Linked e-resources
Details
Table of Contents
Intro; Preface; Acknowledgments; Contents; Acronyms; 1 A Gentle Introduction to Spatiotemporal Data Mining; 1.1 Types of Spatiotemporal Knowledge; 1.2 Motivation and Challenges; 1.2.1 Solar Physics; 1.2.2 Biomedical Sciences; 1.2.3 Epidemiology; 1.3 Challenges; 2 Modeling Spatiotemporal Trajectories; 2.1 Basic Spatiotemporal Data Types; 2.2 Moving Objects; 2.3 Evolving Region Trajectories; 2.3.1 Modeling Spatiotemporal Event Instances and Examples; 3 Modeling Spatiotemporal Relationships Among Trajectories; 3.1 Generic Spatial and Temporal Relationships; 3.1.1 Temporal Relationships
3.1.2 Spatial Relationships3.1.3 Spatial Co-locations; 3.2 Spatiotemporal Relationships; 3.2.1 Spatiotemporal Co-occurrence; 3.2.2 Spatiotemporal Sequences; 4 Significance Measurements for Spatiotemporal Co-occurrences; 4.1 The Family of Jaccard Measures; 4.1.1 J Measure; 4.1.2 J+ Measure; 4.1.3 J* Measure; 4.1.3.1 Key Properties of J*; 4.1.3.2 Antimonotonic Property; 4.1.3.3 Containment Property; 4.1.4 Algorithms for Calculating Jaccard-Derived Measures; 4.1.4.1 Calculating J; 4.1.4.2 Calculating J+; 4.1.4.3 Calculating J*; 4.2 Overlap Measures; 4.2.1 Key Properties of Overlap Measures
4.2.1.1 Antimonotonic Property4.2.1.2 Containment Property; 4.2.2 OMIN and OMAX Calculation Algorithms; 4.3 Cosine Measure; 4.3.1 Key Properties of Cosine Measure; 4.3.1.1 Antimonotonic Property; 4.3.1.2 Containment Property; 4.3.2 Algorithm for Calculating Cosine Measure; 4.4 Summary; 5 Spatiotemporal Co-occurrence Pattern (STCOP) Mining; 5.1 Preliminaries of STCOP Mining; 5.2 Significance and Prevalence Measurements; 5.3 STCOP Mining from Evolving Region Trajectories; 5.4 Efficient Spatiotemporal Joins for STCOP Mining; 5.4.1 Grid-Mapped Interval Trees (GITs)
5.4.2 Chebyshev Polynomial Indexing5.5 Summary; 6 Spatiotemporal Event Sequence (STES) Mining; 6.1 Modeling Spatiotemporal Event Sequences; 6.1.1 Head and Tail Window of an Instance; 6.1.2 Generating Head and Tail Windows; 6.1.3 Strategies for Head and Tail Window Generation; 6.1.3.1 Selection of the Segment: Interval-Based vs. Ratio-Based Generation; 6.1.3.2 Coverage Strategies: Partial, Full and Overfull; 6.1.3.3 Overlapping vs. Disjoint Coverage Strategies; 6.1.3.4 Temporal Propagation Strategies; 6.2 Spatiotemporal Follow Relationship and Measuring the Significance
6.2.1 Significance of Instance Sequences6.2.1.1 Temporal Algebra vs. Head and Tail Windows; 6.2.2 Prevalence of the Event Sequences; 6.3 Apriori-Based Algorithms for Mining Spatiotemporal Event Sequences; 6.3.1 Initialization; 6.3.2 SequenceConnect Algorithm; 6.3.3 Avoiding Spatiotemporal Joins; 6.4 A Pattern Growth-Based Approach for Mining Spatiotemporal Event Sequences; 6.4.1 Event Sequences and Graph Representation; 6.4.1.1 Graph Transformation; 6.4.2 EsGrowth Algorithm; 6.5 Mining the Most Prevalent Spatiotemporal Event Sequences: Top-(R%, K) Approach; 6.6 Summary; References; Index
3.1.2 Spatial Relationships3.1.3 Spatial Co-locations; 3.2 Spatiotemporal Relationships; 3.2.1 Spatiotemporal Co-occurrence; 3.2.2 Spatiotemporal Sequences; 4 Significance Measurements for Spatiotemporal Co-occurrences; 4.1 The Family of Jaccard Measures; 4.1.1 J Measure; 4.1.2 J+ Measure; 4.1.3 J* Measure; 4.1.3.1 Key Properties of J*; 4.1.3.2 Antimonotonic Property; 4.1.3.3 Containment Property; 4.1.4 Algorithms for Calculating Jaccard-Derived Measures; 4.1.4.1 Calculating J; 4.1.4.2 Calculating J+; 4.1.4.3 Calculating J*; 4.2 Overlap Measures; 4.2.1 Key Properties of Overlap Measures
4.2.1.1 Antimonotonic Property4.2.1.2 Containment Property; 4.2.2 OMIN and OMAX Calculation Algorithms; 4.3 Cosine Measure; 4.3.1 Key Properties of Cosine Measure; 4.3.1.1 Antimonotonic Property; 4.3.1.2 Containment Property; 4.3.2 Algorithm for Calculating Cosine Measure; 4.4 Summary; 5 Spatiotemporal Co-occurrence Pattern (STCOP) Mining; 5.1 Preliminaries of STCOP Mining; 5.2 Significance and Prevalence Measurements; 5.3 STCOP Mining from Evolving Region Trajectories; 5.4 Efficient Spatiotemporal Joins for STCOP Mining; 5.4.1 Grid-Mapped Interval Trees (GITs)
5.4.2 Chebyshev Polynomial Indexing5.5 Summary; 6 Spatiotemporal Event Sequence (STES) Mining; 6.1 Modeling Spatiotemporal Event Sequences; 6.1.1 Head and Tail Window of an Instance; 6.1.2 Generating Head and Tail Windows; 6.1.3 Strategies for Head and Tail Window Generation; 6.1.3.1 Selection of the Segment: Interval-Based vs. Ratio-Based Generation; 6.1.3.2 Coverage Strategies: Partial, Full and Overfull; 6.1.3.3 Overlapping vs. Disjoint Coverage Strategies; 6.1.3.4 Temporal Propagation Strategies; 6.2 Spatiotemporal Follow Relationship and Measuring the Significance
6.2.1 Significance of Instance Sequences6.2.1.1 Temporal Algebra vs. Head and Tail Windows; 6.2.2 Prevalence of the Event Sequences; 6.3 Apriori-Based Algorithms for Mining Spatiotemporal Event Sequences; 6.3.1 Initialization; 6.3.2 SequenceConnect Algorithm; 6.3.3 Avoiding Spatiotemporal Joins; 6.4 A Pattern Growth-Based Approach for Mining Spatiotemporal Event Sequences; 6.4.1 Event Sequences and Graph Representation; 6.4.1.1 Graph Transformation; 6.4.2 EsGrowth Algorithm; 6.5 Mining the Most Prevalent Spatiotemporal Event Sequences: Top-(R%, K) Approach; 6.6 Summary; References; Index