Maison des Sciences Humaines
11, Porte des Sciences
L-4366 Esch-sur-Alzette / Belval
LISER Salle de Conference, 1st Floor
seminars@liser.lu
Abstract
Understanding and modelling human mobility are fundamental for applications from planning to operations and management in cities. Mobile sensing has enabled us to collect a large amount of mobility data from human decision-makers, for example, GPS trajectories from mobile phones and passenger trip data of taking buses and trains from smart card data. The presentation will demonstrate the applicability and value of the data with examples of recent developments, including a) Causal inference of behavior changes under incentive interventions, and 2) Inverse reinforcement learning for individual behavior change prediction. The methods are validated using smart card data for a real-world case study on a pre-peak fare discount incentive program in the Hong Kong Mass Transit Railway system. The methodology and empirical findings as well as the future envisions of AI for behavior learning will be discussed.
Biography
Zhenliang Ma is Associate Professor in Transportation Systems at Transport Planning Division at KTH, and Faculty Member of KTH Digital Futures. His research focuses on data science based modeling, simulation, optimization, and control of mobility-related systems, which are: intelligent transport systems and multimodal mobility systems. He is an Associate Editor of IEEE Transactions on Intelligent Transportation Systems, Associate Editor of Journal of Public Transportation, and TRB Committee Member (AP090-Transit Data and AEP060-Travel Demand Management).
