Linked e-resources
Details
Table of Contents
Intro; Preface; Contents; Acronyms; 1 Mobile Big Data; 1.1 Overview of Mobile Big data; 1.2 Characteristics; 1.2.1 ``5V'' Features; 1.2.2 Multi-Dimensional; Spatiotemporal; Multi-Sensory; 1.2.3 Real-Time; 1.2.4 Privacy Sensitive; Summary; 1.3 Organization of the Monograph; References; 2 Source and Collection; 2.1 Overview of Data Sources; 2.1.1 The App-Level Data; 2.1.2 The Network-Level Data; 2.2 Data Collection in Mobile Networks; 2.2.1 Network Architecture Overview; 2.2.2 Key Network Components; 2.2.3 Mobility Management and User Network Behaviors; 2.2.4 Data Collection and Categorization
Pregel and Its DerivativeGraphLab; References; 5 Applications; 5.1 Overview; 5.1.1 Mobility; Fundamental Analysis on Human Mobility; Location Prediction Over Different Time Scales; Correlation Analysis Between Social Tie and Human Mobility; Context-Aware Sensing and Recommendation; 5.1.2 Pervasive Health Computing; 5.1.3 Public Services; 5.1.4 Network Planning and Management; 5.2 Methodology; 5.2.1 Representation; 5.2.2 Models; Descriptive Methods (Unsupervised); Predictive Methods (Supervised); 5.2.3 Knowledge Discovery; 5.3 User Modeling; 5.3.1 With Data from OTT Servers
5.3.2 With Data from Mobile Devices5.3.3 With Data from Network Operators; References; 6 Case Study: Demand Forecasting for Predictive Network Managements; 6.1 Background; 6.1.1 Data-Driven Predictive Network Management; 6.1.2 Objective and Approaches; 6.2 Per-Cell Demand Time Series; 6.2.1 Signaling Dataset; 6.2.2 Per-Cell Demand Time Series; 6.2.3 Analysis of Per-Cell Demand Time Series; Per-cell Demands Autocorrelation Analysis; Spatiotemporal Analysis; 6.3 Demand Prediction Problem Formulation; 6.3.1 Graph-Based Spatial Relevancy Formulation; 6.3.2 Periodicity-Based Temporal Features
6.3.3 Graph-Sequence Demand Prediction Formulation6.4 Deep Graph-Sequence Spatiotemporal Modeling; 6.4.1 Spatial Modeling: Graph Convolutional Networks; Graph Filters and Graph Convolutions; Graph Convolutional Networks; 6.4.2 Temporal Modeling: Gated Recurrent Unit (GRU) Networks; 6.4.3 Spatiotemporal Modeling: Graph Convolutional GRU (GCGRU); 6.5 Experiments; 6.6 Discussions and Summary; References; 7 Case Study: User Identification for Mobile Privacy; 7.1 Background; 7.1.1 Privacy Attack: User Identification; 7.1.2 Approach: Multi-Feature Ensemble Matching Framework
Pregel and Its DerivativeGraphLab; References; 5 Applications; 5.1 Overview; 5.1.1 Mobility; Fundamental Analysis on Human Mobility; Location Prediction Over Different Time Scales; Correlation Analysis Between Social Tie and Human Mobility; Context-Aware Sensing and Recommendation; 5.1.2 Pervasive Health Computing; 5.1.3 Public Services; 5.1.4 Network Planning and Management; 5.2 Methodology; 5.2.1 Representation; 5.2.2 Models; Descriptive Methods (Unsupervised); Predictive Methods (Supervised); 5.2.3 Knowledge Discovery; 5.3 User Modeling; 5.3.1 With Data from OTT Servers
5.3.2 With Data from Mobile Devices5.3.3 With Data from Network Operators; References; 6 Case Study: Demand Forecasting for Predictive Network Managements; 6.1 Background; 6.1.1 Data-Driven Predictive Network Management; 6.1.2 Objective and Approaches; 6.2 Per-Cell Demand Time Series; 6.2.1 Signaling Dataset; 6.2.2 Per-Cell Demand Time Series; 6.2.3 Analysis of Per-Cell Demand Time Series; Per-cell Demands Autocorrelation Analysis; Spatiotemporal Analysis; 6.3 Demand Prediction Problem Formulation; 6.3.1 Graph-Based Spatial Relevancy Formulation; 6.3.2 Periodicity-Based Temporal Features
6.3.3 Graph-Sequence Demand Prediction Formulation6.4 Deep Graph-Sequence Spatiotemporal Modeling; 6.4.1 Spatial Modeling: Graph Convolutional Networks; Graph Filters and Graph Convolutions; Graph Convolutional Networks; 6.4.2 Temporal Modeling: Gated Recurrent Unit (GRU) Networks; 6.4.3 Spatiotemporal Modeling: Graph Convolutional GRU (GCGRU); 6.5 Experiments; 6.6 Discussions and Summary; References; 7 Case Study: User Identification for Mobile Privacy; 7.1 Background; 7.1.1 Privacy Attack: User Identification; 7.1.2 Approach: Multi-Feature Ensemble Matching Framework