10907nam 22005293 450 99659416800331620240503084511.0981-9729-66-1(CKB)31801385000041(MiAaPQ)EBC31311076(Au-PeEL)EBL31311076(MiAaPQ)EBC31319823(Au-PeEL)EBL31319823(EXLCZ)993180138500004120240503d2024 uy 0engur|||||||||||txtrdacontentcrdamediacrrdacarrierSpatial Data and Intelligence 5th China Conference, SpatialDI 2024, Nanjing, China, April 25-27, 2024, Proceedings1st ed.Singapore :Springer Singapore Pte. Limited,2024.©2024.1 online resource (364 pages)Lecture Notes in Computer Science Series ;v.14619981-9729-65-3 Intro -- Preface -- Organization -- Contents -- Spatiotemporal Data Analysis -- Multi-view Contrastive Clustering with Clustering Guidance and Adaptive Auto-encoders -- 1 Introduction -- 2 Related Work -- 2.1 Multi-view Clustering -- 2.2 Contrastive Learning -- 3 The Framework of MAAC Network -- 3.1 Adaptive Graph Auto-encoder -- 3.2 Contrastive Fusion -- 3.3 Graph Clustering -- 3.4 Clustering Guidance Strategy -- 4 Experiments -- 4.1 Datasets and Evaluation Measure -- 4.2 Implementation Details -- 4.3 Baselines -- 4.4 Results -- 4.5 Ablation Experiment -- 4.6 Cluster Visualization -- 5 Conclusion -- References -- Cloud-Edge Collaborative Continual Adaptation for ITS Object Detection -- 1 Introduction -- 2 Related Works -- 3 Preliminaries -- 3.1 Definition -- 3.2 Problem Statement -- 4 The Framework for Continual Adaptation in Traffic Object Detection Based on Cloud-Edge Collaboration -- 4.1 Cloud Component: Dynamic Domain Adaptation -- 4.2 Edge Component: Efficient Model Synchronization -- 5 Experiments -- 5.1 Datasets -- 5.2 Experimental Settings -- 5.3 Methods for Comparison -- 5.4 Experimental Results -- 6 Conclusion -- References -- Understanding Spatial Dependency Among Spatial Interactions -- 1 Introduction -- 2 Methodological Framework -- 2.1 Spatial Dependency Metrics for Spatial Interactions -- 2.2 Factors Influencing Second-Order Spatial Autocorrelation -- 2.3 Spatial Econometric Interaction Modeling -- 3 Experiments and Results -- 3.1 Research Area and Data -- 3.2 Measuring Spatial Dependency Among Spatial Interactions -- 3.3 Exploring Factors Influencing Second-Order Spatial Autocorrelation -- 3.4 Modeling Spatial Interactions Incorporating Spatial Dependency -- 4 Conclusions -- References -- An Improved DBSCAN Clustering Method for AIS Trajectories Incorporating DP Compression and Discrete Fréchet Distance -- 1 Introduction.2 Related Works -- 3 Methodology -- 3.1 Framework of the Research -- 3.2 Trajectory Data Pre-processing -- 3.3 Computation of Distance Matrix -- 3.4 Unsupervised KNN + Kneed -- 4 Experiments -- 4.1 Dataset and Experimental Environment -- 4.2 Data Pre-processing -- 4.3 Comparison of Similarity Measures -- 4.4 Description of Clusters -- 5 Conclusions -- References -- Structure and Semantic Contrastive Learning for Nodes Clustering in Heterogeneous Information Networks -- 1 Introduction -- 2 Related Work -- 3 The Proposed Method -- 3.1 Adjacency Matrix Reconstruction -- 3.2 Cleaning Feature -- 3.3 Contrastive Learning -- 3.4 Objective Function -- 4 Experiments -- 4.1 Datasets and Baselines -- 4.2 Comparison Methods -- 4.3 Ablation Experiments -- 4.4 Parameter Analysis -- 5 Conclusion -- References -- An Accuracy Evaluation Method for Multi-source Data Based on Hexagonal Global Discrete Grids -- 1 Introductory -- 2 Multi-source Data Grids -- 2.1 Selection of Grid Levels -- 2.2 Gridded Representation of Vector Data -- 2.3 Gridded Representation of Remotely Sensed Data -- 3 Accuracy Evaluation System for Gridded Data -- 3.1 Accuracy Evaluation Index System for Vector Data Gridding -- 3.2 Accuracy Evaluation Index System of Remote Sensing Data Gridding -- 4 Experimental Results and Analysis -- 4.1 Conversion Results and Uncertainty Assessment of Remotely Sensed Data -- 4.2 Transformation and Uncertainty Assessment of Vector Data -- 5 Summarize -- References -- Applying Segment Anything Model to Ground-Based Video Surveillance for Identifying Aquatic Plant -- 1 Introduction -- 2 Methodology -- 2.1 Overview -- 2.2 Detection and Segmentation -- 2.3 Area Estimation -- 3 Study Area and Data -- 4 Experiment -- 4.1 Computational Environment -- 4.2 Detection and Segmentation -- 4.3 Area Estimation -- 5 Conclusion -- References -- Spatiotemporal Data Mining.Mining Regional High Utility Co-location Pattern -- 1 Introduction -- 2 Related Work -- 3 Related Concepts and Problem Statement -- 4 Algorithm -- 5 Experiments -- 5.1 Analysis of Mining Results -- 5.2 Efficiency Analysis -- 6 Conclusion -- References -- Local Co-location Pattern Mining Based on Regional Embedding -- 1 Introduction -- 2 Related Works -- 3 Basic Concepts -- 4 Mining Framework -- 4.1 Regional Embedding -- 4.2 Region Functional Annotation -- 4.3 Mining Semantic LCPs -- 4.4 Algorithm Analysis -- 5 Experimental Evaluation -- 5.1 Description of Datasets -- 5.2 Region Partitioning and Function Annotation Based on Regional Embedding -- 5.3 Case Study of Semantic LCP Mining -- 6 Conclusion -- References -- RCPMRLM: A Regional Co-location Pattern Mining Method Based on Representation Learning Model -- 1 Introduction -- 2 Related Concepts -- 2.1 Regional Co-location Patterns Mining -- 2.2 Word Embeddings Representation Model -- 2.3 Similarity Measurement -- 2.4 Clustering Method -- 3 Study Area and Data -- 4 Regional Co-location Pattern Mining Method Based on Representation Learning Model (RCPMRLM) -- 5 Algorithm Complexity Analysis -- 6 Results -- 6.1 Clustering Results -- 6.2 RCPMRLM Mining Results -- 7 Summary -- References -- Construction of a Large-Scale Maritime Elements Semantic Schema Based on Heterogeneous Graph Models -- 1 Introduction -- 2 Related Work -- 2.1 Overview of Related Work on Knowledge Graphs -- 2.2 Overview of Related Work on Ship Behavior Mining -- 3 Technical Framework and Dataset -- 3.1 Technical Framework -- 3.2 Dataset -- 3.3 Introduction to Application Scenarios of the Framework -- 4 Experimental Results and Analysis -- 4.1 Ship Type Prediction -- 4.2 Similar Berth Recommendation -- 5 Conclusion and Future Work -- References.OCGATL: One-Class Graph Attention Networks with Transformation Learning for Anomaly Detection for Argo Data -- 1 Introduction -- 2 Related Work -- 2.1 Graph Anomaly Detection -- 2.2 One-Class Classification -- 2.3 Contrastive Learning -- 3 Preliminaries -- 4 Methodology -- 4.1 Graph Construction -- 4.2 OCGATL Model -- 5 Experiments -- 5.1 Simulation -- 5.2 Argo Real Data Experiment -- 6 Conclusion -- References -- RGCNdist2vec: Using Graph Convolutional Networks and Distance2Vector to Estimate Shortest Path Distance Along Road Networks -- 1 Introduction -- 2 Related Work -- 2.1 Shortest Path Distance Calculation -- 2.2 Graph Neural Network -- 3 Definitions and Solutions -- 3.1 Definition -- 3.2 Solution -- 4 Road Network Shortest Path Estimation Method -- 4.1 RGCNdist2vec -- 4.2 RGCNdist2vec-Encoder -- 4.3 RGCNdist2vec-Decoder -- 5 Sampling Method -- 5.1 Subgraph Sampling Method -- 5.2 Sampling Method Between Subgraphs -- 5.3 Whole Graph Sampling Method -- 6 Experiment -- 6.1 Experimental Introduction -- 6.2 Ablation Experiment -- 6.3 Effect Experiment -- 6.4 Efficiency Experiment -- 7 Conclusion -- References -- Self-supervised Graph Neural Network Based Community Search over Heterogeneous Information Networks -- 1 Introduction -- 2 Related Work -- 3 Community Search Model and Algorithm over HIN -- 3.1 Node Attribute Score Calculation -- 3.2 Community Search -- 4 Experiments -- 4.1 Experiment Settings -- 4.2 Effectiveness Evaluation -- 4.3 Ablation Study -- 4.4 Community Sensitivity Analysis -- 5 Conclusion -- References -- Measurement and Research on the Conflict Between Residential Space and Tourism Space in Pianyan Ancient Township -- 1 Introduction -- 2 Overview of the Study Area and Data Sources -- 2.1 Overview of the Study Area -- 2.2 Data Sources -- 3 Multi-intelligence Body Simulation -- 3.1 Environmental Information Module.3.2 Implementation Module -- 3.3 Information Storage Module -- 3.4 Module for Analyzing Simulation Results -- 4 System Implementation and Simulation Experiments -- 4.1 Spatial Form of the Ancient Town of Pianyan -- 4.2 Spatial Conflict Identification -- 4.3 Optimization Strategies -- 5 Conclusion -- References -- Spatiotemporal Data Prediction -- Spatio-Temporal Sequence Prediction of Diversion Tunnel Based on Machine Learning Multivariate Data Fusion -- 1 Introduction -- 2 Methodology -- 2.1 ARIMA Model -- 2.2 Order of ARIMA Model -- 2.3 The LSSVM Model -- 2.4 The DLSSVM Model -- 2.5 DLSSVM Kernel Function -- 2.6 ARIMA-Bi-DLSSVM Modeling -- 3 Real Experiment for Monitoring Data -- 3.1 Monitoring Data -- 3.2 Data Processing -- 4 Results and Analysis -- 4.1 Prediction Effect of ARIMA-b-DLSSVM -- 4.2 Comparison of Prediction Effect of Several Models -- 5 Conclusion -- References -- DyAdapTransformer: Dynamic Adaptive Spatial-Temporal Graph Transformer for Traffic Prediction -- 1 Introduction -- 2 Related Work -- 2.1 Transformer-Based Traffic Forecasting -- 2.2 Adaptive GNN-Based Traffic Forecasting -- 3 Preliminaries -- 3.1 Definitions -- 3.2 Problem Formulation -- 4 The Proposed Model -- 5 S-TPE: Spatial-Temporal Position Embedding -- 5.1 Temporal Position Embedding (TPE) -- 5.2 Spatial Position Embedding (SPE) Based on Random Walk -- 6 DASCL: Dynamic Adaptive Spatial-Temporal Correlations Learning -- 6.1 Encoder -- 6.2 Decoder -- 7 Experimental Analysis -- 7.1 Datasets -- 7.2 Baseline Methods -- 7.3 Experimental Settings -- 7.4 Experimental Results and Analysis -- 7.5 Interpretability Analysis -- 8 Conclusion -- References -- Predicting Future Spatio-Temporal States Using a Robust Causal Graph Attention Model -- 1 Introduction -- 2 Preliminaries -- 3 Methodology -- 3.1 Forward Propagation of the CGATM -- 3.2 Optimization of the CGATM.4 Experimental Results and Analysis.Lecture Notes in Computer Science SeriesMeng Xiaofeng960613Zhang Xueying1737368Guo Danhuai1737369Hu Di1737370Zheng Bolong1737371Zhang Chunju1737372MiAaPQMiAaPQMiAaPQBOOK996594168003316Spatial Data and Intelligence4159068UNISA