Browse > Article
http://dx.doi.org/10.9708/jksci.2022.27.08.069

Predicting lane speeds from link speeds by using neural networks  

Pyun, Dong hyun (Dept. of Computer Engineering, Graduate School, Hongik University)
Pyo, Changwoo (Dept. of Computer Engineering, Hongik University)
Abstract
In this paper, a method for predicting the speed for each lane from the link speed using an artificial neural network is presented to increase the accuracy of predicting the required time of a driving route. The time required for passing through a link is observed differently depending on the direction of going straight, turning right, or turning left at the intersection of the end of the link. Therefore, it is necessary to predict the speed according to the vehicle's traveling direction. Data required for learning and verification were constructed by refining the data measured at the Gongpyeong intersection of Gukchaebosang-ro in Daegu Metropolitan City and four adjacent intersections around it. Five neural network models were used. In addition, error analysis of the prediction was performed to select a neural network experimentally suitable for the research purpose. Experimental results showed that the error in the estimation of the time required for each lane decreased by 17.4% for the straight lane, 4.4% for the right-turn lane, and 3.9% for the left-turn lane. This experiment is the result of analyzing only one link. If the entire pathway is tested, the effect is expected to be greater.
Keywords
ITS; estimate the transit time; AI; route analysis; lane speeds;
Citations & Related Records
Times Cited By KSCI : 6  (Citation Analysis)
연도 인용수 순위
1 Hwangseong Lee and Jangbae Park, "Traffic State predictability analysis by lane based on vehicle trajectory data," Proceedings of the KOR-KST Conference, pp662-666 (6 pages), 2021.11
2 Jeon, Seung Bae and Oh, Haeng Yeol and Lee, Tae Young and Kim, Gun, Jeong and Myeong-Hun "Road Traffic Speed Prediction Using LSTM Recurrent Neural Network," KOREAN SOCIETY OF CIVIL ENGINEERS, pp434-435 (2 pages), October 2020.
3 Kim Hong Geun and Park Chul Young and Shin Chang Sun and Cho Yong Yun and Park Jang Woo, "Time Series Analysis for Traffic Flow Using Dynamic Linear Model," KIPS Tr. Comp. and Comm. Sys., Vol.6, No.4, pp.179~188, June 2017. DOI: 10.3745/KTCCS.2017.6.4.179   DOI
4 Hee jin Jung and Jin su Yoon and Sang hoon Bae, "Traffic Congestion Estimation by Adopting Recurrent Neural Network," J. Korea Inst. Intell. Transp. Syst., Vol.16 No.6, pp.67~78, December 2017. DOI: 10.12815/kits. 2017.16.6.67   DOI
5 Youngchan Kim and Junwon Kim and Yohee Han and Jongjun Kim and Jewoong Hwang, "Development of Traffic Speed Prediction Model Reflecting Spatio-temporal Impact based on Deep Neural Network," Vol.19, No.1, pp.1~16, February 2020, DOI: 10.12815/kits.2020.19.1.1   DOI
6 Boogi Park and Sang hoon Bae and Bokyung Jung, "Speed Prediction of Urban Freeway Using LSTM and CNN-LSTM Neural Network," J. Korea Inst. Intell. Transp. Syst., Vol.20 No.1(2021), pp.86~99, February 2021, DOI: 10.12815/kits.2021.20.1.86   DOI
7 Dongmin Kim and Suseong Chae and Hojin Kang and Gitae Jang, "Deep learning-based prediction of the travel speed for short term on an arterial road," Proceedings of the KOR-KST Conference, pp571-576(7 pages), November 2021,
8 Jionseok Seo and Huijin Jeong and Hongseok Lee, "Development of traffic congestion prediction and signal control solution based on deep learning," Proceedings of the KOR-KST Conference, pp70-75(7 pages), February 2019.
9 Yoo Jin Kim and Young Yoon, "Speed Prediction and Analysis of Nearby Road Causality Using Explainable Deep Graph Neural Network," Journal of The Korea Convergence Society, Vol. 13. No. 1, pp.51-62, January 2022. DOI: 10.15207/JKCS.2022.13.01.051   DOI
10 Sunghoon Kim and Jonghyuk Park and Yerim Choi, "Traffic Speed Prediction Based on Graph Neural Networks for Intelligent Transportation System," J. Korea Inst. Intell. Transp. Syst., Vol.20 No.1, pp.70~85, February 2021, DOI: 10.12815/kits.2021.20.1.70   DOI
11 Gwondong Lee and Seok-Hee Lee and Ariunerdene Nyamdavaa and Seokil Song, "Prediction Method for Traffic Speed based on ConvLSTM," Journal of KIIT. Vol. 19, No. 12, pp. 27-33, December 2021, DOI: 10.14801/jkiit.2021.19.12.27   DOI
12 Hee-Sub Rim and Cheol Oh and Kyeong-Pyo Kang, "A Novel Method for Estimating Representative Section Travel Times Using Individual Vehicle Trajectory Data," J. Korea Inst. Intell. Transp. Syst., Vol.8 No.6, pp.23~35, December 2009
13 Do Hoon Kim and Tae Ho Kim, "Development of Travel Speed Prediction Model based on Urban Traffic Information System," The Seoul Institute, Vol.18 No.3, pp101-112(12 pages), September 2017,
14 Jiyoung Hwang and Byeongjun Ro and Hwansu ryu, "Asymmetric long time traffic speed prediction using Graph Multi-Attention algorithm," Proceedings of the KOR-KST Conference, pp378-383(7 pages), November 2021.
15 Jeon, Seung Bae and Muhammad Sarfraz Khan and Lee, Jung Hwan and Jeong, Myeong Hun, "Road Network Traffic Data Prediction Using ResNet," Journal of Korean Society for Geospatial Information Science Vol. No.2, pp75-84 (10pages), June 2021, DOI: 10.7319/kogsis.2021.29.2.075   DOI
16 Huijin Jeong and Jinseok Seo and Hongsek Lee, "Prediction of urban traffic congestion through LSTM-RNN model," Proceedings of the KOR-KST Conference, pp64-69(7 pages), February 2019,
17 Kim, Eui-Jin and Kim, Dong-Kyu, "Short-term Prediction of Travel Speed in Urban Areas Using an Ensemble Empirical Mode Decomposition," JOURNAL OF THE KOREAN SOCIETY OF CIVIL ENGINEERS 38(4), pp579-586(8 pages), August 2018,   DOI
18 Young-Jung Yu and Sang-Ho Moon and Seong-Ho Park, "Analysis of KNN Algorithm for Speed Prediction in Urban Roads," Asia-pacific Journal of Multimedia Services Convergent with Art, Humanities, and Sociology Vol.7, No.2, pp245-253, February 2017, DOI: 10.14257/AJMAHS.2017.02.0   DOI
19 Jiwon Son and Junho Song and Namhyuk Kim and Taeheon Kim and Sunghwan Park and Sang-wook Kim, "A Deep Learning Based Traffic Speed Prediction on Multiple-Roads," Proceedings of the online fall academic conference 2020, 27(2), November 2020,