Prediction of occupation of public transport

Exheus, a new spin-off that analyses gene expression via artificial intelligence, to optimise performance, health and nutrition
July 1, 2020
A UPC group and B. Braun investigate new inactivation strategies against SARS-CoV-2 virus through functionalized nanoparticles and activation of heat nanosources
June 28, 2020

The inLab FIB has participated in the development of a system to characterise and model passenger demand on buses. Specifically, it has developed a module for predicting occupation that has been integrated into the application of the Autocorb company, which operates urban and interurban lines in the Barcelona Metropolitan Area. The app enables users to check the estimated occupation of buses throughout the day. The aim is for users to be able to choose the emptiest buses, so that service supply and demand can be balanced. In the context of the COVID-19 health service, this will help to reduce crowds on buses.


The algorithms are based on data-driven methodologies drawn from a wide range of sources (ticketing, the schedule and bus cameras). Classical methods for processing time series have been incorporated into the prediction module. These include the ARIMA method and neural network algorithms that enable important variables such as the school calendar to be included in the occupation time series.

The new functionality is integrated within the Intelibus ecosystem of tools, a real-time information system in the passenger transport system, which uses GPS positions of buses and the ticketing system to provide useful information for public transport users and the service operator.

Testing of the beta version of the app began on 11 May and is available for Android (on Play Store) and iOS devices.

Related Projects