Enhanced Transport Mode Recognition on Mobile Devices [Qualis A1]

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

Hawaii

Conferencia; 2024 Hawaii International Conference on System Sciences (HICSS-57); 2024

University of Hawaii

Establishing the context of users of mobile applications is essential in order to provide the users with relevant information and functionality associated with the user´s location or situation. Context aware solutions are able to adapt its behaviour to better fit the situation the user is situated in by making certain information or functions available. Context aware solutions are applicable to most kinds of modern systems and public transportation systems are no exception. In order to achieve intelligent transportation solutions it is vital to determine contextual information related to travelers, such as which vehicle a traveler is currently using, where the travelers boarded or where they disembarked. This information can contribute towards a more seamless public transport ticketing solution, in addition to providing public transport operators, and other stakeholders, with enriched data that can be used in decision-making processes. In this paper, we suggest an approach, using machine learning, to determine a traveler´s mode of transport using mobile sensor data from the traveler´s smartphone. The trained machine learning models are able to infer the mode of transport with high accuracy, without the need for any additional equipment, using off-the-shelf technology.