AI applications using Open Road Crash data
How might we leverage road crash statistics and multi-agent AI-based web applications to enhance road safety and inform policy making?
Go to Challenge | 13 teams have entered this challenge.
Team Centelon
CityCent is a revolutionary mobile application designed to enhance road safety in urban environments by connecting communities and authorities through real-time data and collaborative features.
Key Features:
Benefits:
Target Audience:
CityCent envisions a future where cities are safer, more efficient, and more livable for everyone.
Road safety remains a critical concern globally, with millions of accidents occurring globally every year. We set out to address this challenge by analyzing a government-provided road accident dataset. Our exploratory analysis revealed patterns—such as accidents being more frequent during certain times, under specific road conditions, and at high-risk locations.
However, data alone wasn’t enough. We integrated real-time traffic and weather feeds to create a dynamic prediction model that can forecast potential accidents based on current conditions. This allows us to issue real-time alerts for dangerous intersections, speeding, or sudden weather changes.
To help authorities make informed decisions, we developed an AI-driven Executive Briefing Agent that generates detailed accident reports and insights. This empowers city planners to identify risk patterns and proactively improve infrastructure or adjust traffic control measures.
Our platform, CityCent, extends beyond just analysis. It provides a mobile app that delivers real-time safety alerts to citizens, while authorities can monitor and respond to potential hazards. As we refine our models and expand data integration, we aim to create a future where road safety is not just reactive but preventive—making our streets safer for everyone.
Our findings and source code can be verified via Git and the model we have created.
Go to Challenge | 13 teams have entered this challenge.
Go to Challenge | 26 teams have entered this challenge.
Go to Challenge | 16 teams have entered this challenge.