× This challenge is awaiting approval from an organizer.

Computational Movement Analysis

Uncertainty quantification and out-of-distribution detection using surjective normalizing flows

⛶  Fullscreen ↓  Download 📂 Demo

Dr. Yanan Xin, who leads the Mobility Information Engineering (MIE) Lab, presented a talk at DINAcon 2023 titled Computational Movement Analysis for Sustainable and Intelligent Mobility.

The transport sector is currently experiencing a rapid transformation fueled by disruptive mobility technologies aimed at providing sustainable and intelligent mobility services. To effectively harness the potential of these technologies, it is crucial to gain a deep understanding of human mobility patterns and develop innovative computational methods to analyze vast amounts of mobility data. In this presentation, Dr. Xin will showcase the research conducted at the Mobility Information Engineering Lab on facilitating the adoption of shared electric vehicles and developing casually-enabled interpretable and robust machine learning methods for mobility data analysis.

{ hacknight challenges }

(( a quick challenge for someone to take their first steps as a user... ))

(( something that one could do once familiar with the project... ))

(( a challenge for the coders and pro users in the room... ))

Uncertainty quantification for mobility analysis

ci arXiv


This repository contains library code for training a surjective normalizing flow for out-of-distribution detection using epistemic uncertainty estimates.


To install the latest GitHub , just call the following on the command line:

pip install git+https://github.com/irmlma/uncertainty-quantification-for-mobility-analysis@<TAG>

This installs the library as well as executables in your current (virtual) environment.


Having installed as described above you can train and make predictions using the provided exectuables.

Train the model using the provided config file via:

    --config=configs/config.py \
    --infile=<FILE> \

where is a COMMA-separated file of numerical values which correspond to the features obtained from transforming inputs through a neural network that has residual connections and was trained using spectral-normalization and is some file to which parameters are written (see Dirmeier et al. (2023)).

To make predictions for epistemic uncertainty estimates, call:

    --params=<PARAMS_FILE> \
    --infile=<FILE> \

where is the same file as before, is a features file and is a file where results are written to.


If you find our work relevant to your research, please consider citing

  title={Uncertainty quantification and out-of-distribution detection using surjective normalizing flows},
  author={Simon Dirmeier and Ye Hong and Yanan Xin and Fernando Perez-Cruz},
  journal={arXiv preprint arXiv:2311.00377}


Simon Dirmeier sfyrbnd @ pm me

This content is a preview from an external site.

Event finished

Event started

Repository updated

23.11.2023 10:44 ~ loleg

First post View challenge

23.11.2023 10:44 ~ loleg


All attendees, sponsors, partners, volunteers and staff at our hackathon are required to agree with the Hack Code of Conduct. Organisers will enforce this code throughout the event. We expect cooperation from all participants to ensure a safe environment for everybody.

Creative Commons LicenceThe contents of this website, unless otherwise stated, are licensed under a Creative Commons Attribution 4.0 International License.