Mahdieh Allahviranloo is Assistant Professor of Department of Civil Engineering, the City College of New York. She was educated at the University of California, Irvine where she was awarded the PhD degree in Civil Engineering. She has a M.S. degree in transportation engineering from Iran University of Science and Technology, and B.S. degree in civil engineering from Sharif University of Technology. She is a recipient of Dwight Eisenhower Graduate Fellowship and Helen Overly Memorial Scholarship. Her research fields are: travel demand modeling, transportation systems analysis, network optimization, data mining, machine learning, and Bayesian econometrics.
Ever since Torsten Hägerstrand’s famous “What about People in Regional Science?” presentation in Copenhagen, Denmark in 1969, that begged the need to study the individual in order to understand social and group behavior, a growing cadre of researchers have been trying to operationalize this concept. In the past forty years there has been an increasing focus on applying activity-based models in travel demand studies to analyze the linkages between travel behavior of individuals and their socio-demographic profiles. In an increasingly data-rich world, it is even more imperative that such disaggregated models be developed to capture the underlying mobility trends, for better planning and design of transportation networks and infrastructure.
Here, we present a comprehensive mathematical/statistical framework to infer and replicate travel behavior of individuals in terms of their socio-demographic profiles. The framework comprises several distinct modules that employ statistical segmentation, Bayesian econometrics, data mining, and optimization techniques to predict the type of activities that individuals are planning to participate in, their activity frequencies, scheduling, and travel linkages. The outputs of the model include the likely content of activity agenda based on an inference procedure that incorporates uncertainty in the decision making procedure, and integrates transportation network topology within activity selection and scheduling. Detailed assessment of human activity patterns and prediction of vehicle movements in the network, with the consequent estimation of vehicular carbon footprints, will tie the model to a larger context of addressing concerns related to global warming and Greenhouse Gas emissions.