A Highway Abnormal Event Discrimination and Detection Method

With the continuous increase in highway traffic volume, abnormal events occur frequently, seriously affecting traffic fluidity and safety. This study aims to develop an efficient abnormal event detection method. Based on simulation data generated by the VISSIM software, the K-means clustering algorithm is applied, with speed, density, and occupancy rate as key feature parameters, aiming to effectively identify abnormal events on highways. The research results show that, after comparing the performance of models using different combinations of feature parameters, the K-means model using speed and occupancy as input features exhibits the best performance, achieving an accuracy of 90.4% and a false negative rate of only 6.47%. The model proposed in this study can effectively identify abnormal events on highways, thereby providing strong support for improving the safety management level of highways.