Handbook of Mobility Data Mining, Volume 2

Handbook of Mobility Data Mining, Volume 2

Mobility Analytics and Prediction

1st Edition - January 1, 2023

Write a review

  • Editor: Haoran Zhang
  • Paperback ISBN: 9780443184246

Purchase options

Purchase options
Available for Pre-Order
Sales tax will be calculated at check-out

Institutional Subscription

Free Global Shipping
No minimum order

Description

The Handbook of Mobility Data Mining: Mobility Analytics and Prediction: Volume 2: Mobility Analytics and Prediction 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. It 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. Further, it focuses on introducing how to design MDM platforms that adapt to the evolving mobility environment, new types of transportation, and users based on an integrated solution that utilizes sensing and communication capabilities to tackle the significant challenges that the MDM field faces. Volume 2: Mobility Analytics and Prediction provides a basis for how to simulate and predict mobility data. After an introductory theory chapter, it then covers crucial topics such as long-term mobility pattern analytics, mobility data generators, user information inference, Grid-based population density prediction, and more. It concludes with a chapter on graph-based mobility data analytics. The information in this work is crucial for researchers, engineers, operators, company administrators, and policymakers in related fields, to comprehensively understand current technologies' infra-knowledge structure and limitations.

Key Features

  • Discusses how to efficiently simulate the massive and large-scale people movement and predict mobility at an urban scale
  • Introduces both online detection methods, which can sequentially process data, and offline detection methods, which are usually more robust
  • Stems from the editor’s strong network of global transport authorities and transport companies, providing a solid knowledge structure and data foundation as well as geographical and stakeholder coverage

Readership

Researchers, engineers, operators, company administrators, and policymakers on transportation, environment, urban planning, data mining, and sustainability; Transport-mobility planners, the road and vehicle industry, urban management authorities, transportation institutes, traffic police, public and goods transport operators; masters and Ph.D. students pursuing research in the area of mobility and transportation

Table of Contents

  • 1. Mobility Simulation and Prediction: Concept, Theory, and Framework

    2. Long-term Mobility Pattern Analytics-Changes Detection
    2.1 Home-work location detection
    2.2 Offline Long-tern Mobility Pattern Changes Detection
    2.3 Online Long-term Mobility Pattern Changes Detection

    3. Long-term Mobility Pattern Analytics-Clustering
    3.1 Time-series based Clustering
    3.2 Graph-based Clustering
    3.3 Advanced Clustering Methods

    4. Mobility Data Generator- Physical Models
    4.1 Physical Environment
    4.2 Agent-based model

    5. Mobility Data Generator- Probabilistic Models
    5.1 Statistic Method
    5.2 Hidden Markov Model-based Generative Model
    5.3 Pure Random Mobility Model
    5.4 Interaction-based Mobility Model
    5.5 Deep Learning Model

    6. User Information Inference
    6.1 Demographic Information Inference
    6.2 Income Information Inference

    7. Mobility Similarity Evaluation
    7.1 Trajectory Similarity Evaluation
    7.2 Individual Mobility Similarity Evaluation
    7.3 OD Similarity Evaluation

    8. Grid-based Population Density Prediction
    8.1 Space-time Multiple Regression Model
    8.2 RNN based Prediction Model
    8.3 Advanced prediction Models

    9. Grid-based OD Prediction
    9.1 RNN based Prediction Model
    9.2 Multi-task Prediction Model
    9.3 Advanced prediction Models

    10. Individual Trajectory Prediction
    10.1 Kalman Filter Method
    10.2 Social Force Model
    10.3 RNN based Prediction Model
    10.4 Social Interactions Model

    11. Graph-based Mobility Data Analytics
    11.1 Graph Construction
    11.2 Graph-based Mobility Data Generation
    11.3 Graph-based Mobility Data Prediction

Product details

  • No. of pages: 300
  • Language: English
  • Copyright: © Elsevier 2023
  • Published: January 1, 2023
  • Imprint: Elsevier
  • Paperback ISBN: 9780443184246

About the Editor

Haoran Zhang

Haoran (Ronan) Zhang is Assistant Professor in the Center for Spatial Information Science at the University of Tokyo, a Researcher at the School of Business Society and Engineering at Mälardalen University in Sweden, and Senior Scientist at Locationmind Inc. in Japan. His research includes smart supply chain technologies, GPS data in shared transportation, urban sustainable performance, GIS technologies in renewable energy systems, and smart cities. He is author of numerous journal articles and Editorial Board Member of several international academic journals. He has Ph.D.’s in both Engineering and Sociocultural Environment and was awarded Excellent Young Researcher by Japan’s Ministry of Education, Culture, Sports, Science and Technology.

Affiliations and Expertise

Assistant Professor, Center for Spatial Information Science, University of Tokyo, Tokyo, Japan; Researcher, School of Business Society and Engineering, Mälardalen University, Sweden; Senior Scientist, Locationmind Inc., Tokyo, Japan

Ratings and Reviews

Write a review

There are currently no reviews for "Handbook of Mobility Data Mining, Volume 2"