Citation

Zhu Y, Huang C, Wang Y, Wang J. Int. J. Automot. Technol. 2022; 23(4): 1141-1151.

Copyright

(Copyright © 2022, Holtzbrinck Springer Nature Publishing Group)

DOI

10.1007/s12239-022-0100-4

PMID

unavailable

Abstract

Accurate short-term traffic state prediction is a crucial requisite for control and guidance of traffic flow in the intelligent traffic system, which has attracted increasing attention in the transportation field recently. This paper tests the optimization performances of two emerging bionic algorithms, known as Cuckoo Search Algorithm (CS) and Bat Algorithm (BA). Combined with the Support Vector Regression (SVR) principle, the two aforementioned algorithms are applied to optimize the kernel function parameters in SVR. At last, the speed data of a road network in Guangzhou are collected. The prediction performances of the CS-SVR and BA-SVR models are tested after preprocessing the data. From the overall prediction rates, the CS-SVR algorithm is slightly better than BA-SVR in terms of calculating speed. Furthermore, the two algorithms are significantly superior to the traditional SVR model and long short-term memory networks (LSTM), thereby verifying their effectiveness and practicability in short-term traffic state prediction.

Language: en

Keywords

Bat algorithm; Cuckoo search algorithm; Intelligent traffic system; Traffic state prediction