Machine Learning-Based Modeling of Celeration for Predicting Red-Light Violations

This research examines the intricate correlation between speed variation (celeration), a metric of driver behavior associated with vehicle control, and occurrences of running red lights. The study is based on a thorough analysis of a large dataset that includes a variety of parameters, such as exceeding speed limits, driver age, passenger count, weather, road condition, and temporal factors. Using cutting-edge machine learning methods like AdaBoost and Bagging, predictive models for red-light violations are painstakingly built, achieving remarkable validation accuracies of 90.4% and 90.1%, respectively. The study acknowledges the dataset's limitations in capturing real-world traffic complexities while focusing on the effectiveness and trade-offs inherent in these methodologies. This emphasizes how important it is to have synchronized and thorough data sources to guarantee accurate representation. The research field is enhancing predictive modeling techniques and improving transportation safety by connecting celebration, speed variation patterns over time, with instances of red-light violations.