Skip to content

M.Sc. Thesis Defense: Peter Braun

Wednesday, 21st March 2018 11:00 am
Where: E2-528 EITC

Title: Transportation Mode Classification


The increasing amount of digital data in urban research has led to urban data mining. In urban research (e.g., travel studies in urban areas), researchers—who conduct paper- and telephone-based travel surveys—often collect biased and inaccurate data about their participants' movements. Although the use of GPS trackers in travel studies improve the accuracy of exact participant trip tracking, the challenge of labelling trip purpose and transportation mode still persists. The automation of such a task is expected to benefit travel studies and other applications that rely on contextual knowledge (e.g., current travel mode of a person). In my M.Sc. thesis work, I focus on urban data mining, which aims to extract implicit, previously unknown and potentially useful information from a large amount of urban data (e.g., movement data). Based on people's movements tracked by GPS and accelerometers, augmented with GIS data, I manage to extract the transportation modes people use in an urban area. I also design and implement a new system to classify transportation modes of trip sub-segments based on Dwell Time History and a Window History Queue, which uses previously encountered data to increase the classification accuracy of the processed data. By exploring the performance of classifiers by training with different combinations of GPS-, accelerometer- and GIS data, the resulting system remains as a semi real-time classification system but achieves a high classification accuracy of 98.5%.

Complete Seminar List
© 2011 University of Manitoba Department of Computer Science
Back to top