A Probability-Based Analytical Model Based on Deep Learning for Traffic Information Estimation

This paper proposes a probability density function model based on deep learning to analyze the relationships between the number of call arrivals and vehicle speed. Furthermore, a vehicle speed estimation method based on deep learning is proposed to estimate vehicle speed in accordance with the number of call arrivals. A traffic flow estimation method is proposed to estimate traffic flow in accordance with the number of normal location updates. Finally, a traffic density estimation method is proposed to estimate the traffic density in accordance with the estimated vehicle speed and the estimated traffic flow. In experiments, the simulation results showed that the accuracies of estimated vehicle speed and estimated traffic density are 96.36% and 96.45%, respectively.

I. Introduction

In recent years, because of advance in science and technology and the maturity of hardware, the intelligent transportation system (ITS) is becoming more and more powerful. Realtime traffic information, such as traffic flow, traffic density and vehicle speed, plays a significant role in ITS. Thus, many researchers contribute into enhancing the effectiveness of traffic information system and many research products have been published.