RL-CNN: Reinforcement Learning-designed Convolutional Neural Network for Urban Traffic Flow Estimation

Karimzadeh, Mostafa; Esposito, Alessandro; Zhao, Zhongliang; Braun, Torsten; Sargento, Susana (March 2021). RL-CNN: Reinforcement Learning-designed Convolutional Neural Network for Urban Traffic Flow Estimation (In Press). In: 17th International Wireless Communications & Mobile Computing Conference - IWCMC 2021. IEEE

[img] Text
Mostafa_RL-CNN.pdf - Accepted Version
Restricted to registered users only
Available under License Publisher holds Copyright.

Download (1MB) | Request a copy

Accurate prediction of urban traffic flows brings enormous advantages to big cities. Therefore, many urban traffic flow predictors have been developed in recent years. Urban traffic flow predictors aim to identify complex mobility patterns and capture urban traffic flow characteristics from large-scale historical datasets. Afterward, trained models are used to predict the future traffic volume in terms of the number of moving objects (e.g., vehicles). Convolutional Neural Networks (CNN) and other deep learning approaches are brilliant choices because of their ability to learn Spatio-temporal dependencies. Nevertheless, the extensive set of hyper-parameters tends to make these neural networks overly complex and challenging to design. In this work, we introduce RL-CNN, a framework based on Reinforcement Learning whose objective is to autonomously discover high performance CNN architectures for the given traffic prediction task without human intervention. We examine the proposed RLCNN model as a traffic flow estimator on a real-world and large scale vehicular network dataset. We observe improvements of 5% - 10% in the average traffic flow prediction accuracy over the state-of-art approaches.

Item Type:

Conference or Workshop Item (Paper)

Division/Institute:

08 Faculty of Science > Institute of Computer Science (INF)
08 Faculty of Science > Institute of Computer Science (INF) > Communication and Distributed Systems (CDS)

UniBE Contributor:

Karimzadeh Motallebiazar, Mostafa; Esposito, Alessandro; Zhao, Zhongliang and Braun, Torsten

Subjects:

000 Computer science, knowledge & systems
500 Science > 510 Mathematics
500 Science
600 Technology

Publisher:

IEEE

Language:

English

Submitter:

Dimitrios Xenakis

Date Deposited:

23 Apr 2021 12:00

Last Modified:

23 Apr 2021 12:00

Uncontrolled Keywords:

Convolutional Neural Networks; Reinforcement Learning; Urban Traffic Estimation

BORIS DOI:

10.48350/155233

URI:

https://boris.unibe.ch/id/eprint/155233

Actions (login required)

Edit item Edit item
Provide Feedback