A supervised learning approach for transport mode detection using GPS tracking data

The fast development in telecommunication is producing a huge amount of data related to how people move and behave over time. Nowadays, travel data are mainly collected through Global Positioning Systems (GPS) and can be used to identify human mobility patterns and travel behaviors. Transport mode detection (TMD) aims to identify the means of transport used by an individual and is a field that has become more popular in recent years as it can be beneficial for various applications. However, developing travel models requires different types of information that can be extracted from raw travel data. Although many useful features like speed, acceleration and bearing rate can be extracted from raw GPS data, detecting transport modes requires further processing. Some previous studies have successfully applied machine learning algorithms for detecting the transport mode. Despite achieving high performance in their models, many of these studies have used rather small datasets generated from a limited number of users or identified a small number of different transport modes. Furthermore, in most of these studies more complex methodologies have been applied, where extra information like GIS layers or road and railway networks were required. The purpose of this study is to propose a simple supervised learning model to identify five common transport modes on large datasets by only using raw GPS data. In total, six commonly used supervised learning algorithms are tested on seven selected features (extracted from raw GPS data). The Random Forest (RF) algorithm proves to perform better in detecting five transport modes from the dataset utilized in this study, with an overall accuracy of 82.7%