Integrating Activity-Based Models with Mobile Phone Data
Advances in Traffic Modeling and Multi-Agent Simulation
- 1st Edition - May 1, 2026
- Latest edition
- Authors: Fei Yang, Yudong Guo, Zhenyu Shan
- Language: English
Integrating Activity-Based Models with Mobile Phone Data: Advances in Traffic Modeling and Multi-Agent Simulation analyzes the path from the observation to prediction using traffi… Read more
Integrating Activity-Based Models with Mobile Phone Data: Advances in Traffic Modeling and Multi-Agent Simulation analyzes the path from the observation to prediction using traffic big data. The book explores the refined identification method of individual travel chains in the diversified and complex urban travel environment, reconstructing the structure and algorithms of Activity-based Models or ABM based on the characteristics identified by mobile phone signaling data. Final sections develop an activity decision-making and microscopic behavior simulation platform. Users will find this to be a resource that supports urban and regional traffic management optimization and traffic planning using traffic big data.
- Discusses highly debated issues in the fields of commodities, sustainable (ESG) finance, and sustainable development
- Applies various levels of analysis and research methods, leading to both macro- and micro-level conclusions
- Includes a highly detailed empirical analysis, utilizing a comprehensive database throughout the book, with information on all ETCs—regardless of their activity status
- Utilizes the example of a market for exchange-traded commodities (ETCs), merging the academic and practical perspectives
Researchers, practitioners, policy makers, college teachers and senior students in the fields of traffic engineering, urban planning, data science
1. Introduction
1.1 General
1.1.1 Existing Traffic Models Mismatch the Urban Developed Governance
1.1.2 Advantages of 4G/5G Mobile Networks in Analysis Individual Activity Chains
1.1.3 Next-Generation Disaggregate Traffic Models for Urban Sustainable Development
1.2 Prospects of Mobile Phone Signaling Data
1.2.1 Academic Prospects
1.2.2 Industrial Applications
1.3 Objectives and Value of Mobile Phone Signaling Data Reliability
1.4 Research Framework: From Feature Recognition to Traffic Modeling
1.4.1 Review of Travel Characteristic Recognition and ABM
1.4.2 Technical Principles and Evaluation of 4G/5G Mobile Phone Signaling Data
1.4.3 Accurate Travel Chain Identification based on mobile phone signaling data
1.4.4 Reconstruction of ABM Fused with Multi-Source Data
1.4.5 Construction of Activity Scheduling and Multi-Agent Micro-Simulation Platform based on the historical activity
1.5 Summary
2. Review of Travel Characteristic Recognition and Activity-Based Modeling
2.1 Development of Travel Chain Identification by Mobile Phone Signaling Data
2.1.1 Characteristics Comparison of Various Mobile Phone Positioning Data
2.1.2 Development of Trip Endpoint Identification
2.1.3 Development of Travel Path Identification
2.1.4 Development of Travel Mode Identification
2.2 Development of ABM
2.2.1 Development with Data Evolution
2.2.2 Development with Prediction Methodology
2.2.3 Development with Model Framework
2.3 Development of Activity Scheduling and Multi-Agent Micro-Simulation Platform
2.3.1 Eindhoven University of Technology: From AURORA to FEATHERS
2.3.2 University of Toronto: From TASHA to GTASIM
2.3.3 Technische Universität Berlin: MATSim
2.3.4 MIT: from DynaMIT to SimMobility
2.3.5 Other Platforms
2.4 Summary
3. Technical Principles and Evaluation of 4G/5G Mobile Phone Signaling Data
3.1 Communication Networks Mechanisms
3.1.1 Evolution of Wireless Communication Systems
3.1.2 Structure of 4G/5G Communication Networks
3.2 Spatio-temporal Characteristics of 4G/5G Mobile Phone Signaling Data
3.2.1 Data Generation and Extraction in 4G/5G Communication Networks
3.2.2 Spatial Distribution of 4G/5G Communication Base Stations
3.2.3 Temporal Characteristics of 4G/5G Mobile Phone Signaling Data
3.3 Summary
4. Accurate Travel Chain Identification Based on Mobile Phone Signaling Data
4.1 Framework
4.2 Experiment Design and Data Analysis
4.2.1 Experimental Design Methodology
4.2.2 Characteristic Analysis of 4G/5G Mobile Phone Signaling Data
4.2.3 Pre-processing
4.3 Accurate Travel Endpoint Identification and Localization
4.3.1 Travel Endpoint Identification
4.3.2 Activity Localization
4.3.3 Optimization Strategies
4.3.4 Parameter Calibration
4.3.5 Validation and Evaluation
4.4 Travel Path Identification in Complex Urban Road Networks
4.4.1 Travel Path Fitting Module 4.4.2 Travel Path Identification Module
4.4.3 Parameter Calibration
4.4.4 Validation and Evaluation
4.5 Motorized Travel Mode Identification in Complex Urban Road Networks
4.5.1 Input Data Characteristics
4.5.2 Identification Algorithms
4.5.3 Parameter Calibration
4.5.4 Validation and Evaluation
4.6 Summary
5. ABMs Combined with Mobile Phone Signaling Data
5.1 Model Structure
5.2 Input Data
5.2.1 Historical Individual Activity Chain
5.2.2 Public Transportation
5.2.3 Point-of-Interest (POI)
5.2.4 Urban Road Network
5.3 Basic Information Prediction Module (BIPM)
5.4 Primary Activity Prediction Module (PAPM)
5.4.1 Activity Start Time and Duration Prediction
5.4.2 Activity Location Prediction
5.5 Secondary Activity Prediction Module (SAPM)
5.5.1 Activity Duration Prediction
5.5.2 Activity Location Prediction
5.5.3 Travel Information Prediction
5.6 Time Dynamic Adjustment Module (TDAM)
5.7 Evaluation with Multi-Source Data and Prediction Methods
5.7.1 Verification Method
5.7.2 Evaluation with Multi-Source Data
5.7.3 Evaluation With Various Prediction Methods
5.8 Summary
6. Activity Scheduling and Multi-Agent Micro-Simulation Platform
6.1 Significance of Historical Behavior in Activity Scheduling
6.2 Platform Structure
6.2.1 Input Data
6.2.2 Activity Simulation and Adjustment Module
6.2.3 State Adjustment Module
6.3 Multi-Scenario Simulation and Evaluation
6.3.1 Parameter calibration
6.3.2 Case Study in Chengdu
6.4 Summary
7. Outlook
1.1 General
1.1.1 Existing Traffic Models Mismatch the Urban Developed Governance
1.1.2 Advantages of 4G/5G Mobile Networks in Analysis Individual Activity Chains
1.1.3 Next-Generation Disaggregate Traffic Models for Urban Sustainable Development
1.2 Prospects of Mobile Phone Signaling Data
1.2.1 Academic Prospects
1.2.2 Industrial Applications
1.3 Objectives and Value of Mobile Phone Signaling Data Reliability
1.4 Research Framework: From Feature Recognition to Traffic Modeling
1.4.1 Review of Travel Characteristic Recognition and ABM
1.4.2 Technical Principles and Evaluation of 4G/5G Mobile Phone Signaling Data
1.4.3 Accurate Travel Chain Identification based on mobile phone signaling data
1.4.4 Reconstruction of ABM Fused with Multi-Source Data
1.4.5 Construction of Activity Scheduling and Multi-Agent Micro-Simulation Platform based on the historical activity
1.5 Summary
2. Review of Travel Characteristic Recognition and Activity-Based Modeling
2.1 Development of Travel Chain Identification by Mobile Phone Signaling Data
2.1.1 Characteristics Comparison of Various Mobile Phone Positioning Data
2.1.2 Development of Trip Endpoint Identification
2.1.3 Development of Travel Path Identification
2.1.4 Development of Travel Mode Identification
2.2 Development of ABM
2.2.1 Development with Data Evolution
2.2.2 Development with Prediction Methodology
2.2.3 Development with Model Framework
2.3 Development of Activity Scheduling and Multi-Agent Micro-Simulation Platform
2.3.1 Eindhoven University of Technology: From AURORA to FEATHERS
2.3.2 University of Toronto: From TASHA to GTASIM
2.3.3 Technische Universität Berlin: MATSim
2.3.4 MIT: from DynaMIT to SimMobility
2.3.5 Other Platforms
2.4 Summary
3. Technical Principles and Evaluation of 4G/5G Mobile Phone Signaling Data
3.1 Communication Networks Mechanisms
3.1.1 Evolution of Wireless Communication Systems
3.1.2 Structure of 4G/5G Communication Networks
3.2 Spatio-temporal Characteristics of 4G/5G Mobile Phone Signaling Data
3.2.1 Data Generation and Extraction in 4G/5G Communication Networks
3.2.2 Spatial Distribution of 4G/5G Communication Base Stations
3.2.3 Temporal Characteristics of 4G/5G Mobile Phone Signaling Data
3.3 Summary
4. Accurate Travel Chain Identification Based on Mobile Phone Signaling Data
4.1 Framework
4.2 Experiment Design and Data Analysis
4.2.1 Experimental Design Methodology
4.2.2 Characteristic Analysis of 4G/5G Mobile Phone Signaling Data
4.2.3 Pre-processing
4.3 Accurate Travel Endpoint Identification and Localization
4.3.1 Travel Endpoint Identification
4.3.2 Activity Localization
4.3.3 Optimization Strategies
4.3.4 Parameter Calibration
4.3.5 Validation and Evaluation
4.4 Travel Path Identification in Complex Urban Road Networks
4.4.1 Travel Path Fitting Module 4.4.2 Travel Path Identification Module
4.4.3 Parameter Calibration
4.4.4 Validation and Evaluation
4.5 Motorized Travel Mode Identification in Complex Urban Road Networks
4.5.1 Input Data Characteristics
4.5.2 Identification Algorithms
4.5.3 Parameter Calibration
4.5.4 Validation and Evaluation
4.6 Summary
5. ABMs Combined with Mobile Phone Signaling Data
5.1 Model Structure
5.2 Input Data
5.2.1 Historical Individual Activity Chain
5.2.2 Public Transportation
5.2.3 Point-of-Interest (POI)
5.2.4 Urban Road Network
5.3 Basic Information Prediction Module (BIPM)
5.4 Primary Activity Prediction Module (PAPM)
5.4.1 Activity Start Time and Duration Prediction
5.4.2 Activity Location Prediction
5.5 Secondary Activity Prediction Module (SAPM)
5.5.1 Activity Duration Prediction
5.5.2 Activity Location Prediction
5.5.3 Travel Information Prediction
5.6 Time Dynamic Adjustment Module (TDAM)
5.7 Evaluation with Multi-Source Data and Prediction Methods
5.7.1 Verification Method
5.7.2 Evaluation with Multi-Source Data
5.7.3 Evaluation With Various Prediction Methods
5.8 Summary
6. Activity Scheduling and Multi-Agent Micro-Simulation Platform
6.1 Significance of Historical Behavior in Activity Scheduling
6.2 Platform Structure
6.2.1 Input Data
6.2.2 Activity Simulation and Adjustment Module
6.2.3 State Adjustment Module
6.3 Multi-Scenario Simulation and Evaluation
6.3.1 Parameter calibration
6.3.2 Case Study in Chengdu
6.4 Summary
7. Outlook
- Edition: 1
- Latest edition
- Published: May 1, 2026
- Language: English
FY
Fei Yang
Professor Fei Yang is based at Southwest Jiaotong University and is Director of the Department of Transportation Engineering in the School of Transportation and Logistics; he is engaged in researching traffic big data and intelligent transportation technology application, travel behaviour theory and empirical evidence, urban traffic planning theory and methodology related research.
Professor Yang received his Ph.D. degree from Tongji University in 2007 and spent one year of postdoctoral study at the University of Wisconsin-Madison in 2011. Professor Yang has been selected for the University's New Century Excellent Talents program. He has conducted more than 10 national and provincial scientific research projects, including four projects of the National Natural Science Foundation of China and one sub-project of the National Key R&D Program of China. He has published more than 70 academic papers and five academic monographs; one of the monographs was funded by the National Publication Foundation and selected for the National Publication Plan for key publications of the "The 13th Five-Year Plan".
Affiliations and expertise
Southwest Jiaotong University, ChinaYG
Yudong Guo
Dr Yudong Guo works at the Sichuan Expressway Construction & Development Group Co., Ltd. and is engaged in expressway operation and management, traffic big data, traffic model, traffic planning and management. He has published more than 15 academic papers, one academic monograph, four patents, and has been awarded one software copyright
Affiliations and expertise
Sichuan Expressway Construction and Development Group Co., Ltd, ChinaZS
Zhenyu Shan
Zhenyu Shan is a researcher at the School of Transportation and Logistics of Southwest Jiaotong University. He has been engaged in researching and applying traffic big data, traffic management, and traffic demand modelling
Affiliations and expertise
Zhenyu Shan