The Diversity and Scale Matter: Ubiquitous Transportation Mode Detection using Single Cell Tower Information

Abstract

Detecting the transportation mode of a user is important for a wide range of applications. While a number of recent systems addressed the transportation mode detection problem using the ubiquitous mobile phones, these studies either leverage GPS, the inertial sensors, and/or multiple cell towers information. However, these different phone sensors have high energy consumption, limited to a small subset of phones (e.g. high-end phones or phones that support neighbouring cell tower information), cannot work in certain areas (e.g. inside tunnels for GPS), and/or work only from the user side. In this paper, we present a transportation mode detection system, MonoSense, that leverages the phone serving cell information only. The basic idea is that the phone speed can be correlated with features extracted from both the serving cell tower ID and the received signal strength from it. To achieve high detection accuracy with this limited information, MonoSense leverages diversity along multiple axes to extract novel features. Specifically, MonoSense extracts features from both the time and frequency domain information available from the serving cell tower over different sliding widow sizes. More importantly, we show also that both the logarithmic and linear RSS scales can provide different information about the movement of a phone, further enriching the feature space and leading to higher accuracy. Evaluation of MonoSense using 135 hours of cellular traces covering 485 km and collected by four users using different Android phones shows that it can achieve an average precision and recall of 89.26% and 89.84% respectively in differentiating between the stationary, walking, and driving modes using only the serving cell tower information, highlighting MonoSense ability to enable a wide set of intelligent transportation applications.