further development and application of PEFEN as a novel differentiable network in porous flow of practical geotechnical engineering.
基金This work was supported in part by the National Key R&D Program of China 2021YFE0110500in part by the National Natural Science Foundation of China under Grant 62062021in part by the Guiyang Scientific Plan Project[2023]48-11.
文摘Unsupervised methods based on density representation have shown their abilities in anomaly detection,but detection performance still needs to be improved.Specifically,approaches using normalizing flows can accurately evaluate sample distributions,mapping normal features to the normal distribution and anomalous features outside it.Consequently,this paper proposes a Normalizing Flow-based Bidirectional Mapping Residual Network(NF-BMR).It utilizes pre-trained Convolutional Neural Networks(CNN)and normalizing flows to construct discriminative source and target domain feature spaces.Additionally,to better learn feature information in both domain spaces,we propose the Bidirectional Mapping Residual Network(BMR),which maps sample features to these two spaces for anomaly detection.The two detection spaces effectively complement each other’s deficiencies and provide a comprehensive feature evaluation from two perspectives,which leads to the improvement of detection performance.Comparative experimental results on the MVTec AD and DAGM datasets against the Bidirectional Pre-trained Feature Mapping Network(B-PFM)and other state-of-the-art methods demonstrate that the proposed approach achieves superior performance.On the MVTec AD dataset,NF-BMR achieves an average AUROC of 98.7%for all 15 categories.Especially,it achieves 100%optimal detection performance in five categories.On the DAGM dataset,the average AUROC across ten categories is 98.7%,which is very close to supervised methods.
基金sponsored by the General Program of the National Natural Science Foundation of China(Grant Nos.52079129 and 52209148)the Hubei Provincial General Fund,China(Grant No.2023AFB567)。
文摘Analyzing rock mass seepage using the discrete fracture network(DFN)flow model poses challenges when dealing with complex fracture networks.This paper presents a novel DFN flow model that incorporates the actual connections of large-scale fractures.Notably,this model efficiently manages over 20,000 fractures without necessitating adjustments to the DFN geometry.All geometric analyses,such as identifying connected fractures,dividing the two-dimensional domain into closed loops,triangulating arbitrary loops,and refining triangular elements,are fully automated.The analysis processes are comprehensively introduced,and core algorithms,along with their pseudo-codes,are outlined and explained to assist readers in their programming endeavors.The accuracy of geometric analyses is validated through topological graphs representing the connection relationships between fractures.In practical application,the proposed model is employed to assess the water-sealing effectiveness of an underground storage cavern project.The analysis results indicate that the existing design scheme can effectively prevent the stored oil from leaking in the presence of both dense and sparse fractures.Furthermore,following extensive modification and optimization,the scale and precision of model computation suggest that the proposed model and developed codes can meet the requirements of engineering applications.
文摘VPNs are vital for safeguarding communication routes in the continually changing cybersecurity world.However,increasing network attack complexity and variety require increasingly advanced algorithms to recognize and categorizeVPNnetwork data.We present a novelVPNnetwork traffic flowclassificationmethod utilizing Artificial Neural Networks(ANN).This paper aims to provide a reliable system that can identify a virtual private network(VPN)traffic fromintrusion attempts,data exfiltration,and denial-of-service assaults.We compile a broad dataset of labeled VPN traffic flows from various apps and usage patterns.Next,we create an ANN architecture that can handle encrypted communication and distinguish benign from dangerous actions.To effectively process and categorize encrypted packets,the neural network model has input,hidden,and output layers.We use advanced feature extraction approaches to improve the ANN’s classification accuracy by leveraging network traffic’s statistical and behavioral properties.We also use cutting-edge optimizationmethods to optimize network characteristics and performance.The suggested ANN-based categorization method is extensively tested and analyzed.Results show the model effectively classifies VPN traffic types.We also show that our ANN-based technique outperforms other approaches in precision,recall,and F1-score with 98.79%accuracy.This study improves VPN security and protects against new cyberthreats.Classifying VPNtraffic flows effectively helps enterprises protect sensitive data,maintain network integrity,and respond quickly to security problems.This study advances network security and lays the groundwork for ANN-based cybersecurity solutions.
基金supported in part by the National Natural Science Foundation of China under Grant 72264036in part by the West Light Foundation of The Chinese Academy of Sciences under Grant 2020-XBQNXZ-020+1 种基金Social Science Foundation of Xinjiang under Grant 2023BGL077the Research Program for High-level Talent Program of Xinjiang University of Finance and Economics 2022XGC041,2022XGC042.
文摘Purpose:This paper aims to address the limitations in existing research on the evolution of knowledge flow networks by proposing a meso-level institutional field knowledge flow network evolution model(IKM).The purpose is to simulate the construction process of a knowledge flow network using knowledge organizations as units and to investigate its effectiveness in replicating institutional field knowledge flow networks.Design/Methodology/Approach:The IKM model enhances the preferential attachment and growth observed in scale-free BA networks,while incorporating three adjustment parameters to simulate the selection of connection targets and the types of nodes involved in the network evolution process Using the PageRank algorithm to calculate the significance of nodes within the knowledge flow network.To compare its performance,the BA and DMS models are also employed for simulating the network.Pearson coefficient analysis is conducted on the simulated networks generated by the IKM,BA and DMS models,as well as on the actual network.Findings:The research findings demonstrate that the IKM model outperforms the BA and DMS models in replicating the institutional field knowledge flow network.It provides comprehensive insights into the evolution mechanism of knowledge flow networks in the scientific research realm.The model also exhibits potential applicability to other knowledge networks that involve knowledge organizations as node units.Research Limitations:This study has some limitations.Firstly,it primarily focuses on the evolution of knowledge flow networks within the field of physics,neglecting other fields.Additionally,the analysis is based on a specific set of data,which may limit the generalizability of the findings.Future research could address these limitations by exploring knowledge flow networks in diverse fields and utilizing broader datasets.Practical Implications:The proposed IKM model offers practical implications for the construction and analysis of knowledge flow networks within institutions.It provides a valuable tool for understanding and managing knowledge exchange between knowledge organizations.The model can aid in optimizing knowledge flow and enhancing collaboration within organizations.Originality/value:This research highlights the significance of meso-level studies in understanding knowledge organization and its impact on knowledge flow networks.The IKM model demonstrates its effectiveness in replicating institutional field knowledge flow networks and offers practical implications for knowledge management in institutions.Moreover,the model has the potential to be applied to other knowledge networks,which are formed by knowledge organizations as node units.
基金the National Natural Science Foundation of China(No.52274048)Beijing Natural Science Foundation(No.3222037)+1 种基金the CNPC 14th Five-Year Perspective Fundamental Research Project(No.2021DJ2104)the Science Foundation of China University of Petroleum,Beijing(No.2462021YXZZ010).
文摘Recent advances in deep neural networks have shed new light on physics,engineering,and scientific computing.Reconciling the data-centered viewpoint with physical simulation is one of the research hotspots.The physicsinformedneural network(PINN)is currently the most general framework,which is more popular due to theconvenience of constructing NNs and excellent generalization ability.The automatic differentiation(AD)-basedPINN model is suitable for the homogeneous scientific problem;however,it is unclear how AD can enforce fluxcontinuity across boundaries between cells of different properties where spatial heterogeneity is represented bygrid cells with different physical properties.In this work,we propose a criss-cross physics-informed convolutionalneural network(CC-PINN)learning architecture,aiming to learn the solution of parametric PDEs with spatialheterogeneity of physical properties.To achieve the seamless enforcement of flux continuity and integration ofphysicalmeaning into CNN,a predefined 2D convolutional layer is proposed to accurately express transmissibilitybetween adjacent cells.The efficacy of the proposedmethodwas evaluated through predictions of several petroleumreservoir problems with spatial heterogeneity and compared against state-of-the-art(PINN)through numericalanalysis as a benchmark,which demonstrated the superiority of the proposed method over the PINN.
基金supported by the National Natural Science Foundation of China(Grant:62176086).
文摘Traffic flow prediction plays a key role in the construction of intelligent transportation system.However,due to its complex spatio-temporal dependence and its uncertainty,the research becomes very challenging.Most of the existing studies are based on graph neural networks that model traffic flow graphs and try to use fixed graph structure to deal with the relationship between nodes.However,due to the time-varying spatial correlation of the traffic network,there is no fixed node relationship,and these methods cannot effectively integrate the temporal and spatial features.This paper proposes a novel temporal-spatial dynamic graph convolutional network(TSADGCN).The dynamic time warping algorithm(DTW)is introduced to calculate the similarity of traffic flow sequence among network nodes in the time dimension,and the spatiotemporal graph of traffic flow is constructed to capture the spatiotemporal characteristics and dependencies of traffic flow.By combining graph attention network and time attention network,a spatiotemporal convolution block is constructed to capture spatiotemporal characteristics of traffic data.Experiments on open data sets PEMSD4 and PEMSD8 show that TSADGCN has higher prediction accuracy than well-known traffic flow prediction algorithms.
基金supported by the National Key Research and Development Program of China(No.2022YFB2602402)the National Natural Science Foundation of China(Nos.U2033215 and U2133210).
文摘As one of the core modules for air traffic flow management,Air Traffic Flow Prediction(ATFP)in the Multi-Airport System(MAS)is a prerequisite for demand and capacity balance in the complex meteorological environment.Due to the challenge of implicit interaction mechanism among traffic flow,airspace capacity and weather impact,the Weather-aware ATFP(Wa-ATFP)is still a nontrivial issue.In this paper,a novel Multi-faceted Spatio-Temporal Graph Convolutional Network(MSTGCN)is proposed to address the Wa-ATFP within the complex operations of MAS.Firstly,a spatio-temporal graph is constructed with three different nodes,including airport,route,and fix to describe the topology structure of MAS.Secondly,a weather-aware multi-faceted fusion module is proposed to integrate the feature of air traffic flow and the auxiliary features of capacity and weather,which can effectively address the complex impact of severe weather,e.g.,thunderstorms.Thirdly,to capture the latent connections of nodes,an adaptive graph connection constructor is designed.The experimental results with the real-world operational dataset in Guangdong-Hong Kong-Macao Greater Bay Area,China,validate that the proposed approach outperforms the state-of-the-art machine-learning and deep-learning based baseline approaches in performance.
基金supported by the National Natural Science Foundation of China(Nos.U19A208162202320)+2 种基金the Fundamental Research Funds for the Central Universities(No.SCU2023D008)the Science and Engineering Connotation Development Project of Sichuan University(No.2020SCUNG129)the Key Laboratory of Data Protection and Intelligent Management(Sichuan University),Ministry of Education.
文摘Due to the rapid evolution of Advanced Persistent Threats(APTs)attacks,the emergence of new and rare attack samples,and even those never seen before,make it challenging for traditional rule-based detection methods to extract universal rules for effective detection.With the progress in techniques such as transfer learning and meta-learning,few-shot network attack detection has progressed.However,challenges in few-shot network attack detection arise from the inability of time sequence flow features to adapt to the fixed length input requirement of deep learning,difficulties in capturing rich information from original flow in the case of insufficient samples,and the challenge of high-level abstract representation.To address these challenges,a few-shot network attack detection based on NFHP(Network Flow Holographic Picture)-RN(ResNet)is proposed.Specifically,leveraging inherent properties of images such as translation invariance,rotation invariance,scale invariance,and illumination invariance,network attack traffic features and contextual relationships are intuitively represented in NFHP.In addition,an improved RN network model is employed for high-level abstract feature extraction,ensuring that the extracted high-level abstract features maintain the detailed characteristics of the original traffic behavior,regardless of changes in background traffic.Finally,a meta-learning model based on the self-attention mechanism is constructed,achieving the detection of novel APT few-shot network attacks through the empirical generalization of high-level abstract feature representations of known-class network attack behaviors.Experimental results demonstrate that the proposed method can learn high-level abstract features of network attacks across different traffic detail granularities.Comparedwith state-of-the-artmethods,it achieves favorable accuracy,precision,recall,and F1 scores for the identification of unknown-class network attacks through cross-validation onmultiple datasets.
基金Supported by the Key R&D Program of Gansu Province(No.23YFGA0063)the National Natural Science Foundation of China(No.62363022,61663021)+1 种基金the Natural Science Foundation of Gansu Province(No.22JR5RA226,23JRRA886)the Gansu Provincial De-partment of Education:Industrial Support Plan Project(No.2023CYZC-35).
文摘Traffic flow forecasting plays a crucial role and is the key technology to realize dynamic traffic guidance and active traffic control in intelligent traffic systems(ITS).Aiming at the complex local and global spatial-temporal dynamic characteristics of traffic flow,this paper proposes a new traffic flow forecasting model spatial-temporal attention graph neural network(STA-GNN)by combining at-tention mechanism(AM)and spatial-temporal convolutional network.The model learns the hidden dynamic local spatial correlations of the traffic network by combining the dynamic adjacency matrix constructed by the graph learning layer with the graph convolutional network(GCN).The local tem-poral correlations of traffic flow at different scales are extracted by stacking multiple convolutional kernels in temporal convolutional network(TCN).And the global spatial-temporal dependencies of long-time sequences of traffic flow are captured by the spatial-temporal attention mechanism(STAtt),which enhances the global spatial-temporal modeling and the representational ability of model.The experimental results on two datasets,METR-LA and PEMS-BAY,show the proposed STA-GNN model outperforms the common baseline models in forecasting accuracy.
