Brief description: 

The QROWD Modal Split toolkit is a disruptive solution to generate dynamic Modal Split (MS) indicators. MS is a globally accepted method to assess patterns of citizens´ usage of the different transport (public and private) modes (car, bus, metro, bike, etc) available in a city/urban agglomeration. But obtaining the data needed for MS is costly, inaccurate and cumbersome, hampering the possibilities of leveraging its value.

The QROWD enabled MS toolkit allows city management to run travel surveys using citizen's mobile phones instead of traditional telephone interviewing or paper surveys. This means shifting from expensive, limited, years old static data to up-to -date cost-efficient data driven decision making, simulations, what-if analysis and policy formulation. Its systematic and timely usage generates disruptive positive changes in traffic management.

The QROWD toolkit integrates a mobile app for citizen sensing & crowdsourcing, gamification features for citizen engagement, purposeful analysis enhanced by big data and ML techniques and visualization tools to deliver easy-to-use MS outputs.

Main Features: 
  • Starting from citizen sensing using the (previously developed by the University of Trento) iLog app, applying AI and ML on Big Data and validating through questions, MS is calculated through advanced data analysis and shown on dashboards used by city staff
  • The iLog is a smartphone app developed by the University of Trento used for people-centric sensing, collecting sensor data from engaged citizens in both active and passive way and putting citizens "in-the-loop" for validation and curation of their own data (or collectively generated by them). iLog can be used to integrate machine analytics with user contributions by connecting with the citizens to detect MS input data
  • Unobtrusive sensing: not interfering with telephone user experience, low battery usage and screen free app
  • State-of-Art Privacy model: GDPR by design; User data is stored and processed anonymously through a unique identifier generated randomly when the user registers on iLog (a disambiguation table allows to retrieve the user identified, when needed); minimized data collection:  the citizen email (identifier) and only sensor data for mobility (GPS, gyroscope and accelerometer); All the raw data are stored for a limited amount of time
Areas of Application: 

Smart Cities; Urban mobility, Transport

Market Trends and Opportunities: 

Modal Split is a consolidated indicator use by most of big cities for decades. Typical constraints in using the conventional tools for calculating Modal Split: time-consuming, cumbersome, quite invasive (daily trip recordings by citizens), costly and not replicable on short term- recurrent basis. Render general results (e.g. on statistical groupings)

Customer Benefits: 
  • Allows city management to connect with the citizens, to better understand their behaviour, needs and routines, how the citizens move, how they interact with the city and its infrastructure
  • MS can be calculated more frequently and accurately, in less time and involving lower costs. Enables dynamic What if analysis to simulate impact of different mobility policy scenarios
Technological novelty: 
  • i-Log collects streams of big personal data in an unobtrusive, privacy compliant and efficient way.
  • Obtaining information about citizens` modal split by collecting their mobile data and asking questions about these data to improve the overall accuracy, allowing integrated real-time information on traffic and multimodal transport.
Component / Service / App


Università degli Studi di Trento
BDV Reference categories: 
Data Analytics
Data Management
Data Visualisation and Interaction
Urban Mobility
Readiness Level: 
Modal Split
transport modes