Handbook of Mobility Data Mining, Volume 3: Mobility Data-Driven Applications

Description

Handbook of Mobility Data Mining: Volume Three: Mobility Data-Driven Applications introduces the fundamental technologies of mobile big data mining (MDM), advanced AI methods, and upper-level applications, helping readers comprehensively understand MDM with a bottom-up approach. The book explains how to preprocess mobile big data, visualize urban mobility, simulate and predict human travel behavior, and assess urban mobility characteristics and their matching performance as conditions and constraints in transport, emergency management, and sustainability development systems. The book contains crucial information for researchers, engineers, operators, administrators, and policymakers seeking greater understanding of current technologies' infra-knowledge structure and limitations. The book introduces how to design MDM platforms that adapt to the evolving mobility environment―and new types of transportation and users―based on an integrated solution that utilizes sensing and communication capabilities to tackle significant challenges faced by the MDM field. This third volume looks at various cases studies to illustrate and explore the methods introduced in the first two volumes, covering topics such as Intelligent Transportation Management, Smart Emergency Management―detailing cases such as the Fukushima earthquake, Hurricane Katrina, and COVID-19―and Urban Sustainability Development, covering bicycle and railway travel behavior, mobility inequality, and road and light pollution inequality.  Front Cover Handbook of Mobility Data Mining Handbook of Mobility: Data Mining Mobility Data-Driven Applications Copyright Contents List of contributors Preface Acknowledgments One - Mobility data in bike-sharing systems 1. Introduction 2. Literature review 3. Case study 3.1 Case 1: Market-oriented subarea division 3.2 Case 2: Layout optimization 3.3 Case 3: System design optimization 4. Conclusion References Two - Improvement of an online ride-hailing system based on empirical GPS data 1. Introduction 2. Related works 3. Problem description 3.1 Emission performance and the user scale 3.1.1 Concept of emission performance 3.1.2 Emission performance and the user scale 3.1.3 Research framework 3.2 Ride-hailing dispatch based on prediction and optimization 3.2.1 Metric of evaluation 3.2.2 Research framework 4. Study case 5. Methodology 5.1 Emission performance and the user scale 5.1.1 Reassignment system 5.1.2 Gibbs Sampling for the generation of simulation samples 5.1.3 Crosssimulation module generation 5.1.4 Equation for result computation 5.2 Ride-hailing dispatch based on prediction and optimization 5.2.1 Time window division 5.2.2 Baseline: greedy algorithm 5.2.3 Prediction model 5.2.4 Optimization 6. Result analysis 6.1 Emission performance and the user scale 6.1.1 Void distance proportion analysis 6.1.2 Emission performance analysis 6.1.3 High-efficiency area computation under metric constraints 6.2 Ride-hailing dispatch based on prediction and optimization 6.2.1 Result of prediction 6.2.2 Result of dispatch 7. Conclusion and future work References Three - Research on vehicle routing problem and application scenarios 1. Introduction 2. Vehicle routing problem in MaaS shared-bus system 2.1 Introduction 2.2 Problem description 2.3 Methodology 2.4 Experiment of real world benchmark 2.4.1 Experimental set up 2.4.2 Experimental results and analysis 2.5 Conclusion 3. Application Scenario of Vehicle Routing Problem in Logistics Transportation 3.1 Introduction 3.2 Problem description 3.3 Methodologies 3.3.1 DBSCAN 3.3.2 Fast Unfolding 3.3.3 Experiment and result analysis 3.4 Conclusion 4. Summary and prospect References Four - Travel demand prediction model and applications 1. Introduction 2. Deep learning 2.1 Convolutional neural networks 2.2 Recurrent neural networks 3. Travel demand prediction model 4. Study case 5. Result and discussion 6. Technical potential analysis of travel demand prediction model 6.1 Scenarios 6.2 Indexes 6.2.1 Empty distance 6.2.2 Relative performance 6.3 Input and output 6.4 Ride-hailing dispatching system simulation 6.5 Result of ride-hailing dispatching system simulation 7. Conclusion References five - Railway usage behavior analysis based on mobile phone big data 1. Introduction 2. Literature review 3. Methodology 3.1 Framework 3.1.1 Dataset preparation 3.1.2 Quantifying usage behavior 3.1.3 Cluster analysis 3.1.4 Station attribution analysis 3.2 Deriving usage behavior probability 3.3 Station type detection 3.3.1 Usage behavior pattern clustering 3.3.2 Subtype detection 3.4 Identification of build environment indicators 4. Case study 4.1 Study area 4.2 Station type detection results 4.2.1 Parameter settings 4.2.2 Sensitivity Analysis 4.2.3 Usage behavior pattern clustering 4.2.4 Subtype detection 4.3 Built environment analysis 5. Discussion and conclusions References Six - An Origin-Destination matrix prediction-based road dynamic pricing optimization system 1. Introduction 2. Methodology 2.1 Karush–Kuhn–Tucker conditions 2.2 Link travel time function 2.3 Travel routes 2.4 Bi-level optimization model 3. Study case 4. Result and discussion 5. Conclusion References Seven - Blockchain for location-based big data-driven services 1. Introduction 1.1 Smart city 1.2 Location-based big data-driven services 1.3 Challenges in location-based big data-driven services 1.4 Blockchain for location-based big data-driven services 2. Background of blockchain 2.1 Blockchain 2.2 Smart contract 2.3 Consensus mechanism 3. Location-based big data-driven services 3.1 Shared mobility services 3.2 Charging services 3.3 Smart logistics services 4. Blockchain in location-based big data-driven services 4.1 Blockchian in shared mobility services 4.2 Blockchian in charging services 4.3 Blockchian in smart logistics services 5. Future trend of blockchain References Eight - Mobility data in urban road emission mitigation 1. Introduction 2. Literature review 3. Case studies 3.1 Case A: comparison between ride-hailing and taxi 3.1.1 Descriptions of the case study 3.1.2 Results 3.2 Case B: emission potential analysis of urban transit buses post-COVID-19 3.2.1 Descriptions of the case study 3.2.2 Methodology 3.2.3 Results 3.3 Case C: spatio-temporal analysis on on-road braking emission 3.3.1 Descriptions of the case study 3.3.2 Methodology 3.3.3 Results 3.4 Case D: travel attraction and urban vehicle emissions in Japan 3.4.1 Descriptions of the case study 3.4.2 Methodology 3.4.3 Results 4. Conclusion References Nine - Living environment inequity analyses based on mobile phone big data 1. Introduction 1.1 Background 1.1.1 Environmental justice 1.1.2 Artificial light at night 1.1.3 TOD usage in the context of aging 1.2 Literature review 1.2.1 EJ research on ALAN 1.2.2 TOD typology and its extension 2. Framework and dataset 2.1 Framework for ALAN inequity analysis 2.2 Framework for TOD inequity analysis 2.3 Case study 2.4 Data description 3. Methodology 3.1 Methodology for ALAN inequity analysis 3.1.1 Quantification of NTL intensity 3.1.2 Inequity analysis of population groups 3.2 Methodology for TOD inequity analysis 3.2.1 TOD indicators 3.2.2 Inequity analysis: correlation coefficient analysis 3.2.3 Validation of inequity: cluster analysis 4. Results 4.1 Result of ALAN inequity analysis 4.1.1 Descriptive analysis 4.1.2 ALAN exposure among different age groups 4.1.3 ALAN exposure among different residence groups 4.2 Result of TOD inequity analysis 4.2.1 Correlation coefficient analysis 4.2.2 Clusters of TODs 5. Conclusion and limitation 5.1 Conclusion of ALAN equity 5.2 Conclusion of TOD equity References Further reading Index A B C D E F G H K L M N O P R S T U V W Back Cover