In order to minimize wind turbine failures,fault diagnosis of wind turbines is becoming increasinglyimportant,deep learning methods excel at multivariate monitoring and data modeling,but they are often limited toEucli...In order to minimize wind turbine failures,fault diagnosis of wind turbines is becoming increasinglyimportant,deep learning methods excel at multivariate monitoring and data modeling,but they are often limited toEuclidean space and struggle to capture the complex coupling between wind turbine sensors.To addressthis problem,we convert SCADA data into graph data,where sensors act as nodes and their topologicalconnections act as edges,to represent these complex relationships more efficiently.Specifically,a wind turbineanomaly identification method based on deep graph convolutional neural network using similarity graphgeneration strategy(SGG-DGCN)is proposed.Firstly,a plurality of similarity graphs containing similarityinformation between nodes are generated by different distance metrics.Then,the generated similarity graphs arefused using the proposed similarity graph generation strategy.Finally,the fused similarity graphs are fed into theDGCN model for anomaly identification.To verify the effectiveness of the proposed SGG-DGCN model,we conducted a large number of experiments.The experimental results show that the proposed SGG-DGCNmodel has the highest accuracy compared with other models.In addition,the results of ablation experimentalso demonstrate that the proposed SGG strategy can effectively improve the accuracy of WT anomalyidentification.展开更多
Limit equilibrium method （LEM） and strength reduction method （SRM） are the most widely used methods for slope stability analysis. However, it can be noted that they both have some limitations in practical applicat...Limit equilibrium method （LEM） and strength reduction method （SRM） are the most widely used methods for slope stability analysis. However, it can be noted that they both have some limitations in practical application. In the LEM, the constitutive model cannot be considered and many assumptions are needed between slices of soil/rock. The SRM requires iterative calculations and does not give the slip surface directly. A method for slope stability analysis based on the graph theory is recently developed to directly calculate the minimum safety factor and potential critical slip surface according to the stress results of numerical simulation. The method is based on current stress state and can overcome the disadvantages mentioned above in the two traditional methods. The influences of edge generation and mesh geometry on the position of slip surface and the safety factor of slope are studied, in which a new method for edge generation is proposed, and reasonable mesh size is suggested. The results of benchmark examples and a rock slope show good accuracy and efficiency of the presented method.展开更多
As autonomous driving systems advance rapidly,there is a surge in demand for high-definition(HD)maps that provide accurate and dependable prior information on static environments around vehicles.As one of the main hig...As autonomous driving systems advance rapidly,there is a surge in demand for high-definition(HD)maps that provide accurate and dependable prior information on static environments around vehicles.As one of the main high-level elements in HD maps,the road lane centerline is essential for downstream tasks such as autonomous navigation and planning.Considering the complex topology and significant overlap concerns of road centerlines,previous studies have rarely examined the centerline HD map mapping problem.Recent learningbased pipelines take heuristic post-processing predictions to generate a structured centerline output without instance information.To ameliorate this situation,we propose a novel,end-to-end road centerlines vectorized graph generation pipeline,termed CenterLineFormer.CenterLineFormer takes a single onboard camera image as input and predicts a directed graph representing the lane-layer map in the bird’s-eye view(BEV).We propose a strategy for better view transformation that uses a cross-attention mechanism to generate a dense BEV feature map.With our pipeline,we can describe the connection relationship between different centerlines and generate structured lane graphs for downstream modules as planning and control.Qualitatively,our experiments emphasize that our pipeline achieves a superior performance against previous baselines on nuScenes dataset.We also show that CenterLineFormer can generate accurate centerline graph topologies on night driving and complex traffic intersection scenes.展开更多
Scene graphs of point clouds help to understand object-level relationships in the 3D space.Most graph generation methods work on 2D structured data,which cannot be used for the 3D unstructured point cloud data.Existin...Scene graphs of point clouds help to understand object-level relationships in the 3D space.Most graph generation methods work on 2D structured data,which cannot be used for the 3D unstructured point cloud data.Existing point-cloud-based methods generate the scene graph with an additional graph structure that needs labor-intensive manual annotation.To address these problems,we explore a method to convert the point clouds into structured data and generate graphs without given structures.Specifically,we cluster points with similar augmented features into groups and establish their relationships,resulting in an initial structural representation of the point cloud.Besides,we propose a Dynamic Graph Generation Network(DGGN)to judge the semantic labels of targets of different granularity.It dynamically splits and merges point groups,resulting in a scene graph with high precision.Experiments show that our methods outperform other baseline methods.They output reliable graphs describing the object-level relationships without additional manual labeled data.展开更多
Predicting molecular properties is essential for advancing for advancing drug discovery and design. Recently, Graph Neural Networks (GNNs) have gained prominence due to their ability to capture the complex structural ...Predicting molecular properties is essential for advancing for advancing drug discovery and design. Recently, Graph Neural Networks (GNNs) have gained prominence due to their ability to capture the complex structural and relational information inherent in molecular graphs. Despite their effectiveness, the “black-box” nature of GNNs remains a significant obstacle to their widespread adoption in chemistry, as it hinders interpretability and trust. In this context, several explanation methods based on factual reasoning have emerged. These methods aim to interpret the predictions made by GNNs by analyzing the key features contributing to the prediction. However, these approaches fail to answer critical questions: “How to ensure that the structure-property mapping learned by GNNs is consistent with established domain knowledge”. In this paper, we propose MMGCF, a novel counterfactual explanation framework designed specifically for the prediction of GNN-based molecular properties. MMGCF constructs a hierarchical tree structure on molecular motifs, enabling the systematic generation of counterfactuals through motif perturbations. This framework identifies causally significant motifs and elucidates their impact on model predictions, offering insights into the relationship between structural modifications and predicted properties. Our method demonstrates its effectiveness through comprehensive quantitative and qualitative evaluations of four real-world molecular datasets.展开更多
Social relationships,such as parent-offspring and friends,are crucial and stable connections between individuals,especially at the person level,and are essential for accurately describing the semantics of videos.In th...Social relationships,such as parent-offspring and friends,are crucial and stable connections between individuals,especially at the person level,and are essential for accurately describing the semantics of videos.In this paper,we analogize such a task to scene graph generation,which we call video social relationship graph generation(VSRGG).It involves generating a social relationship graph for each video based on person-level relationships.We propose a context-aware graph neural network(CAGNet)for VSRGG,which effectively generates social relationship graphs through message passing,capturing the context of the video.Specifically,CAGNet detects persons in the video,generates an initial graph via relationship proposal,and extracts facial and body features to describe the detected individuals,as well as temporal features to describe their interactions.Then,CAGNet predicts pairwise relationships between individuals using graph message passing.Additionally,we construct a new dataset,VidSoR,to evaluate VSRGG,which contains 72 h of video with 6276 person instances and 5313 relationship instances of eight relationship types.Extensive experiments show that CAGNet can make accurate predictions with a comparatively high mean recall(mRecall)when using only visual features.展开更多
It is a common practice to simulate some historical or test systems to validate the efficiency of new methods or concepts. However, there are only a small number of existing power system test cases, and validation and...It is a common practice to simulate some historical or test systems to validate the efficiency of new methods or concepts. However, there are only a small number of existing power system test cases, and validation and evaluation results, obtained using such a limited number of test cases, may not be deemed sufficient or convincing. In order to provide more available test cases, a new random graph generation algorithm, named ‘‘dualstage constructed random graph’’ algorithm, is proposed to effectively model the power grid topology. The algorithm generates a spanning tree to guarantee the connectivity of random graphs and is capable of controlling the number of lines precisely. No matter how much the average degree is,whether sparse or not, random graphs can be quickly formed to satisfy the requirements. An approach is developed to generate random graphs with prescribed numbers of connected components, in order to simulate the power grid topology under fault conditions. Our experimental study on several realistic power grid topologies proves that the proposed algorithm can quickly generate a large number of random graphs with the topology characteristics of real-world power grid.展开更多
We study the task of automated house design,which aims to automatically generate 3D houses from user requirements.However,in the automatic system,it is non-trivial due to the intrinsic complexity of house designing:1)...We study the task of automated house design,which aims to automatically generate 3D houses from user requirements.However,in the automatic system,it is non-trivial due to the intrinsic complexity of house designing:1)the understanding of user requirements,where the users can hardly provide high-quality requirements without any professional knowledge;2)the design of house plan,which mainly focuses on how to capture the effective information from user requirements.To address the above issues,we propose an automatic house design framework,called auto-3D-house design(A3HD).Unlike the previous works that consider the user requirements in an unstructured way(e.g.,natural language),we carefully design a structured list that divides the requirements into three parts(i.e.,layout,outline,and style),which focus on the attributes of rooms,the outline of the building,and the style of decoration,respectively.Following the processing of architects,we construct a bubble diagram(i.e.,graph)that covers the rooms′attributes and relations under the constraint of outline.In addition,we take each outline as a combination of points and orders,ensuring that it can represent the outlines with arbitrary shapes.Then,we propose a graph feature generation module(GFGM)to capture layout features from the bubble diagrams and an outline feature generation module(OFGM)for outline features.Finally,we render 3D houses according to the given style requirements in a rule-based method.Experiments on two benchmark datasets(i.e.,RPLAN and T3HM)demonstrate the effectiveness of our A3HD in terms of both quantitative and qualitative evaluation metrics.展开更多
Learning activities interactions between small groups is a key step in understanding team sports videos.Recent research focusing on team sports videos can be strictly regarded from the perspective of the audience rath...Learning activities interactions between small groups is a key step in understanding team sports videos.Recent research focusing on team sports videos can be strictly regarded from the perspective of the audience rather than the athlete.For team sports videos such as volleyball and basketball videos,there are plenty of intra-team and inter-team relations.In this paper,a new task named Group Scene Graph Generation is introduced to better understand intra-team relations and inter-team relations in sports videos.To tackle this problem,a novel Hierarchical Relation Network is proposed.After all players in a video are finely divided into two teams,the feature of the two teams’activities and interactions will be enhanced by Graph Convolutional Networks,which are finally recognized to generate Group Scene Graph.For evaluation,built on Volleyball dataset with additional 9660 team activity labels,a Volleyball+dataset is proposed.A baseline is set for better comparison and our experimental results demonstrate the effectiveness of our method.Moreover,the idea of our method can be directly utilized in another video-based task,Group Activity Recognition.Experiments show the priority of our method and display the link between the two tasks.Finally,from the athlete’s view,we elaborately present an interpretation that shows how to utilize Group Scene Graph to analyze teams’activities and provide professional gaming suggestions.展开更多
基金supported by National Natural Science Foundation of China(Nos.U52305124,U62201399)the Zhejiang Natural Science Foundation of China(Nos.LQ23E050002)+4 种基金the Basic Scientific Research Project of Wenzhou City(Nos.G2022008,G2023028)the General Scientific Research Project of Educational Department of Zhejiang Province(Nos.Y202249008,Y202249041)China Postdoctoral Science Foundation(Nos.2023M740988)Zhejiang Provincial Postdoctoral Science Foundation(Nos.ZJ2023122)the Master’s Innovation Foundation of Wenzhou University(Nos.3162024004106).
文摘In order to minimize wind turbine failures,fault diagnosis of wind turbines is becoming increasinglyimportant,deep learning methods excel at multivariate monitoring and data modeling,but they are often limited toEuclidean space and struggle to capture the complex coupling between wind turbine sensors.To addressthis problem,we convert SCADA data into graph data,where sensors act as nodes and their topologicalconnections act as edges,to represent these complex relationships more efficiently.Specifically,a wind turbineanomaly identification method based on deep graph convolutional neural network using similarity graphgeneration strategy(SGG-DGCN)is proposed.Firstly,a plurality of similarity graphs containing similarityinformation between nodes are generated by different distance metrics.Then,the generated similarity graphs arefused using the proposed similarity graph generation strategy.Finally,the fused similarity graphs are fed into theDGCN model for anomaly identification.To verify the effectiveness of the proposed SGG-DGCN model,we conducted a large number of experiments.The experimental results show that the proposed SGG-DGCNmodel has the highest accuracy compared with other models.In addition,the results of ablation experimentalso demonstrate that the proposed SGG strategy can effectively improve the accuracy of WT anomalyidentification.
基金support of the National Natural Science Foundation of China (Grant No. 41130751)China Scholarship Council, Research Program for Western China Communication (Grant No. 2011ZB04)China Central University Funding
文摘Limit equilibrium method （LEM） and strength reduction method （SRM） are the most widely used methods for slope stability analysis. However, it can be noted that they both have some limitations in practical application. In the LEM, the constitutive model cannot be considered and many assumptions are needed between slices of soil/rock. The SRM requires iterative calculations and does not give the slip surface directly. A method for slope stability analysis based on the graph theory is recently developed to directly calculate the minimum safety factor and potential critical slip surface according to the stress results of numerical simulation. The method is based on current stress state and can overcome the disadvantages mentioned above in the two traditional methods. The influences of edge generation and mesh geometry on the position of slip surface and the safety factor of slope are studied, in which a new method for edge generation is proposed, and reasonable mesh size is suggested. The results of benchmark examples and a rock slope show good accuracy and efficiency of the presented method.
基金the National Key Research and Development Program of China(No.2018YFB1305005)。
文摘As autonomous driving systems advance rapidly,there is a surge in demand for high-definition(HD)maps that provide accurate and dependable prior information on static environments around vehicles.As one of the main high-level elements in HD maps,the road lane centerline is essential for downstream tasks such as autonomous navigation and planning.Considering the complex topology and significant overlap concerns of road centerlines,previous studies have rarely examined the centerline HD map mapping problem.Recent learningbased pipelines take heuristic post-processing predictions to generate a structured centerline output without instance information.To ameliorate this situation,we propose a novel,end-to-end road centerlines vectorized graph generation pipeline,termed CenterLineFormer.CenterLineFormer takes a single onboard camera image as input and predicts a directed graph representing the lane-layer map in the bird’s-eye view(BEV).We propose a strategy for better view transformation that uses a cross-attention mechanism to generate a dense BEV feature map.With our pipeline,we can describe the connection relationship between different centerlines and generate structured lane graphs for downstream modules as planning and control.Qualitatively,our experiments emphasize that our pipeline achieves a superior performance against previous baselines on nuScenes dataset.We also show that CenterLineFormer can generate accurate centerline graph topologies on night driving and complex traffic intersection scenes.
基金This work was supported by the National Natural Science Foundation of China(Nos.62173045 and 61673192)the Fundamental Research Funds for the Central Universities(No.2020XD-A04-2)the BUPT Excellent PhD Students Foundation(No.CX2021222).
文摘Scene graphs of point clouds help to understand object-level relationships in the 3D space.Most graph generation methods work on 2D structured data,which cannot be used for the 3D unstructured point cloud data.Existing point-cloud-based methods generate the scene graph with an additional graph structure that needs labor-intensive manual annotation.To address these problems,we explore a method to convert the point clouds into structured data and generate graphs without given structures.Specifically,we cluster points with similar augmented features into groups and establish their relationships,resulting in an initial structural representation of the point cloud.Besides,we propose a Dynamic Graph Generation Network(DGGN)to judge the semantic labels of targets of different granularity.It dynamically splits and merges point groups,resulting in a scene graph with high precision.Experiments show that our methods outperform other baseline methods.They output reliable graphs describing the object-level relationships without additional manual labeled data.
文摘Predicting molecular properties is essential for advancing for advancing drug discovery and design. Recently, Graph Neural Networks (GNNs) have gained prominence due to their ability to capture the complex structural and relational information inherent in molecular graphs. Despite their effectiveness, the “black-box” nature of GNNs remains a significant obstacle to their widespread adoption in chemistry, as it hinders interpretability and trust. In this context, several explanation methods based on factual reasoning have emerged. These methods aim to interpret the predictions made by GNNs by analyzing the key features contributing to the prediction. However, these approaches fail to answer critical questions: “How to ensure that the structure-property mapping learned by GNNs is consistent with established domain knowledge”. In this paper, we propose MMGCF, a novel counterfactual explanation framework designed specifically for the prediction of GNN-based molecular properties. MMGCF constructs a hierarchical tree structure on molecular motifs, enabling the systematic generation of counterfactuals through motif perturbations. This framework identifies causally significant motifs and elucidates their impact on model predictions, offering insights into the relationship between structural modifications and predicted properties. Our method demonstrates its effectiveness through comprehensive quantitative and qualitative evaluations of four real-world molecular datasets.
基金supported by the National Natural Science Foundation of China(No.62072232)the Fundamental Research Funds for the Central Universities(No.021714380026)the Collaborative Innovation Center of Novel Software Technology and Industrialization.
文摘Social relationships,such as parent-offspring and friends,are crucial and stable connections between individuals,especially at the person level,and are essential for accurately describing the semantics of videos.In this paper,we analogize such a task to scene graph generation,which we call video social relationship graph generation(VSRGG).It involves generating a social relationship graph for each video based on person-level relationships.We propose a context-aware graph neural network(CAGNet)for VSRGG,which effectively generates social relationship graphs through message passing,capturing the context of the video.Specifically,CAGNet detects persons in the video,generates an initial graph via relationship proposal,and extracts facial and body features to describe the detected individuals,as well as temporal features to describe their interactions.Then,CAGNet predicts pairwise relationships between individuals using graph message passing.Additionally,we construct a new dataset,VidSoR,to evaluate VSRGG,which contains 72 h of video with 6276 person instances and 5313 relationship instances of eight relationship types.Extensive experiments show that CAGNet can make accurate predictions with a comparatively high mean recall(mRecall)when using only visual features.
文摘It is a common practice to simulate some historical or test systems to validate the efficiency of new methods or concepts. However, there are only a small number of existing power system test cases, and validation and evaluation results, obtained using such a limited number of test cases, may not be deemed sufficient or convincing. In order to provide more available test cases, a new random graph generation algorithm, named ‘‘dualstage constructed random graph’’ algorithm, is proposed to effectively model the power grid topology. The algorithm generates a spanning tree to guarantee the connectivity of random graphs and is capable of controlling the number of lines precisely. No matter how much the average degree is,whether sparse or not, random graphs can be quickly formed to satisfy the requirements. An approach is developed to generate random graphs with prescribed numbers of connected components, in order to simulate the power grid topology under fault conditions. Our experimental study on several realistic power grid topologies proves that the proposed algorithm can quickly generate a large number of random graphs with the topology characteristics of real-world power grid.
基金supported by the National Natural Science Foundation of China(NSFC)(No.62072190)TCL Science and Technology Innovation Fund,China.
文摘We study the task of automated house design,which aims to automatically generate 3D houses from user requirements.However,in the automatic system,it is non-trivial due to the intrinsic complexity of house designing:1)the understanding of user requirements,where the users can hardly provide high-quality requirements without any professional knowledge;2)the design of house plan,which mainly focuses on how to capture the effective information from user requirements.To address the above issues,we propose an automatic house design framework,called auto-3D-house design(A3HD).Unlike the previous works that consider the user requirements in an unstructured way(e.g.,natural language),we carefully design a structured list that divides the requirements into three parts(i.e.,layout,outline,and style),which focus on the attributes of rooms,the outline of the building,and the style of decoration,respectively.Following the processing of architects,we construct a bubble diagram(i.e.,graph)that covers the rooms′attributes and relations under the constraint of outline.In addition,we take each outline as a combination of points and orders,ensuring that it can represent the outlines with arbitrary shapes.Then,we propose a graph feature generation module(GFGM)to capture layout features from the bubble diagrams and an outline feature generation module(OFGM)for outline features.Finally,we render 3D houses according to the given style requirements in a rule-based method.Experiments on two benchmark datasets(i.e.,RPLAN and T3HM)demonstrate the effectiveness of our A3HD in terms of both quantitative and qualitative evaluation metrics.
基金National Natural Science Foundation of China(Grant No.U20B2069)Fundamental Research Funds for the Central Universities.
文摘Learning activities interactions between small groups is a key step in understanding team sports videos.Recent research focusing on team sports videos can be strictly regarded from the perspective of the audience rather than the athlete.For team sports videos such as volleyball and basketball videos,there are plenty of intra-team and inter-team relations.In this paper,a new task named Group Scene Graph Generation is introduced to better understand intra-team relations and inter-team relations in sports videos.To tackle this problem,a novel Hierarchical Relation Network is proposed.After all players in a video are finely divided into two teams,the feature of the two teams’activities and interactions will be enhanced by Graph Convolutional Networks,which are finally recognized to generate Group Scene Graph.For evaluation,built on Volleyball dataset with additional 9660 team activity labels,a Volleyball+dataset is proposed.A baseline is set for better comparison and our experimental results demonstrate the effectiveness of our method.Moreover,the idea of our method can be directly utilized in another video-based task,Group Activity Recognition.Experiments show the priority of our method and display the link between the two tasks.Finally,from the athlete’s view,we elaborately present an interpretation that shows how to utilize Group Scene Graph to analyze teams’activities and provide professional gaming suggestions.
