This paper proposes an extended system dependence graph called AspectSDG to represent control and data dependences for AspeetC＋＋ programs, and presents an approach for the construction of AspectSDG. This approach de...This paper proposes an extended system dependence graph called AspectSDG to represent control and data dependences for AspeetC＋＋ programs, and presents an approach for the construction of AspectSDG. This approach decomposes aspect-oriented programs into three parts： component codes, aspect codes, and weaving codes. It constructs program dependence graphs （PDGs） for each part, and then connects the PDGs at call sites to form the complete AspectSDG. The AspectSDG can deal with advice precedence correctly, and represent the additional dependences caused by aspect codes. Based on this model, we introduce how to compute a static slice of an AspectC＋ ＋ program.展开更多
Large-scale complex systems have the feature of including large amount of variables that have complex relationships, for which signed directed graph （SDG） model could serve as a significant tool by describing the ca...Large-scale complex systems have the feature of including large amount of variables that have complex relationships, for which signed directed graph （SDG） model could serve as a significant tool by describing the causal relationships among variables. Although qualitative SDG expresses the causing effects between variables easily and clearly, it has many disadvantages or limitations. Probabilistic SDG proposed in the article describes deliver relationships among faults and variables by conditional probabilities, which contains more information and performs more applicability. The article introduces the concepts and con- struction approaches of probabilistic SDG, and presents the inference approaches aiming at fault diagnosis in this framework, i.e. Bayesian inference with graph elimination or junction tree algorithms to compute fault probabilities. Finally, the probabilistic SDG of a typical example of 65t/h boiler system is given.展开更多
The lack of existing solutions makes it really hard to understand formal specification languages since the application domain for representations is useful for the purpose of carrying out certain software engineering ...The lack of existing solutions makes it really hard to understand formal specification languages since the application domain for representations is useful for the purpose of carrying out certain software engineering operations such as slicing and the computation of program metrics.A Z specification dependence graph is presented in this letter. It draws on the strengths of a range of earlier works and adapts them, if necessary, to the Z language.展开更多
Accurate traffic pattern prediction in largescale networks is of great importance for intelligent system management and automatic resource allocation.System-level mobile traffic forecasting has significant challenges ...Accurate traffic pattern prediction in largescale networks is of great importance for intelligent system management and automatic resource allocation.System-level mobile traffic forecasting has significant challenges due to the tremendous temporal and spatial dynamics introduced by diverse Internet user behaviors and frequent traffic migration.Spatialtemporal graph modeling is an efficient approach for analyzing the spatial relations and temporal trends of mobile traffic in a large system.Previous research may not reflect the optimal dependency by ignoring inter-base station dependency or pre-determining the explicit geological distance as the interrelationship of base stations.To overcome the limitations of graph structure,this study proposes an adaptive graph convolutional network(AGCN)that captures the latent spatial dependency by developing self-adaptive dependency matrices and acquires temporal dependency using recurrent neural networks.Evaluated on two mobile network datasets,the experimental results demonstrate that this method outperforms other baselines and reduces the mean absolute error by 3.7%and 5.6%compared to time-series based approaches.展开更多
Deep neural network-based relational extraction research has made significant progress in recent years,andit provides data support for many natural language processing downstream tasks such as building knowledgegraph,...Deep neural network-based relational extraction research has made significant progress in recent years,andit provides data support for many natural language processing downstream tasks such as building knowledgegraph,sentiment analysis and question-answering systems.However,previous studies ignored much unusedstructural information in sentences that could enhance the performance of the relation extraction task.Moreover,most existing dependency-based models utilize self-attention to distinguish the importance of context,whichhardly deals withmultiple-structure information.To efficiently leverage multiple structure information,this paperproposes a dynamic structure attention mechanism model based on textual structure information,which deeplyintegrates word embedding,named entity recognition labels,part of speech,dependency tree and dependency typeinto a graph convolutional network.Specifically,our model extracts text features of different structures from theinput sentence.Textual Structure information Graph Convolutional Networks employs the dynamic structureattention mechanism to learn multi-structure attention,effectively distinguishing important contextual features invarious structural information.In addition,multi-structure weights are carefully designed as amergingmechanismin the different structure attention to dynamically adjust the final attention.This paper combines these featuresand trains a graph convolutional network for relation extraction.We experiment on supervised relation extractiondatasets including SemEval 2010 Task 8,TACRED,TACREV,and Re-TACED,the result significantly outperformsthe previous.展开更多
Due to the structural dependencies among concurrent events in the knowledge graph and the substantial amount of sequential correlation information carried by temporally adjacent events,we propose an Independent Recurr...Due to the structural dependencies among concurrent events in the knowledge graph and the substantial amount of sequential correlation information carried by temporally adjacent events,we propose an Independent Recurrent Temporal Graph Convolution Networks(IndRT-GCNets)framework to efficiently and accurately capture event attribute information.The framework models the knowledge graph sequences to learn the evolutionary represen-tations of entities and relations within each period.Firstly,by utilizing the temporal graph convolution module in the evolutionary representation unit,the framework captures the structural dependency relationships within the knowledge graph in each period.Meanwhile,to achieve better event representation and establish effective correlations,an independent recurrent neural network is employed to implement auto-regressive modeling.Furthermore,static attributes of entities in the entity-relation events are constrained andmerged using a static graph constraint to obtain optimal entity representations.Finally,the evolution of entity and relation representations is utilized to predict events in the next subsequent step.On multiple real-world datasets such as Freebase13(FB13),Freebase 15k(FB15K),WordNet11(WN11),WordNet18(WN18),FB15K-237,WN18RR,YAGO3-10,and Nell-995,the results of multiple evaluation indicators show that our proposed IndRT-GCNets framework outperforms most existing models on knowledge reasoning tasks,which validates the effectiveness and robustness.展开更多
An engineering system may consist of several different types of components,belonging to such physical"domains"as mechanical,electrical,fluid,and thermal.It is termed a multi-domain(or multi-physics)system.Th...An engineering system may consist of several different types of components,belonging to such physical"domains"as mechanical,electrical,fluid,and thermal.It is termed a multi-domain(or multi-physics)system.The present paper concerns the use of linear graphs(LGs)to generate a minimal model for a multi-physics system.A state-space model has to be a minimal realization.Specifically,the number of state variables in the model should be the minimum number that can completely represent the dynamic state of the system.This choice is not straightforward.Initially,state variables are assigned to all the energy-storage elements of the system.However,some of the energy storage elements may not be independent,and then some of the chosen state variables will be redundant.An approach is presented in the paper,with illustrative examples in the mixed fluid-mechanical domains,to illustrate a way to recognize dependent energy storage elements and thereby obtain a minimal state-space model.System analysis in the frequency domain is known to be more convenient than in the time domain,mainly because the relevant operations are algebraic rather than differential.For achieving this objective,the state space model has to be converted into a transfer function.The direct way is to first convert the state-space model into the input-output differential equation,and then substitute the time derivative by the Laplace variable.This approach is shown in the paper.The same result can be obtained through the transfer function linear graph(TF LG)of the system.In a multi-physics system,first the physical domains have to be converted into an equivalent single domain(preferably,the output domain of the system),when using the method of TFLG.This procedure is illustrated as well,in the present paper.展开更多
基金Supported by the National Science Foundation forDistinguished Young Scholars (60425206) the National Natural Sci-ence Foundation of China ( 90412003 , 60373066 , 60403016 ,60503033) the National Basic Research Programof China (973 Pro-gram2002CB312000)
文摘This paper proposes an extended system dependence graph called AspectSDG to represent control and data dependences for AspeetC＋＋ programs, and presents an approach for the construction of AspectSDG. This approach decomposes aspect-oriented programs into three parts： component codes, aspect codes, and weaving codes. It constructs program dependence graphs （PDGs） for each part, and then connects the PDGs at call sites to form the complete AspectSDG. The AspectSDG can deal with advice precedence correctly, and represent the additional dependences caused by aspect codes. Based on this model, we introduce how to compute a static slice of an AspectC＋ ＋ program.
文摘Large-scale complex systems have the feature of including large amount of variables that have complex relationships, for which signed directed graph （SDG） model could serve as a significant tool by describing the causal relationships among variables. Although qualitative SDG expresses the causing effects between variables easily and clearly, it has many disadvantages or limitations. Probabilistic SDG proposed in the article describes deliver relationships among faults and variables by conditional probabilities, which contains more information and performs more applicability. The article introduces the concepts and con- struction approaches of probabilistic SDG, and presents the inference approaches aiming at fault diagnosis in this framework, i.e. Bayesian inference with graph elimination or junction tree algorithms to compute fault probabilities. Finally, the probabilistic SDG of a typical example of 65t/h boiler system is given.
文摘The lack of existing solutions makes it really hard to understand formal specification languages since the application domain for representations is useful for the purpose of carrying out certain software engineering operations such as slicing and the computation of program metrics.A Z specification dependence graph is presented in this letter. It draws on the strengths of a range of earlier works and adapts them, if necessary, to the Z language.
基金supported by the National Natural Science Foundation of China(61975020,62171053)。
文摘Accurate traffic pattern prediction in largescale networks is of great importance for intelligent system management and automatic resource allocation.System-level mobile traffic forecasting has significant challenges due to the tremendous temporal and spatial dynamics introduced by diverse Internet user behaviors and frequent traffic migration.Spatialtemporal graph modeling is an efficient approach for analyzing the spatial relations and temporal trends of mobile traffic in a large system.Previous research may not reflect the optimal dependency by ignoring inter-base station dependency or pre-determining the explicit geological distance as the interrelationship of base stations.To overcome the limitations of graph structure,this study proposes an adaptive graph convolutional network(AGCN)that captures the latent spatial dependency by developing self-adaptive dependency matrices and acquires temporal dependency using recurrent neural networks.Evaluated on two mobile network datasets,the experimental results demonstrate that this method outperforms other baselines and reduces the mean absolute error by 3.7%and 5.6%compared to time-series based approaches.
文摘Deep neural network-based relational extraction research has made significant progress in recent years,andit provides data support for many natural language processing downstream tasks such as building knowledgegraph,sentiment analysis and question-answering systems.However,previous studies ignored much unusedstructural information in sentences that could enhance the performance of the relation extraction task.Moreover,most existing dependency-based models utilize self-attention to distinguish the importance of context,whichhardly deals withmultiple-structure information.To efficiently leverage multiple structure information,this paperproposes a dynamic structure attention mechanism model based on textual structure information,which deeplyintegrates word embedding,named entity recognition labels,part of speech,dependency tree and dependency typeinto a graph convolutional network.Specifically,our model extracts text features of different structures from theinput sentence.Textual Structure information Graph Convolutional Networks employs the dynamic structureattention mechanism to learn multi-structure attention,effectively distinguishing important contextual features invarious structural information.In addition,multi-structure weights are carefully designed as amergingmechanismin the different structure attention to dynamically adjust the final attention.This paper combines these featuresand trains a graph convolutional network for relation extraction.We experiment on supervised relation extractiondatasets including SemEval 2010 Task 8,TACRED,TACREV,and Re-TACED,the result significantly outperformsthe previous.
基金the National Natural Science Founda-tion of China(62062062)hosted by Gulila Altenbek.
文摘Due to the structural dependencies among concurrent events in the knowledge graph and the substantial amount of sequential correlation information carried by temporally adjacent events,we propose an Independent Recurrent Temporal Graph Convolution Networks(IndRT-GCNets)framework to efficiently and accurately capture event attribute information.The framework models the knowledge graph sequences to learn the evolutionary represen-tations of entities and relations within each period.Firstly,by utilizing the temporal graph convolution module in the evolutionary representation unit,the framework captures the structural dependency relationships within the knowledge graph in each period.Meanwhile,to achieve better event representation and establish effective correlations,an independent recurrent neural network is employed to implement auto-regressive modeling.Furthermore,static attributes of entities in the entity-relation events are constrained andmerged using a static graph constraint to obtain optimal entity representations.Finally,the evolution of entity and relation representations is utilized to predict events in the next subsequent step.On multiple real-world datasets such as Freebase13(FB13),Freebase 15k(FB15K),WordNet11(WN11),WordNet18(WN18),FB15K-237,WN18RR,YAGO3-10,and Nell-995,the results of multiple evaluation indicators show that our proposed IndRT-GCNets framework outperforms most existing models on knowledge reasoning tasks,which validates the effectiveness and robustness.
基金supported by research grants from the Natural Sciences and Engineering Research Council(NSERC)of Canada
文摘An engineering system may consist of several different types of components,belonging to such physical"domains"as mechanical,electrical,fluid,and thermal.It is termed a multi-domain(or multi-physics)system.The present paper concerns the use of linear graphs(LGs)to generate a minimal model for a multi-physics system.A state-space model has to be a minimal realization.Specifically,the number of state variables in the model should be the minimum number that can completely represent the dynamic state of the system.This choice is not straightforward.Initially,state variables are assigned to all the energy-storage elements of the system.However,some of the energy storage elements may not be independent,and then some of the chosen state variables will be redundant.An approach is presented in the paper,with illustrative examples in the mixed fluid-mechanical domains,to illustrate a way to recognize dependent energy storage elements and thereby obtain a minimal state-space model.System analysis in the frequency domain is known to be more convenient than in the time domain,mainly because the relevant operations are algebraic rather than differential.For achieving this objective,the state space model has to be converted into a transfer function.The direct way is to first convert the state-space model into the input-output differential equation,and then substitute the time derivative by the Laplace variable.This approach is shown in the paper.The same result can be obtained through the transfer function linear graph(TF LG)of the system.In a multi-physics system,first the physical domains have to be converted into an equivalent single domain(preferably,the output domain of the system),when using the method of TFLG.This procedure is illustrated as well,in the present paper.
