Predicting Traffic Accident Severity with Deep Neural Networks
By: Meghan Bibb, Pablo Rivas, Mahee Tayba
Potential Business Impact:
Predicts how bad car crashes will be.
Traffic accidents can be studied to mitigate the risk of further events. Recent advances in machine learning have provided an alternative way to study data associated with traffic accidents. New models achieve good generalization and high predictive power over imbalanced data. In this research, we study neural network-based models on data related to traffic accidents. We begin analyzing relative feature colinearity and unsupervised dimensionality reduction through autoencoders, followed by a dense network. The features are related to traffic accident data and the target is to classify accident severity. Our experiments show cross-validated results of up to 92% accuracy when classifying accident severity using the proposed deep neural network.
Similar Papers
Predicting and Explaining Traffic Crash Severity Through Crash Feature Selection
Machine Learning (CS)
Finds what makes car crashes worse.
Learning Multimodal Embeddings for Traffic Accident Prediction and Causal Estimation
Machine Learning (CS)
Predicts car crashes using road and sky pictures.
Deep Learning Advances in Vision-Based Traffic Accident Anticipation: A Comprehensive Review of Methods, Datasets, and Future Directions
CV and Pattern Recognition
Helps cars predict crashes before they happen.