Abstract
ABSTRACTConstructing agent data with detailed information on their sociodemographics is substantially important for agent-based modelling. However, to collect data about the whole population is not efficient, since it requires an expensive and time-consuming survey, especially for a large population. The paper uses a novel approach that integrates Bayesian network (BN) and generalized raking (GR) multilevel iterative proportional fitting (IPF). Furthermore, the approach is applied to construct the population for Greater Jakarta, Indonesia, which consists of 30 million inhabitants. The results show that the BN approach can produce data that represent the probability distribution of sample data and that the IPF can match it against aggregate census data.
Highlights
Agent-based transportation models require detailed individual and household information such as sociodemographic and geocoding of activity locations (Balmer, Axhausen, & Nagel, 2006)
The results show that the Bayesian network (BN) approach can produce data that represent the probability distribution of sample data and that the iterative proportional fitting (IPF) can match it against aggregate census data
We found that the BN can construct a synthetic population and reproduce the Household Travel Survey (HTS) data
Summary
Agent-based transportation models require detailed individual and household information such as sociodemographic and geocoding of activity locations (Balmer, Axhausen, & Nagel, 2006). BN step We consider seven variables by combining individual and household data for the population synthesis using BN, as presented in Table 4: type of activities, age, sex, income, housing, car. As found in Sun and Erath (2015) and Zhang et al (2017) that the BN model can reproduce the distribution of the HTS data
Sign-in/Register to view highlights & summary Sign-in/Register to access full text options 
Free) 
Talk to us
Join us for a 30 min session where you can share your feedback and ask us any queries you have
Schedule a call
