Making pervasive sensing possible: Effective travel mode sensing based on smartphones

Abstract

Smartphones with embedded Global Positioning Systems (GPS) sensors and accelerometers provide outstanding opportunities to gather information about transportation modes. In comparison to traditional approaches of measuring travel behavior, such as self-reports and travel behavior surveys, a smartphone application that tracks movement increases spatiotemporal resolution and reduces the burden on individuals to manually recall and log travel behavior. Studies using smartphones to detect travel modes mainly use segmentation approaches, which divide movement data into single-mode segments. These approaches hinge on the accurate detection of transitional nodes, which are occasionally difficult to identify. In this study, we proposed a method to detect travel modes based on the chained random forest (RF) model, which automatically classifies smartphone data into different travel modes without using a prior search for transitional nodes. We evaluated the proposed method by collecting and analyzing 12 people's travel behavior spanning six days. The proposed method achieved 93.8% overall accuracy and performed well in both indoor and outdoor environments. This travel mode detection model offers potentials in conducting pervasive sensing, which will eventually benefit many areas of research that require large scale travel behavior monitoring.