Background
The project ‘SINUS’ (Sensor Integration for Urban Risk Prediction) explores the feasibility of matching wearable physiological sensors with data interfaces of urban data ecosystems for improving the current state of the art of predicting risk patterns for vulnerable road users in urban road networks.
Methods
By establishing semantic interoperability of different, formerly isolated data sources, and their integration in a common big data lake, machine learning algorithms are applied, refined and trained. This paves the way for predictions of occurring safety risks for observed standard situations with high spatio-temporal resolution in an urban road network.
Results
The information could be used in a wide variety of ICT-supported application scenarios, such as transportation management, public safety planning, crowd management, health monitoring, digital mobility services or city planning. As a proof-of-concept, two ICT-supported information applications are implemented and evaluated.