Big Data and Mobility as a Service

Front Cover
Big Data and Mobility as a Service
Copyright
Contents
Contributors
Introduction
	1. Background
	2. Big data: Definition, history, today
	3. MaaS: Definition, history, today
	4. Big data X MaaS
	5. Summary
Chapter 1: MaaS system development and APPs
	1. The development history of MaaS
		1.1. The conception
		1.2. The early application
		1.3. MaaS alliance
		1.4. Development
		1.5. Revolution and innovation
	2. The category of MaaS system
		2.1. Level 0: No integration
		2.2. Level 1: Information integration
		2.3. Level 2: Integration of booking and payment
		2.4. Level 3: Integration of the service offering
		2.5. Level 4: Integration of societal goals
	3. Study case
		3.1. UbiGo
			3.1.1. Introduction
			3.1.2. Services
			3.1.3. Characteristics
		3.2. Whim
			3.2.1. Introduction
			3.2.2. Services
			3.2.3. Characteristics
		3.3. Moovit
			3.3.1. Introduction
			3.3.2. Services
			3.3.3. Characteristics
		3.4. Uber
			3.4.1. Introduction
			3.4.2. Services
			3.4.3. Characteristics
	4. Future development trend of MaaS system
		4.1. Data-integrated
		4.2. Future-oriented
		4.3. Sustainable
	References
Chapter 2: Spatio-temporal data preprocessing technologies
	1. Introduction
	2. Raw GPS data and workflow of data preprocessing
	3. Key technologies and corresponding application
		3.1. Outlier removement
		3.2. Stay location detection
		3.3. Travel segmentation
		3.4. Travel mode detection
		3.5. Map matching
		3.6. Summary
	4. Case study
		4.1. Stay location detection: Life pattern analysis
			4.1.1. Introduction
			4.1.2. Problem and methodology
			4.1.3. Result illustration and analysis
			4.1.4. Conclusion
		4.2. Travel segmentation and mode detection: Ride-sharing potential analysis
			4.2.1. Introduction
			4.2.2. Problem and methodology
			4.2.3. Result illustration and analysis
			4.2.4. Conclusion
		4.3. Map matching: Estimation of urban scale PM emission
			4.3.1. Introduction
			4.3.2. Problem and methodology
			4.3.3. Result illustration and analysis
			4.3.4. Conclusion
	5. Conclusion
	References
Chapter 3: Travel similarity estimation and clustering
	1. Introduction
	2. Trajectory similarity
		2.1. Point-to-point distance metric
		2.2. Similarity function of trajectory
		2.3. Trajectory clustering
	3. Travel pattern similarity
		3.1. Travel pattern extraction
		3.2. Travel pattern expression
		3.3. Travel pattern clustering
	4. Origin-destination matrix similarity
		4.1. Volume difference focused OD similarity measure
		4.2. Image-based OD similarity measure
		4.3. Transforming distance-based OD similarity measure
		4.4. OD tableau similarity measure: Mobsimilarity
	5. Case study
		5.1. CDR-based travel estimation accuracy analysis
		5.2. Metro usage pattern clustering
	6. Conclusion and future directions
	References
Chapter 4: Data fusion technologies for MaaS
	1. Introduction
	2. Data formula
		2.1. Attribute and event data
		2.2. Trajectory data
		2.3. Origin-destination (OD) trip data
		2.4. Correlation network
		2.5. Environmental data
	3. Categories of data fusion methods in MaaS
	4. Data fusion based on deep learning
		4.1. Fundamental building units of deep learning network
			4.1.1. CNN
			4.1.2. RNN
			4.1.3. ConvLSTM
			4.1.4. Autoencoder (AE)
			4.1.5. Convolution graph neural network (ConvGNN)
		4.2. Fusion strategy
			4.2.1. Concatenation
			4.2.2. Sum & Hadamard product
			4.2.3. Attention mechanism
			4.2.4. Graph fusion
			4.2.5. Output-input structure
	5. Decomposition-based methods
	6. Challenging problems of data fusion in MaaS
		6.1. Data quality
		6.2. Model complexity
		6.3. Data fusion in comparative analysis
	7. Conclusions
	Acknowledgments
	References
Chapter 5: Data-driven optimization technologies for MaaS
	1. Overview of data-driven optimization for the urban mobility system
		1.1. Data-driven dispatching methods for on-demand ridesharing
		1.2. Data-driven scheduling methods for public transit
		1.3. Data-driven rebalancing methods for bicycle-sharing
	2. Overview of the general concept in MaaS System
		2.1. Overview of the MaaS systems
		2.2. Overview of data in MaaS systems
	3. Mobility resource allocation in MaaS system
		3.1. Mobility resource allocation framework in MaaS
		3.2. Data-driven online stochastic resource allocation problems
	4. Data-driven optimization technologies for resource allocation in MaaS
		4.1. Sample average approximation
		4.2. Robust optimization
		4.3. Predictive analysis and prescriptive analysis
		4.4. Machine learning-based robust optimization
	5. Real-world application and case study
		5.1. Problem description
		5.2. Methodology
		5.3. Results and discussion
	6. Conclusions
	References
Chapter 6: Data-driven estimation for urban travel shareability
	1. Introduction
		1.1. The emergence of sharing transportation
		1.2. The significance of shareability estimation
		1.3. Chapter organization
	2. Emerging sharing transportation mode
		2.1. Bicycle sharing
		2.2. Ride sharing and taxi sharing
		2.3. Customized bus
		2.4. Characteristics of sharing transportation modes
	3. Background to traditional data and their limitations
	4. New and emerging source of data
		4.1. Track and trace data
			4.1.1. Mobile phone data
			4.1.2. Smart card data
			4.1.3. Taxi GPS data
			4.1.4. Bicycle-sharing data
		4.2. Geographic information data
			4.2.1. Transportation network
			4.2.2. Vector data
			4.2.3. Point of interest data
			4.2.4. Navigation data
		4.3. Advantages and disadvantages of new data sources
	5. Emerging form of key technologies
		5.1. Agent-based modeling
		5.2. How ABM can be applied in shareability estimation
			5.2.1. Level 1: ABM in macroscopic policy assessment
			5.2.2. Level 2: ABM in microscopic strategy evaluation
			5.2.3. Level 3: ABM in both macroscopic and microscopic strategy optimization
	6. Case study of ABM in urban shareability estimation
		6.1. Dynamic electric fence for bicycle sharing
		6.2. ABM simulation
		6.3. Data and study area
		6.4. Result of simulation
		6.5. Evaluation of the result
	7. Opportunities and challenges
		7.1. Data acquisition
		7.2. Demand prediction
		7.3. Design improvement of ABM
		7.4. Acceleration of large-scale ABM
	8. Conclusions
	Acknowledgment
	References
Chapter 7: Data mining technologies for Mobility-as-a-Service (MaaS)
	1. Introduction of data mining technologies in MaaS system
	2. Data mining technologies in MaaS system
		2.1. What is data mining?
		2.2. Object of data mining
		2.3. Classical steps of data mining
		2.4. Types of transportation data
			2.4.1. Static data
			2.4.2. Fixed detector data
			2.4.3. Mobile detector data
			2.4.4. Operation data
	3. Methodologies of data mining technologies used in MaaS system
		3.1. Support vector machine
			3.1.1. linear SVM in linearly separable case
			3.1.2. linear SVM in linearly inseparable case
			3.1.3. Nonlinear SVM
		3.2. Linear regression
			3.2.1. Least square method
			3.2.2. Maximum likelihood estimation
		3.3. Decision tree
			3.3.1. The structure of decision tree
			3.3.2. Attribute partition selection
				Information entropy
				Information gain
				Rate of information gain
				Gini index
		3.4. Clustering analysis
			3.4.1. Similarity measurement
				Numerical variable
			3.4.2. Clustering algorithms
				K-means
					Objective function
				Hierarchical clustering
					Algorithm
				Density-based spatial clustering of applications with noise (DBSCAN)
					Algorithm
				Grid-based clustering
					Algorithm
	4. Case study of data mining for MaaS: Bike sharing in Beijing during Covid-19 pandemic
	5. Summary of chapter
	References
Chapter 8: MaaS and IoT: Concepts, methodologies, and applications
	1. Introduction
	2. Overview of the concept
		2.1. Overview of the general concept
		2.2. Challenges of IoT application in MaaS
	3. Key technologies and methodologies
		3.1. Intelligent transportation equipment
		3.2. Communication protocols for the Internet of Things
		3.3. Microservices based on the Internet of Things
		3.4. Cloud computing based on the Internet of Things
		3.5. Edge computing
		3.6. Security technologies for the Internet of Things
	4. Application and case study
		4.1. Background introduction
		4.2. System framework
		4.3. Core function
	5. Conclusion and future directions
	References
Chapter 9: MaaS system visualization
	1. Overview of the general concept
	2. The key visualization technologies in MaaS for different stakeholders
		2.1. The perspective of demanders of mobility
		2.2. The perspective of supplier of transportation service
			2.2.1. Monitoring
				Object movement monitoring
				Operation status monitoring
			2.2.2. Analysis and optimization
		2.3. The perspective of city manager
	3. Real-world application and case study
		3.1. Case for demanders of mobility
		3.2. Case for supplier of transportation service
		3.3. Case for city manager
		3.4. Open-source visualization tools and libraries
	4. Conclusion and future directions
	References
Chapter 10: MaaS for sustainable urban development
	1. Introduction
	2. MaaS interacted with urban traffic and space
		2.1. Urban traffic structure
		2.2. Urban spatial structure
	3. Strategies for MaaS in urban sustainable development at multiple scales
		3.1. Macroscale: Synergy between urban agglomerations and metropolitan areas
		3.2. Mesoscale: Optimization of internal resources in cities
		3.3. Microscale: The refinement of urban streets
	4. Case study
	5. Conclusion
	References
Index
Back Cover