Muutke küpsiste eelistusi

Mobile Big Data 2018 ed. [Kõva köide]

, , ,
  • Formaat: Hardback, 125 pages, kõrgus x laius: 235x155 mm, kaal: 454 g, 36 Illustrations, color; 1 Illustrations, black and white; XII, 125 p. 37 illus., 36 illus. in color., 1 Hardback
  • Sari: Wireless Networks
  • Ilmumisaeg: 31-Aug-2018
  • Kirjastus: Springer International Publishing AG
  • ISBN-10: 3319961152
  • ISBN-13: 9783319961156
Teised raamatud teemal:
  • Kõva köide
  • Hind: 104,29 €*
  • * hind on lõplik, st. muud allahindlused enam ei rakendu
  • Tavahind: 122,69 €
  • Säästad 15%
  • Raamatu kohalejõudmiseks kirjastusest kulub orienteeruvalt 2-4 nädalat
  • Kogus:
  • Lisa ostukorvi
  • Tasuta tarne
  • Tellimisaeg 2-4 nädalat
  • Lisa soovinimekirja
Mobile Big Data 2018 ed.Suurem pilt
  • Formaat: Hardback, 125 pages, kõrgus x laius: 235x155 mm, kaal: 454 g, 36 Illustrations, color; 1 Illustrations, black and white; XII, 125 p. 37 illus., 36 illus. in color., 1 Hardback
  • Sari: Wireless Networks
  • Ilmumisaeg: 31-Aug-2018
  • Kirjastus: Springer International Publishing AG
  • ISBN-10: 3319961152
  • ISBN-13: 9783319961156
Teised raamatud teemal:
Püsilink: https://www.kriso.ee/db/9783319961156.html

This book  provides a comprehensive picture of mobile big data starting from data sources to mobile data driven applications. Mobile Big Data comprises two main components: an overview of mobile big data, and the case studies based on real-world data recently collected by one of the largest mobile network carriers in China.

 In the first component, four areas of mobile big data life cycle are surveyed: data source and collection, transmission, computing platform and applications. In the second component, two case studies are provided, based on the signaling data collected in the cellular core network in terms of subscriber privacy evaluation and demand forecasting for network management. These cases respectively give a vivid demonstration of what  mobile big data looks like, and how it can be analyzed and mined to generate useful and meaningful information and knowledge.

 This book targets researchers, practitioners and professors relevant to this field.  Advanced-level students studying computer science and electrical engineering will also be interested in this book as supplemental reading. 


Arvustused

The study shows that the rich set of smartphone sensors currently available enables user identification across datasets collected from different mobile networks. This text is best suited to graduate-level computer science and engineering students, and to professionals. Summing Up: Recommended. Graduate students, faculty, and professionals. (C. Tappert, Choice, Vol. 46 (9), May, 2019)

1 Mobile Big Data 1(12)
1.1 Overview of Mobile Big data
1(1)
1.2 Characteristics
2(7)
1.2.1 "5V" Features
2(1)
1.2.2 Multi-Dimensional
3(3)
1.2.3 Real-Time
6(1)
1.2.4 Privacy Sensitive
6(3)
1.3 Organization of the Monograph
9(1)
References
9(4)
2 Source and Collection 13(14)
2.1 Overview of Data Sources
13(4)
2.1.1 The App-Level Data
15(1)
2.1.2 The Network-Level Data
15(2)
2.2 Data Collection in Mobile Networks
17(7)
2.2.1 Network Architecture Overview
17(1)
2.2.2 Key Network Components
18(3)
2.2.3 Mobility Management and User Network Behaviors
21(1)
2.2.4 Data Collection and Categorization
22(2)
References
24(3)
3 Transmission 27(8)
3.1 Computing Infrastructure
27(2)
3.1.1 Mobile Cloud Computing
27(1)
3.1.2 Fog/Edge Computing
28(1)
3.2 Communication and Networking Infrastructure
29(3)
3.2.1 Software Defined Networking (SDN)
29(1)
3.2.2 Cloud Radio Access Networks (C-RAN)
30(2)
References
32(3)
4 Computing 35(16)
4.1 Hardware
36(3)
4.1.1 Heterogeneous Computing
36(1)
4.1.2 Computing Systems
37(2)
4.2 Software
39(7)
4.2.1 Key Properties and Architecture
39(2)
4.2.2 Batch Computing Systems
41(2)
4.2.3 Stream Computing Systems
43(1)
4.2.4 Data Mining Systems
44(2)
References
46(5)
5 Applications 51(20)
5.1 Overview
51(7)
5.1.1 Mobility
51(5)
5.1.2 Pervasive Health Computing
56(1)
5.1.3 Public Services
57(1)
5.1.4 Network Planning and Management
58(1)
5.2 Methodology
58(4)
5.2.1 Representation
59(1)
5.2.2 Models
59(2)
5.2.3 Knowledge Discovery
61(1)
5.3 User Modeling
62(4)
5.3.1 With Data from OTT Servers
62(2)
5.3.2 With Data from Mobile Devices
64(1)
5.3.3 With Data from Network Operators
65(1)
References
66(5)
6 Case Study: Demand Forecasting for Predictive Network Managements 71(26)
6.1 Background
71(3)
6.1.1 Data-Driven Predictive Network Management
71(1)
6.1.2 Objective and Approaches
72(2)
6.2 Per-Cell Demand Time Series
74(6)
6.2.1 Signaling Dataset
74(1)
6.2.2 Per-Cell Demand Time Series
74(3)
6.2.3 Analysis of Per-Cell Demand Time Series
77(3)
6.3 Demand Prediction Problem Formulation
80(2)
6.3.1 Graph-Based Spatial Relevancy Formulation
80(1)
6.3.2 Periodicity-Based Temporal Features
81(1)
6.3.3 Graph-Sequence Demand Prediction Formulation
81(1)
6.4 Deep Graph-Sequence Spatiotemporal Modeling
82(7)
6.4.1 Spatial Modeling: Graph Convolutional Networks
82(3)
6.4.2 Temporal Modeling: Gated Recurrent Unit (GRU) Networks
85(2)
6.4.3 Spatiotemporal Modeling: Graph Convolutional GRU (GCGRU)
87(2)
6.5 Experiments
89(3)
6.6 Discussions and Summary
92(1)
References
93(4)
7 Case Study: User Identification for Mobile Privacy 97
7.1 Background
97(2)
7.1.1 Privacy Attack: User Identification
97(1)
7.1.2 Approach: Multi-Feature Ensemble Matching Framework
98(1)
7.2 Problem Description
99(4)
7.2.1 Assumptions
99(1)
7.2.2 Formulation: k-Cardinality Bipartite Matching
100(2)
7.2.3 Key Challenges
102(1)
7.3 Representations and Distance Measures
103(13)
7.3.1 Location Visiting Frequency Modeling
103(5)
7.3.2 Location Visiting Frequency and Dwelling Time Modeling
108(6)
7.3.3 Geospatial Habitat Region Modeling
114(2)
7.4 Ensemble Matching
116(3)
7.5 Experiments
119(5)
7.5.1 Signaling Dataset
119(1)
7.5.2 Distance Measures
120(2)
7.5.3 User Identification Performance
122(2)
7.6 Discussions and Summary
124(1)
References
125