Spatial context mining approach for transport mode recognition from mobile sensed big data

Knowledge about what transport mode people use is important information of any mobility or travel behaviour research. With ubiquitous presence of smartphones, and its sensing possibilities, new opportunities to infer transport mode from movement data are appearing. In this paper we investigate the role of spatial context of human movements in inferring transport mode from mobile sensed data. For this we use data collected from more than 8000 participants over a period of four months, in combination with freely available geographical information. We develop a support vectors machines-based model to infer five transport modes and achieve success rate of 94%. The developed model is applicable across different mobile sensed data, as it is independent on the integration of additional sensors in the device itself. Furthermore, suggested approach is robust, as it strongly relies on pre-processed data, which makes it applicable for big data implementations in (smart) cities and other data-driven mobility platforms.