Shone, Fred;
Hillel, Tim;
(2025)
Activity Based Modelling with Deep Conditional Generation.
In:
Proceedings of 13th Symposium of the European Association for Research in Transportation 2025.
(pp. pp. 1-12).
hEART
Preview |
Text
hEART_2025_shortpaper_13.pdf - Published Version Download (687kB) | Preview |
Abstract
Modelling human activity scheduling is a challenging task at the core of activity-based modelling. Existing approaches to activity scheduling are increasingly expensive and slow to develop, and can also produce unrealistically homogenous outputs, failing to model the real diversity in human behaviours. We contribute a novel methodology combining a deep generative model with conditionality, such that the model can be used in an activity modelling or transport simulation based framework. By explicitly and simultaneously modelling variation of observed activity schedules, we better represent real diversity. Our experimental results demonstrate that our approach is both cheaper and faster than existing activity scheduling solutions, whilst still providing closely tailored and high quality outputs.
| Type: | Proceedings paper |
|---|---|
| Title: | Activity Based Modelling with Deep Conditional Generation |
| Event: | hEART 2025: 13th Symposium of the European Association for Research in Transportation |
| Location: | Munich, Germany |
| Dates: | 10th-12th June 2025 |
| Open access status: | An open access version is available from UCL Discovery |
| Publisher version: | https://transp-or.epfl.ch/heart/2025.php |
| Language: | English |
| Additional information: | This version is the version of record. For information on re-use, please refer to the publisher's terms and conditions. |
| Keywords: | Activity Based Modelling, Choice Modelling, Deep Generative Machine Learning |
| UCL classification: | UCL UCL > Provost and Vice Provost Offices > UCL BEAMS UCL > Provost and Vice Provost Offices > UCL BEAMS > Faculty of Engineering Science > Dept of Civil, Environ and Geomatic Eng |
| URI: | https://discovery.ucl.ac.uk/id/eprint/10215191 |
Archive Staff Only
 |
View Item |
