Citation

Ji B, Hong EJ. Sensors (Basel) 2019; 19(23): s19235327.

Affiliation

Department of Computer and Telecommunication Engineering, Yonsei University, Wonju-si 26493, Korea.

Copyright

(Copyright © 2019, MDPI: Multidisciplinary Digital Publishing Institute)

DOI

10.3390/s19235327

PMID

31816962

Abstract

In this paper, we propose a method for deep-learning-based real-time road traffic predictions using long-term evolution (LTE) access data. The proposed system generates a road traffic speed learning model based on road speed data and historical LTE data collected from a plurality of base stations located within a predetermined radius from the road. Real-time LTE data were the input for the generated learning model in order to predict the real-time speed of traffic. Since the system was developed using a time-series-based road traffic speed learning model based on LTE data from the past, it is possible for it to be used for a road where the environment has changed. Moreover, even on roads where the collection of traffic data is invalid, such as a radio shadow area, it is possible to directly enter real-time wireless communications data into the traffic speed learning model to predict the traffic speed on the road in real time, and in turn, raise the accuracy of real-time road traffic predictions.

Language: en

Keywords

LTE access data; cellular phones; deep learning; long short-term memory (LSTM); road traffic prediction