Modelling the Changing Surroundings of Everyday Life
Understanding travel behaviour and travel demand is of constant importance to transportation communities and agencies in every country. Modelling this kind of activity on the aggregate scale is very important for applications like measuring time expenditures and quality of life, tourist activity and environmental issues. Nowadays, attempts have been made to automatically infer transportation modes from positional data, such as the data collected by using GPS devices so that the cost in time and budget of conventional travel diary survey could be significantly reduced. Some limitations, however, exist in the literature, in aspects of data collection (sample size selected, duration of study, granularity of data), selection of variables (or combination of variables), and method of inference (the number of transportation modes to be used in the learning).
This project aims to fully understand these aspects in the process of inference. The work attempts to solve a classification problem of GPS data into different transportation modes (car, walk, cycle, underground, train and bus). We first study the variables that could contribute positively to this classification, and statistically quantify their discriminatory power. We then introduce a novel approach to carry out this inference using a framework based on Support Vector Machines (SVM) classification. We then apply segmentation strategies to identify significant stops that occurred along a person’s track such as home, work, etc. The classification then is subjected to a network matching process that checks whether the identified modes follow their corresponding transport networks to verify the final classification. This project is sponsored by u-blox and EPSRC.
- For more information about this project please contact Professor Tao Cheng
(tao [dot] cheng [at] ucl.ac.uk)
Page last modified on 28 oct 12 07:21