Travel mode detection method based on big smartphone global positioning system tracking data

Abstract

This article proposes a machine learning–based travel mode detection method using urban residents’ travel routes as the data source, collected via smartphone global positioning system modules. A data-driven machine learning strategy was chosen in the model construction. This study performed data cleaning and mining on over 4400 pieces of urban resident travel records containing several millions of global positioning system tracking points. Series of characteristic values of speed, travel distance, and direction are calculated, which reflect the travel mode of smartphone holders. In travel mode identification, first, the transition regions of travel segments of different travel modes are effectively distinguished; then, continuous tracking points for single-mode travel are connected into single-mode travel segments. The travel mode of the surveyed subjects is identified based on the calculated features of average speed, average acceleration, and average change of direction within each single-mode segment. The random forest method is chosen as the basis model to classify travel mode. Three-quarters of the travel records were used to construct the random forest classifier, and the detection accuracy of the established model for the remaining ¼ of the travel record reached 94.4%. The proposed method uses massive smartphone global positioning system tracking points as the basis; the detection results are consistent with manually collected prompted recall survey records.