Long Term Traffic Prediction in Highway Using Parallel CNN

Donghyun Lim; Minhyeok Lee; Junhee Seok

doi:10.1109/ICITE50838.2020.9231436

Long Term Traffic Prediction in Highway Using Parallel CNN

Donghyun Lim, Minhyeok Lee, Junhee Seok

School of Electrical Engineering

Research output: Chapter in Book/Report/Conference proceeding › Conference contribution

3 Citations (Scopus)

Abstract

For navigation system, predicting future traffic conditions is crucial. To predict the traffic condition, statistical methods and neural network models have been studied. However, conventional methods have three limitations in which only the temporal properties are used, only narrow sections or time steps are predicted and not general road sections such as all section of highway but specific sections are used as test results. This paper proposes a parallel Convolutional Neural Network (CNN) that uses spatiotemporal properties and predicts for the next five hours and up to 400 km ranges in Korea's representative highway. Using a highway dataset, the proposed parallel CNN is trained and evaluated. As a result, the result of our model is improved by 10.6%, in terms of Root Mean Square Error (RMSE), compared to the conventional method. Moreover, in terms of the average of Average Speed Difference (ASD), the result of our model is improved by 63.5%.

Original language	English
Title of host publication	2020 IEEE 5th International Conference on Intelligent Transportation Engineering, ICITE 2020
Publisher	Institute of Electrical and Electronics Engineers Inc.
Pages	107-110
Number of pages	4
ISBN (Electronic)	9781728194097
DOIs	https://doi.org/10.1109/ICITE50838.2020.9231436
Publication status	Published - 2020 Sept
Event	5th IEEE International Conference on Intelligent Transportation Engineering, ICITE 2020 - Beijing, China Duration: 2020 Sept 11 → 2020 Sept 13

Publication series

Name	2020 IEEE 5th International Conference on Intelligent Transportation Engineering, ICITE 2020

Conference

Conference	5th IEEE International Conference on Intelligent Transportation Engineering, ICITE 2020
Country/Territory	China
City	Beijing
Period	20/9/11 → 20/9/13

Bibliographical note

Publisher Copyright:
© 2020 IEEE.

Keywords

deep learning
forecast up to five hours ahead
highway
spatialoral properties
traffic prediction

ASJC Scopus subject areas

Artificial Intelligence
Decision Sciences (miscellaneous)
Automotive Engineering
Control and Optimization
Transportation

Access to Document

10.1109/ICITE50838.2020.9231436

Cite this

Lim, D., Lee, M., & Seok, J. (2020). Long Term Traffic Prediction in Highway Using Parallel CNN. In 2020 IEEE 5th International Conference on Intelligent Transportation Engineering, ICITE 2020 (pp. 107-110). Article 9231436 (2020 IEEE 5th International Conference on Intelligent Transportation Engineering, ICITE 2020). Institute of Electrical and Electronics Engineers Inc.. https://doi.org/10.1109/ICITE50838.2020.9231436

Long Term Traffic Prediction in Highway Using Parallel CNN. / Lim, Donghyun; Lee, Minhyeok; Seok, Junhee.
2020 IEEE 5th International Conference on Intelligent Transportation Engineering, ICITE 2020. Institute of Electrical and Electronics Engineers Inc., 2020. p. 107-110 9231436 (2020 IEEE 5th International Conference on Intelligent Transportation Engineering, ICITE 2020).

Research output: Chapter in Book/Report/Conference proceeding › Conference contribution

Lim, D, Lee, M & Seok, J 2020, Long Term Traffic Prediction in Highway Using Parallel CNN. in 2020 IEEE 5th International Conference on Intelligent Transportation Engineering, ICITE 2020., 9231436, 2020 IEEE 5th International Conference on Intelligent Transportation Engineering, ICITE 2020, Institute of Electrical and Electronics Engineers Inc., pp. 107-110, 5th IEEE International Conference on Intelligent Transportation Engineering, ICITE 2020, Beijing, China, 20/9/11. https://doi.org/10.1109/ICITE50838.2020.9231436

Lim D, Lee M, Seok J. Long Term Traffic Prediction in Highway Using Parallel CNN. In 2020 IEEE 5th International Conference on Intelligent Transportation Engineering, ICITE 2020. Institute of Electrical and Electronics Engineers Inc. 2020. p. 107-110. 9231436. (2020 IEEE 5th International Conference on Intelligent Transportation Engineering, ICITE 2020). doi: 10.1109/ICITE50838.2020.9231436

Lim, Donghyun ; Lee, Minhyeok ; Seok, Junhee. / Long Term Traffic Prediction in Highway Using Parallel CNN. 2020 IEEE 5th International Conference on Intelligent Transportation Engineering, ICITE 2020. Institute of Electrical and Electronics Engineers Inc., 2020. pp. 107-110 (2020 IEEE 5th International Conference on Intelligent Transportation Engineering, ICITE 2020).

@inproceedings{8722771fcc9042db975270b79e05f978,

title = "Long Term Traffic Prediction in Highway Using Parallel CNN",

abstract = "For navigation system, predicting future traffic conditions is crucial. To predict the traffic condition, statistical methods and neural network models have been studied. However, conventional methods have three limitations in which only the temporal properties are used, only narrow sections or time steps are predicted and not general road sections such as all section of highway but specific sections are used as test results. This paper proposes a parallel Convolutional Neural Network (CNN) that uses spatiotemporal properties and predicts for the next five hours and up to 400 km ranges in Korea's representative highway. Using a highway dataset, the proposed parallel CNN is trained and evaluated. As a result, the result of our model is improved by 10.6%, in terms of Root Mean Square Error (RMSE), compared to the conventional method. Moreover, in terms of the average of Average Speed Difference (ASD), the result of our model is improved by 63.5%.",

keywords = "deep learning, forecast up to five hours ahead, highway, spatialoral properties, traffic prediction",

author = "Donghyun Lim and Minhyeok Lee and Junhee Seok",

note = "Publisher Copyright: {\textcopyright} 2020 IEEE.; 5th IEEE International Conference on Intelligent Transportation Engineering, ICITE 2020 ; Conference date: 11-09-2020 Through 13-09-2020",

year = "2020",

month = sep,

doi = "10.1109/ICITE50838.2020.9231436",

language = "English",

series = "2020 IEEE 5th International Conference on Intelligent Transportation Engineering, ICITE 2020",

publisher = "Institute of Electrical and Electronics Engineers Inc.",

pages = "107--110",

booktitle = "2020 IEEE 5th International Conference on Intelligent Transportation Engineering, ICITE 2020",

}

TY - GEN

T1 - Long Term Traffic Prediction in Highway Using Parallel CNN

AU - Lim, Donghyun

AU - Lee, Minhyeok

AU - Seok, Junhee

PY - 2020/9

Y1 - 2020/9

N2 - For navigation system, predicting future traffic conditions is crucial. To predict the traffic condition, statistical methods and neural network models have been studied. However, conventional methods have three limitations in which only the temporal properties are used, only narrow sections or time steps are predicted and not general road sections such as all section of highway but specific sections are used as test results. This paper proposes a parallel Convolutional Neural Network (CNN) that uses spatiotemporal properties and predicts for the next five hours and up to 400 km ranges in Korea's representative highway. Using a highway dataset, the proposed parallel CNN is trained and evaluated. As a result, the result of our model is improved by 10.6%, in terms of Root Mean Square Error (RMSE), compared to the conventional method. Moreover, in terms of the average of Average Speed Difference (ASD), the result of our model is improved by 63.5%.

AB - For navigation system, predicting future traffic conditions is crucial. To predict the traffic condition, statistical methods and neural network models have been studied. However, conventional methods have three limitations in which only the temporal properties are used, only narrow sections or time steps are predicted and not general road sections such as all section of highway but specific sections are used as test results. This paper proposes a parallel Convolutional Neural Network (CNN) that uses spatiotemporal properties and predicts for the next five hours and up to 400 km ranges in Korea's representative highway. Using a highway dataset, the proposed parallel CNN is trained and evaluated. As a result, the result of our model is improved by 10.6%, in terms of Root Mean Square Error (RMSE), compared to the conventional method. Moreover, in terms of the average of Average Speed Difference (ASD), the result of our model is improved by 63.5%.

KW - deep learning

KW - forecast up to five hours ahead

KW - highway

KW - spatialoral properties

KW - traffic prediction

UR - http://www.scopus.com/inward/record.url?scp=85097234337&partnerID=8YFLogxK

U2 - 10.1109/ICITE50838.2020.9231436

DO - 10.1109/ICITE50838.2020.9231436

M3 - Conference contribution

AN - SCOPUS:85097234337

T3 - 2020 IEEE 5th International Conference on Intelligent Transportation Engineering, ICITE 2020

SP - 107

EP - 110

BT - 2020 IEEE 5th International Conference on Intelligent Transportation Engineering, ICITE 2020

PB - Institute of Electrical and Electronics Engineers Inc.

T2 - 5th IEEE International Conference on Intelligent Transportation Engineering, ICITE 2020

Y2 - 11 September 2020 through 13 September 2020

ER -

Long Term Traffic Prediction in Highway Using Parallel CNN

Abstract

Publication series

Conference

Bibliographical note

Keywords

ASJC Scopus subject areas

Access to Document

Other files and links

Fingerprint

Cite this