COMMIT
Context-Aware Mobility Mining Tools
Abstract
The research project developed innovative methods for mobility data analysis and integrating mobility data with spatio-temporal context. Particularly, methods targeting mining mobility patterns, integrating mobility data with context data, enhancing tracking data quality, and visualizing mobility data are developed.
These methods are tested using multiple large-scale mobility data sets, including long-term GPS tracking data collected through the GoEco! and SBB Green Class projects and other publicly available data sets such as the GeoLife data set. The successful application of the developed methods on large-scale real-world mobility data sets demonstrates the generalizability and reusability of these methods.
As a major outcome of the project, an open source Python library, trackintel, is published that includes the core functional modules developed throughout the research project. Besides trackintel, multiple research papers and Ph.D./MSc/BSc theses are published under partial or full support of the COMMIT project.
People
Collaborators
description
Problem:
Current methods for mining movement trajectories in order to analyze our mobility behavior
- omit the movement’s context (e.g., weather, environment);
- focus on the status quo of mobility behavior rather than its dynamic change (e.g., as reaction to new mobility options).
Solution:
We aim to develop generalizable and reusable methods for the integration of movement trajectories from various sources with spatio-temporal context data and for knowledge discovery from such semantically enriched, longitudinal data.
Impact:
Understanding human mobility is highly significant for numerous disciplines as well as for society as a whole, working towards the goal of increasing its sustainability. An open-source analysis framework for movement data will be of use to researchers from a variety of disciplines.
Presentation
Gallery
Annexe
Publications
- Hong, Ye, Yanan Xin, Henry Martin, Dominik Bucher, and Martin Raubal. “A clustering-based framework for individual travel behaviour change detection.” 11th International Conference on Geographic Information Science (GIScience), 2021 (in print).
- Zhao, Pengxiang, David Jonietz, and Martin Raubal. "Applying frequent-pattern mining and time geography to impute gaps in smartphone-based human-movement data." International Journal of Geographical Information Science, 2021: 1-29.
- Martin, Henry, et al. "Graph-ResNets for short-term traffic forecasts in almost unknown cities." NeurIPS 2019 Competition and Demonstration Track. PMLR, 2020.
- Bucher, Dominik, Henry Martin, David Jonietz, Martin Raubal, and René Westerholt. "Estimation of Moran’s I in the Context of Uncertain Mobile Sensor Measurements." 11th International Conference on Geographic Information Science (GIScience), Leibniz International Proceedings in Informatics, LIPIcs 177, 2021.
- Martin, Henry, Ye Hong, Dominik Bucher, Christian Rupprecht, and René Buffat. "Traffic4cast-Traffic Map Movie Forecasting--Team MIE-Lab." arXiv preprint arXiv:1910.13824, 2019.
- Zhao, Pengxiang, Dominik Bucher, Henry Martin, and Martin Raubal. "A clustering-based framework for understanding individuals’ travel mode choice behavior." 22nd Conference on Geographic Information Science (AGILE 2019), Limassol, Cyprus, pp.77-94, Cham: Springer, June 17-20, 2019.
- Martin, Henry, Dominik Bucher, Esra Suel, Pengxiang Zhao, Fernando Perez-Cruz, and Martin Raubal. "Graph convolutional neural networks for human activity purpose imputation from GPSbased trajectory data." Modeling and Decision-Making in the Spatiotemporal Domain (Workshop at the Thirty-Second Conference on Neural Information Processing Systems NIPS), Montreal, Canada, 2018.
- Urner, Jorim, Dominik Bucher, Jing Yang, and David Jonietz. "Assessing the influence of spatiotemporal context for next place prediction using different machine learning approaches." ISPRS International Journal of Geo-Information 7, no. 5 (2018): 166.
Additional resources
Bibliography
Publications
Related Pages
- Trackintel: An open-source python library for human mobility modeling and analysis. In GeoPython 2021 (online). GitHub - mie-lab/trackintel: trackintel is a framework for spatio-temporal analysis of movement trajectory and mobility data.
More projects
IRMA
FLBI
STIMO
VOCIM
News
Latest news
Smartair | An active learning algorithm for real-time acquisition and regression of flow field data
Smartair | An active learning algorithm for real-time acquisition and regression of flow field data
The Promise of AI in Pharmaceutical Manufacturing
The Promise of AI in Pharmaceutical Manufacturing
Efficient and scalable graph generation through iterative local expansion
Efficient and scalable graph generation through iterative local expansion
Contact us
Let’s talk Data Science
Do you need our services or expertise?
Contact us for your next Data Science project!