Enhanced Transport Mode Recognition on Mobile Devices

ANDERS SKRETTING; TOR-MORTEN GRØNLI; TIM A. MAJCHRZAK; CRISTIAN MATEOS; HIRSCH, MATÍAS

Hawaii

Conferencia; 57th Hawaii International Conference on System Sciences; 2024

University of Hawai?i at Manoa

Establishing the context of users of mobileapplications is essential to provide the users with relevantinformation and functionality associated with the user’slocation or situation. Context aware solutions adaptits behaviour to fit the situation the user is situated inby making certain information or functions available.They are applicable to most kinds of modern systems;public transportation systems are no exception. Toachieve intelligent transportation, it is vital to determinecontextual information related to travelers, such as whichvehicle is currently used and where the travelers boardedor disembarked. This contributes towards more seamlesspublic transport ticketing and provides public transportoperators with enriched data. In this paper, we suggestan approach, using machine learning, to determine atraveler’s mode of transport using mobile sensor datafrom the traveler’s smartphone. The trained machinelearning models can infer the mode of transport withhigh accuracy using off-the-shelf technology