Abstract

ArcGIS Machine Learning Classification of Travel Mode in GPS Data
Track: Community Planning and Economic Development
Authors: Dara Seidl

To reduce respondent burden in travel behavior surveys, travel characteristics may be automatically detected from GPS data. One such attribute is mode, which requires accurate classification of travel by automobile, bus, bicycle, train, or foot, without the ground truth of participant-reported data. With GPS data collected from a sample in the United States, this study examines the feasibility of integrating machine learning algorithms in ArcGIS to automate the classification of travel mode.