Pseudorange-Based Multi-Modal Transport Classification with Raw GNSS Android Data

Multi-modal transport refers to multiple transportation means (e.g., car, plane) that can be used to transport people or goods. Classifying the mode of transportation can have multiple usages towards sustainable transport solutions, such as optimizing routes, reducing transit times, having efficient logistics operations, reducing transportation costs by strategically combining different modes, or understanding how people move within cities for migration studies. Multi-modal transport classification has traditionally relied on data collected from various movement sensors (e.g., accelerometers, pedometers, gyroscopes); yet, with the opening of the access to raw Global Navigation Satellite Systems (GNSS) data on mobile devices, new avenues of multi-modal analysis have been created, when GNSS signals alone (without additional sensors) could be used to classify the mode of transport. This paper introduces a novel pseudorangebased approach for multi-modal transport classification, where only the instantaneous raw navigation data from two strong satellites in view is used to classify the user transportation mode at that instant. We validate our concept based on Machine Learning (ML) algorithms with data collected with four Android devices (three smartphones and a smartwatch) in 24 scenarios, encompassing five different transportation modes.