A Study of Bad Driving Behavior Based on Improved K-Means Clustering and Neural Network

Abstract

With the popularization of the Internet of Vehicles technology, excavating useful information from a large amount of driving behavior data to evaluate the driver's safe driving behaviors in real time, accurately and efficiently, is of great significance to improve the safety management level and transportation efficiency of road transportation process. Based on the driver's driving behavior characteristics and driving industry management standards, this paper proposes a bad driving behavior evaluation method based on improved k-means clustering and neural network. It uses the improved k-means clustering method to select typical sample points from the characteristic parameters extracted from the vehicle GPS positioning platform. The Backpropagation neural network algorithm is designed to learn the clustering results, and the online classification evaluation of bad driving behavior is realized. It provides a new direction for the transportation vehicle management department to carry out safety management of the road transportation process.