DCM-ARD is a bayesian ARD approach for automatically determining an optimal utility function specification in Discrete Choice Models (DCMs) from an exponentially large set of possible specifications in a purely data-driven manner, as proposed in the paper:

• Rodrigues, F., Ortelli, N., Bierlaire, M., Pereira, F. Bayesian Automatic Relevance Determination for Utility Function Specification in Discrete Choice Models. ArXiv 2019.
  

Download (GitHub)

SimMobility is an integrated mobility simulation platform that comprehensively simulates Future Mobility scenarios by integrating long, medium, and short-term travel behavior. Various mobility-sensitive behavioral models are integrated within the state-of-the-art scalable simulators to predict the impact of mobility demands on transportation networks, intelligent transportation services and vehicular emissions. The platform simulates the effects of a portfolio of technology, policy and investment options under alternative future scenarios. SimMobility encompasses the modeling of millions of agents, including pedestrians, drivers, phones, traffic lights, GPS, cars, buses, and trains, from second-by-second to year-by-year simulations and across countries. Its development is ongoing by the Intelligent Transportation System Lab at the Massachusetts Institute of Technology (MIT) and the Singapore-MIT Alliance for Research and Technology (SMART).

For more information and for citation purposes, please refer to the following paper:

• Adnan, M., Pereira, F.C., Azevedo, C.M.L., Basak, K., Lovric, M., Raveau, S., Zhu, Y., Ferreira, J., Zegras, C. and Ben-Akiva, M., 2016. Simmobility: A multi-scale integrated agent-based simulation platform. In 95th Annual Meeting of the Transportation Research Board Forthcoming in Transportation Research Record.
  

Download (GitHub)

A neural network layer that enables training of deep neural networks directly from crowdsourced labels (e.g. from Amazon Mechanical Turk) or, more generally, labels from multiple annotators with different biases and levels of expertise, as proposed in the paper:

• Rodrigues, F. and Pereira, F. Deep Learning from Crowds. In Proc. of the Thirty-Second AAAI Conference on Artificial Intelligence (AAAI-18).
  

Download Source Code

Related Datasets

• LabelMe (multi-class classification; annotations from Amazon Mechanical Turk)
• MovieReviews (regression; annotations from Amazon Mechanical Turk)
• 2003 CONLL NER task (sequence labelling; annotations from Amazon Mechanical Turk)

Deep joint mean and quantile regression for spatio-temporal problems, as proposed in the paper:

• Rodrigues, F. and Pereira, F.C., 2018. Beyond expectation: Deep joint mean and quantile regression for spatio-temporal problems. arXiv:1808.08798

Download Source Code

A deep learning approach for combining time-series and textual data for taxi demand prediction in event areas.

This code reproduces the experiments in the paper:

• Rodrigues, F. and Markou, I. and Pereira, F. C. Combining time-series and textual data for taxi demand prediction in event areas: a deep learning approach. In Information Fusion, Elsevier, 2018.

Download Source Code