avikumart/Road-Traffic-Severity-Classification-Project
This is a multiclass classification project to classify severity of road accidents into three categories. this project is based on real-world data and dataset is also highly imbalanced.
Implements class imbalance handling via SMOTENC and dimensionality reduction with PCA, achieving 88% weighted F1-score on Ethiopian accident data with 32 features. Uses scikit-learn's RandomForest with hyperparameter tuning (n_estimators, max_depth) and includes categorical feature selection via chi-squared statistics. Deploys as an interactive Streamlit web application for real-time accident severity prediction.
No commits in the last 6 months.
Stars
20
Forks
7
Language
Jupyter Notebook
License
Apache-2.0
Category
Last pushed
Jul 10, 2024
Commits (30d)
0
Get this data via API
curl "https://pt-edge.onrender.com/api/v1/quality/ml-frameworks/avikumart/Road-Traffic-Severity-Classification-Project"
Open to everyone — 100 requests/day, no key needed. Get a free key for 1,000/day.
Higher-rated alternatives
DavidF-22/ICS5110-AppliedML_Project
Applied ML pipeline for analysing and modelling Malta traffic accidents using real-world textual...
chelzakaria/ONCycle
🚆 AI-powered train delay predictor - Know exactly when your train will actually arrive
404Avinash/j_b
Jatayu - ML-powered bird strike prediction and aviation safety intelligence platform with...
deshithagallage/Bus-Arrival-Time-Prediction-Frontend
This repository contains the frontend code for the Bus Arrival Time Prediction project, offering...
karthik-d/LocateMyBus
IoT and ML to assuage the uncertainty in city bus schedules. Track live running status and avail...