Exploration and Research on Intelligent Traffic Control System based on Cloud Computing

DOI

10.2991/iccset-14.2015.41How to use a DOI?

Keywords

Intelligent transportation; cloud computing; MapReduce; traffic flow forecasting

Abstract

As an important part of the intelligent transportation system, the short-term traffic flow forecasting is always one of hot research. The short-time traffic flow prediction based on MapReduce technology is put forward in the paper from the view of improving practical prediction algorithm of cloud computing platform and in combination with the technical advantage in mass data storage and massively parallel real-time processing. Improve the computational efficiency of the short-time traffic flow forecasting under the premise of ensuring the accuracy of prediction so as to enhancing the practical of the prediction algorithm. Simulation results show that the problems of long training time of the early network weights in BP neural network algorithm and of low efficiency for matching the searching history database in K nearest neighbor nonparametric regression algorithm pattern. And, it can effectively improve the prediction of the practicability of the algorithm.

Copyright

© 2015, the Authors. Published by Atlantis Press.

Open Access

This is an open access article distributed under the CC BY-NC license (http://creativecommons.org/licenses/by-nc/4.0/).

Download article (PDF)

TY  - CONF
AU  - Hongxia Liu
PY  - 2015/01
DA  - 2015/01
TI  - Exploration and Research on Intelligent Traffic Control System based on Cloud Computing
BT  - Proceedings of the 2014 International Conference on Computer Science and Electronic Technology
PB  - Atlantis Press
SP  - 192
EP  - 197
SN  - 2352-538X
UR  - https://doi.org/10.2991/iccset-14.2015.41
DO  - 10.2991/iccset-14.2015.41
ID  - Liu2015/01
ER  -