Summer Conferences

During this summer, our MLSM group presented two papers at two conferences. The first paper was presented at the International Symposium on Transportation Data & Modelling (ISTDM2023) held in Ispra, Italy, from June 19 to 22. The second paper was presented at the 23rd Conference of the International Federation of Operational Research Societies (IFORS2023) in Santiago, Chile, from July 10 to 14. Check below for more details:

New member in our group: welcome Danya!

Danya Li recently joined our group as a Ph.D. student and she will be working under the supervision of Professors Francisco Pereira and Rico Kruger from our group, Prof. Xiang Xu from the Norwegian University of Science and Technology (NTNU), and Prof. Xiao Yu from Aalto University.

Danya graduated from the Swiss Federal Institute of Technology in Lausanne (EPFL) with a Master’s in Civil Engineering. Her research will focus on developing a new generation of behavioral models at the intersection of econometrics and psychology using machine learning and virtual reality.

We wish her a fun and productive time during her stay with us! 😊

New member in our group: welcome Mana!

Mana Meskar recently joined our group as a visiting PhD student from Sharif University of Technology. She will be co-supervised by Rico Kruger and Filipe Rodrigues from our group.

Mana has received her BSc and MSc in industrial engineering from Sharif university of technology. She is particularly interested in the intersection of Data Analytics and Operations Research, with a specific focus on the subjects of Transportation and Two-sided Markets.

Her current research is on matching strategies in ride-hailing platforms and her overall goal is to uncover the factors that affect drivers’ responses to ride requests received through the platform’s dispatch system. Additionally, she aim to develop an effective machine-learning-based model for predicting drivers’ decisions to accept or reject ride requests. This model will enable platforms to make data-based decisions and form the basis for developing a strategy for ongoing dispatch center processes

We wish her a fun and productive time during her stay with us! 😊

New member in our group: welcome Santa!

Santa Maiti recently joined our group as a visiting Eurotech (Marie Skłodowska-Curie) Postdoctoral Researcher from the Technical University of Munich (TUM). Her supervisor is Prof. Constantinos Antoniou from TUM and co-supervisor is Associate Prof. Carlos Lima Azevedo from DTU.

Santa received her PhD in Intelligent Transportation (2020) from the University of Melbourne and her Masters (in Research) from the Indian Institute of Technology Kharagpur in Information Technology (2013). She worked in Tata Consultancy Services Innovation Lab, India, for three years as a researcher. Her main research interests are intelligent transportation systems, machine learning, connected and autonomous vehicles, transportation planning, and shared mobility.

Her current research is on modular, autonomous pods (vehicles) that can physically join while traveling to allow an en-route transfer. She is using model-free Reinforcement Learning based approach to represent the pod’s mobility. The work aims to analyse pods’ mobility service in the simulation environment and compare it with private transport (taxi) service and transfer-free ridesharing (DRT) service.

We wish her a fun and productive time during her stay with us! 😊

New member in our group: welcome Xiaoyi!

Xiaoyi Wu recently joined our group as a Ph.D. student for the DREMTS project(Demand-Responsive Electrified Multi-modal Transit Systems), a collaborative initiative between DTU and KTH under the DTU Alliance partnership of the Nordic Five Tech.

Her research will focus on developing novel behavior predictive algorithms and integrating them into new demand management schemes for next-generation transportation systems. She will be working under the supervision of professors Carlos Lima Azevedo and Filipe Rodrigue.
Xiaoyi has graduated from the University of Pennsylvania with a Master of Urban Spatial Analytics degree.

We wish her a fun and productive time during her stay with us! 😊

New member in our group: welcome Ricardo!

Ricardo Daziano recently joined our group as a Guest Professor from Cornell University as part of DTU Management visiting scholar program. He is hosted by Assistant Professor Rico Krueger.

Ricardo’s research focuses on engineering decision making, specifically on theoretical and applied econometrics of consumer behavior and discrete choice models applied to technological innovation in transportation and energy. His specific empirical research interests include the analysis of air travel demand, the study of pro-environmental preferences toward low-emission vehicles, modeling the adoption of sustainable travel behavior, estimating willingness-to-pay for renewable energy, and forecasting consumers’ response to environmentally-friendly energy sources.

We wish him a fun and productive time during his stay with us! 😊

New Ph.D. graduation in our group: congrats Renming!

On March 14th, 2023, Renming Liu successfully defended his Ph.D. thesis entitled “Design, Optimization and Simulation of Tradable Mobility Credit”.

Congratulations, Renming!

MLSM Group at TRB 2023!

Members of our MLSM group attended the 102^nd Transportation Research Board Annual Meeting (TRB 2023) in Washington D.C. from 8-12 January 2023. Three interesting papers were presented and Christoffer Riis had a talk on “Using Computer Vision to Register Patterns of Bicycle Helmet Use “. Check out below for the full list of papers.

MLSM Group at TRB 2023!

The 102^nd Transportation Research Board Annual Meeting (TRB 2023) will be held held in person, January 8–12, 2023 in Washington, D.C. Our group will contribute with three interesting papers and a talk by Christoffer Riis. Check out below for more details.

MLSM at NeurIPS!

The 36th conference on Neural Information Processing Systems (NeurIPS) will be held in New Orleans from November 28th to December 9th.

Our group will be presenting an interesting paper entitled “Bayesian Active Learning with Fully Bayesian Gaussian Processes“. In this paper, we exploit the bias-variance trade-off inherent in a Gaussian process’ hyperparameters to design two new active learning acquisition functions: Bayesian Query-by-Committee and Query-by Mixture of Gaussian Processes. For six simulators, we improve the active learning performance by 12%! We will use these insights to efficiently analyze the effects of policies in traffic simulators, leading to greener aviation traffic 🌱✈.

Check below for more details!