Occupant Injury Severity Prediction in Road Traffic Accidents using Machine Learning Techniques

Over years, automotive industry has made a significant progress in improving passenger car safety systems to reduce occupant injuries and fatalities due to road accidents. To further enhance the vehicle safety, it is very important to have a deeper understanding on real world accidents and true safety benefits associated with various safety systems. This requires a framework to understand the effectiveness of safety systems towards reduction in occupant injury and fatalities. This study focusses on utilizing machine learning techniques to predict occupant injury severity by considering accident parameters and safety systems, using the Road Accident Sampling System - India (RASSI) real world accident data. The RASSI database contains comprehensive accident data, including various factors that contributes for occupant injury. The study focused on fifteen accident parameters that represent key aspects of crash scenarios such as vehicle type, accident type, vehicle speed, and occupant details. Multiple machine learning algorithms such as decision tree, random forest, support vector machine and neural network are employed to construct robust models for predicting injury severity. The performance of each machine learning model is evaluated using appropriate metrics such as accuracy, precision, recall and F1-score. Additionally, a feature importance analysis is conducted to identify the critical factors that influence the injury severity. The results demonstrate the effectiveness of the proposed approach in accurately predicting occupant injury severity across different crash scenarios. Moreover, the study provides opportunity to gain valuable insights into the underlying factors that impact occupant injury severity. This will help safety engineers to carry out studies to understand the effectiveness of safety systems independently. This will aid selection and prioritisation of various safety systems towards enhancing the occupant safety considering real world accident scenarios.