Realistic Transport Simulation: Tackling the Small Data Challenge with Open Data

Guimu Guo, Jalal Majed Khalil, Da Yan, Virginia Sisiopiku

Research output: Chapter in Book/Report/Conference proceedingConference contribution

4 Scopus citations

Abstract

MATSim is the state-of-the-art open source software for agent-based transport simulation, intended for use to evaluate transportation planning models. A standard approach to use MATSim is to conduct a user survey about their day-plans of travel, from which a synthetic dataset of agents' day-plans for an entire region is generated for transport simulation. The simulation output can be used for various evaluations, such as congestion conditions of road segments and their peak hours.This paper aims to conduct a transportation simulation on MATSim for the region of Birmingham, AL. A traditional approach based on Iterative Proportional Fitting (IPF) is not sufficient for generating a realistic synthetic population due to the small data problem: Birmingham is a small city with limited transport data statistics, and we only have a survey of 451 people for their day-plans. To tackle the small data problem, we seek the assistance of abundant open data such as US Census data, OpenStreetMap, OpenAddresses and Birmingham Business}{Alliance to complete the fine details realistically. We also utilize various data science and machine learning techniques to build models that utilize these open data to generate a realistic population. Preliminary tests demonstrate reasonable accuracy of the simulation results.

Original languageEnglish (US)
Title of host publicationProceedings - 2019 IEEE International Conference on Big Data, Big Data 2019
EditorsChaitanya Baru, Jun Huan, Latifur Khan, Xiaohua Tony Hu, Ronay Ak, Yuanyuan Tian, Roger Barga, Carlo Zaniolo, Kisung Lee, Yanfang Fanny Ye
PublisherInstitute of Electrical and Electronics Engineers Inc.
Pages4512-4519
Number of pages8
ISBN (Electronic)9781728108582
DOIs
StatePublished - Dec 2019
Externally publishedYes
Event2019 IEEE International Conference on Big Data, Big Data 2019 - Los Angeles, United States
Duration: Dec 9 2019Dec 12 2019

Publication series

NameProceedings - 2019 IEEE International Conference on Big Data, Big Data 2019

Conference

Conference2019 IEEE International Conference on Big Data, Big Data 2019
Country/TerritoryUnited States
CityLos Angeles
Period12/9/1912/12/19

All Science Journal Classification (ASJC) codes

  • Artificial Intelligence
  • Computer Networks and Communications
  • Information Systems
  • Information Systems and Management

Fingerprint

Dive into the research topics of 'Realistic Transport Simulation: Tackling the Small Data Challenge with Open Data'. Together they form a unique fingerprint.

Cite this