Transportation mode inference using environmental constraints

Abstract

Analysis of transportation mode used by tourists in touristic destination areas provides basic information of tourism policy making for local governments or marketing strategy making for the tourism industry. With the technical advances of tracking devices, GPS supported smartphones sense the movement of tourists, and generate a large volumes of data which show tourists' trajectory data. Because GPS trajectory data has only latitudes, longitude and time, transportation modes should be inferred by any methods. Some researchers infer transportation modes from velocity of tourists by using machine learning like Support Vector Machine (SVM) and Conditional Random Field (CRF). However, because trains and buses temporarily stop at stations or bus stops, respectively, when movement is slow, the transportation mode can not be inferred correctly only from velocity. The locations where trains and buses temporarily stop are generally known in advance. Therefore, the transportation mode can be correctly inferred by using such location data as environmental constraints.In this research, we propose a new transportation mode inference method using environmental constraints. We assume that tourists move by foot or public transportation in the large-size touristic destinations which include many touristic spots.