Activity recognition for smartphone based travel surveys based on cross-user history data



In transport modeling and prediction, trip purpose plays an important role. The most particular case is activity-based modeling, whereby mobility choices (e.g. mode, path, departure time) are made in order to carry out specific activities. A current challenge, however, lies on getting appropriate data that relates observed trips with their purpose.
Recently, a smartphone-based travel survey (the Future Mobility Survey, FMS) was run in Singapore that collected location data from nearly 800 participants overall. Users ran FMS permanently during at least 14 days and tagged at least 5 of them. This dataset presents diverse opportunities in terms of developing machine learning models for the future versions of FMS, where the tagging process is more intelligent and easier to use (e.g. having pre-filled activities associated to the user traces).
This paper proposes a learning model that, given an identified stop, predicts the most likely activity associated to it. Our data often contains errors or noise due to limited functionality of physical sensors in a dense area, and human’s mistakes in the tagging process. To alleviate this effect, we generate heterogeneous features by different spatial quantization techniques and apply ensemble learning for a good generalization performance.


Pattern recognition, ensemble models, smartphone data


Actvity recognition from personal location data


22nd International Conference on Pattern Recognition (ICPR 2014), August 2014

Cited by

No citations found