Application of Bionic Algorithm Based on CS-SVR and BA-SVR in Short-Term Traffic State Prediction Modeling of Urban Road

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 algorit...

Celý popis

Uloženo v:
Podrobná bibliografie
Vydáno v:International journal of automotive technology Ročník 23; číslo 4; s. 1141 - 1151
Hlavní autoři: Zhu, Yun, Huang, Chengwenyuan, Wang, Yang, Wang, Jianyu
Médium: Journal Article
Jazyk:angličtina
Vydáno: Seoul The Korean Society of Automotive Engineers 01.08.2022
Springer Nature B.V
한국자동차공학회
Témata:
Automotive Engineering
Bionics
Engineering
Kernel functions
Machine learning
Optimization
Prediction models
Roads & highways
Search algorithms
Support vector machines
Traffic control
Traffic flow
Traffic models
Transportation networks
자동차공학
Traffic state prediction
Bat algorithm
Cuckoo search algorithm
Intelligent traffic system
ISSN:1229-9138, 1976-3832
On-line přístup:Získat plný text
Tagy: Přidat tag
Žádné tagy, Buďte první, kdo vytvoří štítek k tomuto záznamu!
Popis
Shrnutí: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.
Bibliografie:ObjectType-Article-1
SourceType-Scholarly Journals-1
ObjectType-Feature-2
content type line 14
ISSN:1229-9138
1976-3832
DOI:10.1007/s12239-022-0100-4