Muutke küpsiste eelistusi

Mobility Patterns, Big Data and Transport Analytics: Tools and Applications for Modeling [Pehme köide]

Edited by , Edited by (Lecturer, Department of Civil and Environmental Engineering, University of Cyprus and Head, Lab. for Transport Engineering, Universit), Edited by (Professor and Chair of Transportation Systems Engineering, Technical University of Munich, Germany)
  • Formaat: Paperback / softback, 452 pages, kõrgus x laius: 229x152 mm, kaal: 680 g
  • Ilmumisaeg: 27-Nov-2018
  • Kirjastus: Elsevier Science Publishing Co Inc
  • ISBN-10: 0128129700
  • ISBN-13: 9780128129708
Teised raamatud teemal:
Mobility Patterns, Big Data and Transport Analytics: Tools and Applications for ModelingSuurem pilt
  • Formaat: Paperback / softback, 452 pages, kõrgus x laius: 229x152 mm, kaal: 680 g
  • Ilmumisaeg: 27-Nov-2018
  • Kirjastus: Elsevier Science Publishing Co Inc
  • ISBN-10: 0128129700
  • ISBN-13: 9780128129708
Teised raamatud teemal:
Püsilink: https://www.kriso.ee/db/9780128129708.html
Märksõnad:

Mobility Patterns, Big Data and Transport Analytics provides a guide to the new analytical framework and its relation to big data, focusing on capturing, predicting, visualizing and controlling mobility patterns - a key aspect of transportation modeling. The book features prominent international experts who provide overviews on new analytical frameworks, applications and concepts in mobility analysis and transportation systems. Users will find a detailed, mobility ‘structural’ analysis and a look at the extensive behavioral characteristics of transport, observability requirements and limitations for realistic transportation applications and transportation systems analysis that are related to complex processes and phenomena.

This book bridges the gap between big data, data science, and transportation systems analysis with a study of big data’s impact on mobility and an introduction to the tools necessary to apply new techniques.

The book covers in detail, mobility ‘structural’ analysis (and its dynamics), the extensive behavioral characteristics of transport, observability requirements and limitations for realistic transportation applications, and transportation systems analysis related to complex processes and phenomena. The book bridges the gap between big data, data science, and Transportation Systems Analysis with a study of big data’s impact on mobility, and an introduction to the tools necessary to apply new techniques.

  • Guides readers through the paradigm-shifting opportunities and challenges of handling Big Data in transportation modeling and analytics
  • Covers current analytical innovations focused on capturing, predicting, visualizing, and controlling mobility patterns, while discussing future trends
  • Delivers an introduction to transportation-related information advances, providing a benchmark reference by world-leading experts in the field
  • Captures and manages mobility patterns, covering multiple purposes and alternative transport modes, in a multi-disciplinary approach
  • Companion website features videos showing the analyses performed, as well as test codes and data-sets, allowing readers to recreate the presented analyses and apply the highlighted techniques to their own data
Contributors xv
About the Editors xvii
1 Big Data and Transport Analytics: An Introduction
Constantinos Antoniou
Loukas Dimitriou
Francisco Camara Pereira
1 Introduction
1(2)
2 Book Structure
3(6)
Special Acknowledgments
4(1)
References
5(1)
Further Reading
5(4)
Part I Methodological
2 Machine Learning Fundamentals
Francisco Camara Pereira
Stanislav S. Borysov
1 Introduction
9(2)
2 A Little Bit of History
11(8)
3 Deep Neural Networks and Optimization
19(4)
4 Bayesian Models
23(1)
5 Basics of Machine Learning Experiments
24(3)
6 Concluding Remarks
27(4)
References
28(1)
Further Reading
29(2)
3 Using Semantic Signatures for Social Sensing in Urban Environments
Krzysztof Janowicz
Grant McKenzie
Yingjie Hu
Rui Zhu
Song Gao
1 Introduction
31(2)
2 Spatial Signatures
33(1)
2.1 Spatial Point Pattern
34(1)
2.2 Spatial Autocorrelations
34(1)
2.3 Spatial Interactions With Other Geographic features
34(3)
2.4 Place-Based Statistics
37(1)
3 Temporal Signatures
37(4)
4 Thematic Signatures
41(4)
5 Examples
45(1)
5.1 Comparing Place Types
45(3)
5.2 Coreference Resolution Across Gazetteers
48(1)
5.3 Ceoprivacy
48(1)
5.4 Temporally Enhanced Geolocation
49(1)
5.5 Regional Variation
50(1)
5.6 Extraction of Urban Functional Regions
50(2)
6 Summary
52(3)
References
53(2)
4 Geographic Space as a Living Structure for Predicting Human Activities Using Big Data
Bin Jiang
Zheng Ren
1 Introduction
55(2)
2 Living Structure and the Topological Representation
57(3)
3 Data and Data Processing
60(3)
4 Prediction of Tweet Locations Through Living Structure
63(1)
4.1 Correlations at the Scale of Thiessen Polygons
63(1)
4.2 Correlations at the Scale of Natural Cities
64(1)
4.3 Degrees of Wholeness or Life or Beauty
65(1)
5 Implications on the Topological Representation and Living Structure
66(4)
6 Conclusion
70(3)
Acknowledgments
70(1)
References
71(2)
5 Data Preparation
Kristian Henrickson
Filipe Rodrigues
Francisco Camara Pereira
1 Introduction
73(1)
2 Tools and Techniques
74(1)
2.1 Scripting and Statistical Analysis Software
74(2)
2.2 Database Management Software
76(3)
2.3 Working With Web Data
79(2)
3 Probe Vehicle Traffic Data
81(1)
3.1 Formats and Protocols
81(2)
3.2 Data Characteristics
83(2)
3.3 Challenges
85(3)
3.4 Data Preparation and Quality Control
88(7)
4 Context Data
95(1)
4.1 The Role of Context Data
95(1)
4.2 Types of Context Data
96(3)
4.3 Formats and Data Collection
99(1)
4.4 Data Cleaning and Preparation
99(8)
References
102(5)
6 Data Science and Data Visualization
Michalis Xyntarakis
Constantinos Antoniou
1 Introduction
107(8)
2 Structured Visualization
115(5)
3 Multidimensional Data Visualization Techniques
120(1)
3.1 Parallel Coordinates
121(2)
3.2 Multidimensional Scaling (MDS)
123(1)
3.3 t-Distributed Stochastic Neighbor Embedding for High-Dimensional Data Sets (t-SNE)
123(1)
4 Case Studies
124(1)
4.1 Experimental Setup
124(1)
4.2 Car Characteristics Data Set
125(3)
4.3 Congestion on 195
128(4)
4.4 Dimensionality Reduction on NYC Taxi Flows
132(8)
4.5 Dimensionality Reduction on the NYC Turnstile Data Set
140(2)
5 Conclusions
142(1)
References
143(2)
Further Reading
144(1)
7 Model-Based Machine Learning for Transportation
Inon Peled
Filipe Rodrigues
Francisco Camara Pereira
1 Introduction
145(1)
1.1 Background Concepts
146(1)
1.2 Notation
147(1)
2 Case Study 1: Taxi Demand in New York City
147(1)
2.1 Initial Probabilistic Model: Linear Regression
147(1)
2.2 Key Components of MBML
148(2)
2.3 Inference
150(2)
2.4 Model Improvements
152(3)
3 Case Study 2: Travel Mode Choices
155(2)
3.1 Improvement: Hierarchical Modeling
157(3)
4 Case Study 3: Freeway Occupancy in San Francisco
160(1)
4.1 Autoregressive Model
160(1)
4.2 State-Space Model
160(1)
4.3 Linear Dynamical Systems
161(1)
4.4 Common Enhancements to LDS
162(2)
4.5 NonLinear Variations on LDS
164(1)
5 Case Study 4: Incident Duration Prediction
165(1)
5.1 Preprocessing
166(1)
5.2 Bag-of-Words Encoding
166(1)
5.3 Latent Dirichlet Allocation
166(3)
6 Summary
169(1)
6.1 Further Reading
169(4)
References
170(3)
8 Textual Data in Transportation Research: Techniques and Opportunities
Aseem Kinra
Samaneh Beheshti Kashi
Francisco Camara Pereira
Francois Combes
Werner Rothengatter
1 Introduction
173(1)
2 Big Textual Data, Text Sources, and Text Mining
174(1)
2.1 Meaning of Text in the Context of Computational Linguistics
174(2)
2.2 Text Mining
176(1)
2.3 Text Mining Process Model
177(2)
2.4 Textual Data Sources in Transportation
179(2)
3 Fundamental Concepts and Techniques in Literature
181(2)
3.1 Topic Modeling
183(2)
3.2 Word2Vec---Text Embeddings With Deep Learning
185(2)
4 Application Examples of Big Textual Data in Transportation
187(1)
4.1 Developing Transportation and Logistics Performance Classifiers Using NLTK and Naive Bayes
187(3)
4.2 Understanding the Public Opinion Toward Driverless Cars With Topic Modeling
190(2)
4.3 Predicting Taxi Demand in Special Events With Text Embeddings and Deep Learning
192(2)
5 Conclusions
194(7)
References
195(2)
Further Reading
197(4)
Part II Applications
9 Statewide Comparison of Origin-Destination Matrices Between California Travel Model and Twitter
Jae Hyun Lee
Adam Davis
Elizabeth McBride
Konstadinos G. Goulias
1 Introduction
201(2)
2 California Statewide Travel Demand Model
203(1)
3 Twitter Data
204(2)
4 Trip Extraction Methods
206(2)
5 Models for Matrix Conversion
208(3)
5.1 Tobit Regression Model
211(1)
5.2 Latent Class Regression Model
212(13)
6 Summary and Conclusion
225(4)
References
226(3)
10 Transit Data Analytics for Planning, Monitoring, Control, and Information
Haris N. Koutsopoulos
Zhenliang Ma
Peyman Noursalehi
Yiwen Zhu
1 Introduction
229(3)
2 Measuring System Performance From the Passenger's Point of View
232(1)
2.1 The Individual Reliability Buffer Time (IRBT)
233(5)
2.2 Denied Boarding
238(5)
3 Decision Support With Predictive Analytics
243(2)
3.1 Framework
245(5)
3.2 Application: Provision of Crowding Predictive Information
250(2)
4 Optimal Design of Transit Demand Management Strategies
252(2)
4.1 Framework and Problem Formulation
254(2)
4.2 Application: Prepeak Discount Design
256(2)
5 Conclusion
258(5)
Acknowledgments
259(1)
References
259(2)
Further Reading
261(2)
11 Data-Driven Traffic Simulation Models: Mobility Patterns Using Machine Learning Techniques
Vasileia Papathanasopoulou
Constantinos Antoniou
Haris N. Koutsopoulos
1 New Modeling Challenges and Data Opportunities
263(1)
1.1 New Modeling Requirements
264(1)
1.2 New Data Sources
264(1)
1.3 Future Challenges
265(1)
2 Background
265(2)
3 Data-Driven Traffic Performance Modeling: Overall Framework
267(1)
3.1 Modeling Approach
267(1)
3.2 Model Components
268(8)
4 Application to Mesoscopic Modeling
276(1)
4.1 Data and Experimental Design
276(1)
4.2 Case Study Setup
276(1)
4.3 Application and Results
277(1)
5 Application to Microscopic Traffic Modeling
277(1)
5.1 Data and Experimental Design
278(1)
5.2 Case Study Setup
279(1)
5.3 Application and Results
279(1)
6 Application to Weak Lane Discipline Modeling
280(1)
6.1 Data and Experimental Design
281(1)
6.2 Case Study Setup
282(2)
6.3 Application and Results
284(3)
7 Network-Wide Application
287(1)
7.1 Implementation Aspects
287(2)
7.2 Case Study Setup
289(1)
7.3 Results
289(1)
8 Conclusions
290(7)
Acknowledgments
291(1)
References
291(6)
12 Big Data and Road Safety: A Comprehensive Review
Katerina Stylianou
Loukas Dimitriou
Mohamed Abdel-Aty
1 Introduction
297(1)
2 The Role of Big Data in Traffic Safety Analysis
298(1)
2.1 Real-Time Crash Prediction
299(28)
2.2 Driving Behavior
327(5)
3 ADAS and Autonomous Vehicles (AVs)
332(4)
4 Conclusions
336(9)
References
337(8)
13 A Back-Engineering Approach to Explore Human Mobility Patterns Across Megacities Using Online Traffic Maps
Vana Gkania
Loukas Dimitriou
1 Introduction
345(2)
2 Data and Traffic Information Extraction Methods
347(1)
2.1 Cities Characteristics
347(2)
2.2 Data Gathering and Preprocessing
349(1)
2.3 Extracting Traffic Information by Image Processing
349(2)
3 Temporal and Spatiotemporal Mobility Patterns
351(1)
3.1 Temporal Patterns
352(4)
3.2 Spatiotemporal Patterns
356(2)
4 Dynamic Clustering and Propagation of Congestion
358(4)
5 Conclusions
362(3)
References
363(2)
14 Pavement Patch Defects Detection and Classification Using Smartphones, Vibration Signals and Video Images
Symeon E. Christodoulou
Charalambos Kyriakou
George Hadjidemetriou
1 Introduction
365(2)
2 Brief Literature Review
367(1)
2.1 Vibration-Based Methods
367(1)
2.2 Vision-Based Methods
368(1)
3 Methodology
369(1)
3.1 Anomaly Detection Using ANNs and Timeseries Analysis of Vibration Signals
369(2)
3.2 Anomaly Detection Using Entropic-Filter Image Segmentation
371(3)
3.3 Patch Detection and Measurement Using Support Vector Machines (SVM)
374(3)
4 Conclusions
377(5)
References
379(3)
15 Collaborative Positioning for Urban Intelligent Transportation Systems (ITS) and Personal Mobility (PM): Challenges and Perspectives
Vassilis Gikas
Guenther Retscher
Allison Kealy
1 Introduction
382(1)
2 C-ITS in Support of the Smart Cities Concept
383(1)
2.1 Scientific and Policy Perspectives of Urban C-ITS
383(3)
2.2 Taxonomy of Urban C-ITS Applications
386(1)
3 User Requirements for Urban C-ITS
387(1)
3.1 Requirements Overview
387(1)
3.2 Positioning Requirements and Parameters Definition
387(2)
4 Positioning Technologies for Urban ITS
389(4)
4.1 Radio Frequency-Based (RF) Technologies
393(4)
4.2 MEMS-Based Inertial Navigation
397(1)
4.3 Optical Technologies
398(1)
5 Measuring Types and Positioning Techniques
399(1)
5.1 Absolute Positioning Techniques
399(2)
5.2 Relative and Hybrid Positioning Techniques
401(1)
6 CP for C-ITS
402(1)
6.1 From Single Sensor Positioning to CP
402(1)
6.2 Fusion Algorithms and Techniques for CP
403(1)
7 Application Cases of Integrated Urban C-ITS
404(1)
7.1 Case 1: Smart-Bike Systems as a Component of Urban C-ITS
404(2)
7.2 Case 2: Smart Intersection for Traffic Control and Safety
406(1)
8 Discussion, Perspectives, and Conclusions
407(8)
References
409(4)
Further Reading
413(2)
Conclusions 415(4)
Index 419
Constantinos Antoniou is a Professor and Chair of Transportation Systems Engineering at the Technical University of Munich, Germany. He was previously an Associate Professor at the National Technical University of Athens, Greece. His research focuses on modelling and simulation of transportation systems, Intelligent Transport Systems (ITS), calibration and optimization applications, road safety and sustainable transport system. Antoniou has been involved in a large number of projects, primarily in Europe and the US, and has authored more than 500 scientific publications, including in Elseviers Transportation Research Part C: Emerging Technologies (for which he serves on the editorial board) and Transportation Research Part A: Policy and Practice (for which he serves as an Associate Editor). Loukas Dimitriou is an Assistant Professor in the Department of Civil and Environmental Engineering, University of Cyprus (UCY) and founder and head of the Lab for Transport Engineering, UCY. His research interests focus on the application of advanced computational intelligence methods, concepts and techniques for understanding the complex phenomena involved in realistic transport systems, and developing design and control strategies. The methodological paradigms that he proposes utilize elements from Data Science, behavioral analytics, complex systems modelling and advanced optimization, applied in traditional fields of transport, like demand modelling, travel behavior and systems organization, optimization and control. He has more than 100 publications in peer-reviewed journals, proceedings of conferences and book chapters, while he is an active member of international scientific organizations and committees.

Francisco Pereira is a Professor at the Technical University of Denmark, in Kongens Lyngby, Denmark, where he leads the Smart Mobility research group. Previously, he was Senior Research Scientist at MIT/CEE ITSLab, where he worked on real-time traffic prediction, behavior modeling, and advanced data collection technologies, both in Boston and Singapore, as part of the Singapore-MIT Alliance for Research and Technology, Future Urban Mobility project (SMART/FM). His main research focus is on applying machine learning and pattern recognition to the context of transportation systems with the purpose of understanding and predicting mobility behavior, and modeling and optimizing the transportation system as a whole. He has been published in many journals, including in Elseviers Transportation Research Part C: Emerging Technologies.