A Short-Term Traffic Flow Prediction Based on Recurrent Neural Networks for Road Transportation Control in ITS
Wafa Shafqat1, Sehrish Malik2, Yung-Cheol Byun3, Do-Hyeun Kim4
1Wafa Shafqat, Department of Computer Engineering, Jeju National University, Jeju-do, Republic of Korea.
2Sehrish Malik, Department of Computer Engineering, Jeju National University, Jeju-do, Republic of Korea.
3Yung-Cheol Byun, Department of Computer Engineering, Jeju National University, Jeju-do, Republic of Korea.
4Do-Hyeun Kim, Department of Computer Engineering, Jeju National University, Jeju-do, Republic of Korea.
Manuscript received on 01 January 2019 | Revised Manuscript received on 06 January 2019 | Manuscript Published on 07 April 2019 | PP: 245-249 | Volume-8 Issue- 3C January 2019 | Retrieval Number: C10580183C19/2019©BEIESP
Open Access | Editorial and Publishing Policies | Cite | Mendeley | Indexing and Abstracting
© The Authors. Blue Eyes Intelligence Engineering and Sciences Publication (BEIESP). This is an open-access article under the CC-BY-NC-ND license (http://creativecommons.org/licenses/by-nc-nd/4.0/)
Abstract: In order to overcome the rising issue of traffic congestion, effective and exact traffic flow information is needed. Though, there have been lots of research and work being done on traffic predictions; still this field of research needs more attention. Methods/Statistical analysis: In this work, we have collected some real time traffic data for analyzing different flow patterns under different environmental conditions. In this paper, we present a short-term traffic flow prediction using RNN (Recurrent Neural Networks) for Road Transportation Control in ITS. Findings: Prediction of accurate traffic rate flow at any given time interval which is of vital importance in assisting and managing the road traffic conditions in smart cities. Improvements/Applications: Applied system uses deep learning technique for accurate predictions of traffic flow rate at any specific time.
Keywords: Traffic Flow Prediction, Recurrent Neural Networks (RNNs), Road Transportation, Long Short Term Memory (LSTM), Flow rate.
Scope of the Article: Computer Science and Its Applications