COMMIT

Context-Aware Mobility Mining Tools

Started

January 10, 2018

Status

Completed

Share this project

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

PI | Partners:

ETH Zurich, Geoinformation Engineering:

Prof. Martin Raubal

More info

‍

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

Download Presentation



Gallery

Annexe

Additional resources

—



Bibliography

Publications



Hong, Y.; Xin, Y.; Martin, H.; Bucher, D.; Raubal, M.; Janowicz, K.; Verstegen, J. A. "A Clustering-Based Framework for Individual Travel Behaviour Change Detection" LIPIcs, Volume 208, GIScience 2021 208 4:1-4:15 2021 View publication 



Zhao, P.; Jonietz, D.; Raubal, M. "Applying frequent-pattern mining and time geography to impute gaps in smartphone-based human-movement data" International Journal of Geographical Information Science 35 11 2187-2215 2021 View publication 



Martin, H.; Bucher, D.; Hong, Y.; Buffat, R.; Rupprecht, C.; Raubal, M.; Escalante, H. J.; Hadsell, R. "Graph-ResNets for short-term traffic forecasts in almost unknown cities" Proceedings of the NeurIPS 2019 Competition and Demonstration Track 123 153–163 2020 View publication 



Bucher, D.; Martin, H.; Jonietz, D.; Raubal, M.; Westerholt, R.; Janowicz, K.; Verstegen, J. A. "Estimation of Moran’s I in the Context of Uncertain Mobile Sensor Measurements" LIPIcs, Volume 177, GIScience 2021 177 2:1-2:15 2020 View publication 

Zhao, P.; Bucher, D.; Martin, H.; Raubal, M. "A Clustering-Based Framework for Understanding Individuals’ Travel Mode Choice Behavior" 77-94 2020 View publication 



Martin, H.; Hong, Y.; Bucher, D.; Rupprecht, C.; Buffat, R. "Traffic4cast-Traffic Map Movie Forecasting -- Team MIE-Lab" Preprint 2019 View publication 



Urner, J.; Bucher, D.; Yang, J.; Jonietz, D. "Assessing the Influence of Spatio-Temporal Context for Next Place Prediction using Different Machine Learning Approaches" ISPRS International Journal of Geo-Information 7 5 166 2018 View publication 



Martin, H.; Bucher, D.; Suel, E.; Zhao, P.; Perez-Cruz, F.; Raubal, M. "Graph Convolutional Neural Networks for Human Activity Purpose Imputation" NIPS 2018 Spatiotemporal Workshop 2018 View publication 