Image-to-image learning to predict traffic speeds by considering area-wide spatio-temporal dependencies
- Authors
- Jo, Dohyoung; Yu, Byeonghyeop; Jeon, Hyunjeong; Sohn, Keemin
- Issue Date
- Feb-2019
- Publisher
- Institute of Electrical and Electronics Engineers Inc.
- Keywords
- Deep convolutional neural network (CNN), machine learning; spatio-temporal dependency; traffic speed
- Citation
- IEEE Transactions on Vehicular Technology, v.68, no.2, pp 1188 - 1197
- Pages
- 10
- Journal Title
- IEEE Transactions on Vehicular Technology
- Volume
- 68
- Number
- 2
- Start Page
- 1188
- End Page
- 1197
- URI
- https://scholarworks.bwise.kr/cau/handle/2019.sw.cau/3353
- DOI
- 10.1109/TVT.2018.2885366
- ISSN
- 0018-9545
1939-9359
- Abstract
- Spatio-temporal dependencies are the key to predicting the traffic parameters of an urban arterial network. However, their inclusion in forecasting traffic states has been hampered due to both the absence of a robust model and the computational burden. Recently, an innovative way to tackle the problem was developed by adopting a convolutional neural network for map images representing a traffic state. Unlike previous studies that utilized map images only for input, the present study adopted images for both the input and the output of the proposed model. The results show that the performance of image-to-image learning is superior to that of existing models. IEEE
- Files in This Item
- There are no files associated with this item.
- Appears in
Collections - College of Engineering > ETC > 1. Journal Articles
Items in ScholarWorks are protected by copyright, with all rights reserved, unless otherwise indicated.