Every day around the world, a large percentage of people die from traffic accident injuries. An effective approach for reducing traffic fatalities is: first building automatic traffic accident detection systems, second, reducing the time between when an accident occurs and when first emergency responders are dispatched to the scene of the accident. Recent approaches are using built-in vehicle automatic accident detection and notification systems. While these approaches work fine, they are expensive, maintenance is a complex task, and are not available in all cars. On the other hand, the ability to detect traffic accidents using smartphones has only recently become possible because of the advances in the processing power and sensors deployed on smartphones.
What it does
Our objective is to reduce the number of road accidents and their severity by predicting severity of accidents in areas taking into account numerous surrounding factors and alerting the driver to be careful in case of the former being true
How I built it
According to the idea, a website is implemented that makes use of various parameters like latitude longitude, Humidity, Pressure, etc. A statistical machine learning model built using python is employed for the prediction of chances and severity of an accident using the parameters as input.
Challenges I ran into
The main challenge which I faced was to improve the accuracy of the model, After trying many algorithms I achieved an accuracy of 92 percent.
Accomplishments that I'm proud of
I am proud that travelify might help to reduce accidents
What I learned
I learned various new techniques to improve the accuracy and I tried a new way to deploy using streamlit
What's next for travilify
To make it real-time using geo API.