Citation: Lim, J.; Park, S.; Choi, D.;
Bok, K.; Yoo, J. Road Speed
Prediction Scheme by Analyzing
Road Environment Data. Sensors
2022, 22, 2606. https://doi.org/
10.3390/s22072606
Academic Editors: Felipe Jiménez,
Yangquan Chen, Subhas
Mukhopadhyay, Nunzio Cennamo,
M. Jamal Deen, Junseop Lee and
Simone Morais
Received: 13 January 2022
Accepted: 25 March 2022
Published: 29 March 2022
Publisher’s Note: MDPI stays neutral
with regard to jurisdictional claims in
published maps and institutional affil-
iations.
Copyright: © 2022 by the authors.
Licensee MDPI, Basel, Switzerland.
This article is an open access article
distributed under the terms and
conditions of the Creative Commons
Attribution (CC BY) license (https://
creativecommons.org/licenses/by/
4.0/).
Article
Road Speed Prediction Scheme by Analyzing Road
Environment Data
Jongtae Lim
1
, Songhee Park
1
, Dojin Choi
2
, Kyoungsoo Bok
3
and Jaesoo Yoo
1,
*
1
Department of Information & Communication Engineering, Chungbuk National University,
Cheongju 28644, Korea; jtlim@chungbuk.ac.kr (J.L.); shpark1586@chungbuk.ac.kr (S.P.)
2
Department of Computer Engineering, Changwon National University,
Changwon 51140, Korea; dojinchoi@changwon.ac.kr
3
Department of Artificial Intelligence Convergence, Wonkwang University, Iksan 54538, Korea;
ksbok@wku.ac.kr
* Correspondence: yjs@chungbuk.ac.kr; Tel.: +82-43-261-3230
Abstract:
Road speed is an important indicator of traffic congestion. Therefore, the occurrence of
traffic congestion can be reduced by predicting road speed because predicted road speed can be
provided to users to distribute traffic. Traffic congestion prediction techniques can provide alternative
routes to users in advance to help them avoid traffic jams. In this paper, we propose a machine-
learning-based road speed prediction scheme using road environment data analysis. The proposed
scheme uses not only the speed data of the target road, but also the speed data of neighboring roads
that can affect the speed of the target road. Furthermore, the proposed scheme can accurately predict
both the average road speed and rapidly changing road speeds. The proposed scheme uses historical
average speed data from the target road organized by the day of the week and hour to reflect the
average traffic flow on the road. Additionally, the proposed scheme analyzes speed changes in
sections where the road speed changes rapidly to reflect traffic flows. Road speeds may change
rapidly as a result of unexpected events such as accidents, disasters, and construction work. The
proposed scheme predicts final road speeds by applying historical road speeds and events as weights
for road speed prediction. It also considers weather conditions. The proposed scheme uses long
short-term memory (LSTM), which is suitable for sequential data learning, as a machine learning
algorithm for speed prediction. The proposed scheme can predict road speeds in 30 min by using
weather data and speed data from the target and neighboring roads as input data. We demonstrate
the capabilities of the proposed scheme through various performance evaluations.
Keywords:
road speed prediction; traffic congestion; traffic incident analysis; traffic prediction; traffic
data analysis
1. Introduction
Various studies have recently been conducted to solve problems caused by traffic
congestion [
1
–
17
]. These studies have aimed to reduce the occurrence rate of traffic conges-
tion by predicting traffic congestion in advance and avoiding various problems caused by
traffic congestion by providing alternatives to drivers approaching traffic jams. Road speed
is one of the most important indicators of traffic conditions. Various factors affect road
speed, including the speed limit of a road, traffic volume that the road can accommodate,
traffic flow over time, and the effects of connected roads, accidents, weather, and special
days such as national holidays. These factors affecting road speed are defined as road
environment data. Because road environment data affect traffic congestion, it is necessary
to analyze the impact of each factor and combined factors on traffic congestion.
The degree of traffic congestion is determined by various factors such as road speed,
traffic volume, number of low-speed vehicles, and road congestion. The National Intelli-
gent Transport System (ITS) Center, which manages all traffic information in South Korea,
Sensors 2022, 22, 2606. https://doi.org/10.3390/s22072606 https://www.mdpi.com/journal/sensors
