A project developed while Karnataka State Police Hackathon on Road Accident Prediction using user's Location and weather conditions by applying Machine Learning concepts.
You can access the dataset here.
pip install -r requirements.txt python app.py
We have developed an accident prediction app using FlutterFlow. This app allows users to predict the severity of an accident by providing inputs such as District Name, Weather, Number of Vehicles involved, Latitude, and Longitude.
- Prediction: Users can input the necessary parameters and receive the severity prediction for the potential accident.
- Analysis: The app provides analysis of accident data and displays graphs for different comparisons.
- Maps: Interactive heat maps and severity dot maps are available to visualize accident data.
We have implemented secure login/signup functionality with face authentication using FaceID. This ensures that only authorized users can access the system.
RESULTS AND DISCUSSIONS
Figure 1.0
The above image is the accidenatal prediction app that we have builded using flutterflow.
Figure 1.1
The above image is the Home page of the website from where we can access the other parts of the website. To move further, we will have to scroll up and continue surfing.
Figure 1.2
The above image shows the Description of the Project and here we can use the Prediction and Analysis option which gives the analysis of the accident data and the prediction of severity of the accident on the given input variables.
Figure 1.3
The above image shows the prediction after we put in the input for District Name, Weather, Number of Vehicles involved, Latitude, and Longitude. This will predict the Severity over these inputs and would show as output.
Figure 1.4
This image shows the Analysis part of the project and shows graphs of different comparisons as you would scroll down. There are two options shown named View Heat Map and View Severity Map which would open up an interactive map for Accident data.
Figure 1.5
This image shows the Heat map for accidents and also marks the hotspots for high accident areas from the website.
Figure 1.6
This image shows the Heat map for accidents and also marks the hotspots for high accident areas from the website.
Figure 1.7
This image shows the dot map for the accidents Severity wise and gives the required data throughout Karnataka.
We have created an AI Bot that would give us information on the dataset provided and answer the required queries regarding the accidents. The Bot is in its Beta version.
To access the Bot, we can see it on the website at the bottom right corner on every page of the site.
Contributions are welcome! If you have suggestions or improvements, please open an issue or submit a pull request.
This project is licensed under the MIT License. See the LICENSE file for details.
Made with ❤️ by Purval Bhude. For more about me and my work, visit my Portfolio or LinkedIn.