QROWD will participate in Smart City Expo World Congress in Barcelona 2018 with an Elevator Pitch: A smart solution to calculate the Modal Split – the case of Trento
The city of Trento, currently participating in the QROWD project, has continuously ranked high since 2014, when it was selected as an IEEE core smart city. Located in a narrow valley and divided by a railway, a river, and a motorway, Trento has committed to deploy smarter mobility solutions to improve mobility for residents and visitors. The Modal Split has been identified as the most appropriate tool to gather useful insights on the percentage share of each type of transport in the total inland transport.
Citizens’ mobility habits have been detected in Trento for the past fifteen years. However, calculating the modal split can be a daunting task, and employing traditional methods can prove costly and time-consuming.
By participating in the QROWD project, Trento has developed a novel method to gather information about daily movements putting people in the loop. This includes novel types of data collection: big and open static data are integrated with data coming from citizens. Citizen sensing (collection of sensor data through a specific app) is then complemented by machine learning techniques to quicken the whole process. Flanking this new approach is, of course, a concern for transparency in data processing and, against this backdrop, gamification strategies are developed to encourage data sharing providing added value to the process. Then, the usefulness of raw data is enhanced by ad hoc analytics based on specific parameters: type and occupation of users, purpose of a trip and multimodality of transport, and selection of a typical working day during school terms. Finally, visualization of data in a readable manner fosters deeper knowledge about movements occurring on the territory, thus enhancing the decision-making process.
Crowdsensing and crowdsourcing techniques are employed: a mobile application collects sensor data from citizens’ smartphones and validates them through Artificial Intelligence techniques and manual feedback.
The unlocking and integration of dissimilar data sources together with a more accurate, more frequent and less costly computation of the Modal Split are prominent benefits of this approach.
Currently at its testing phase, this innovative solution will allow more reliable computation of the modal split, leveraging alternative data sources, covering a more representative sample size and collecting data more frequently. It will allow local administrations to understand how mobility occurs in Trento, and therefore assess the impact of past policies and think of new ways to tackle the most urgent mobility issues.
This smart solution to calculate the modal split in Trento can spread into a standardized solution for the computation of the modal split which is scalable and applicable in different contexts regardless of the differences in the mobility and transport situation.