A novel adaptive ensemble model framework for short-term traffic flow prediction based on model selection and multi-objective optimization

Ye Li; Hui Liu; Yanfei Li; Zijie Cao; Zhu Duan

doi:10.1117/12.2620238

22 December 2021 A novel adaptive ensemble model framework for short-term traffic flow prediction based on model selection and multi-objective optimization

Ye Li, Hui Liu, Yanfei Li, Zijie Cao, Zhu Duan

Author Affiliations +

Proceedings Volume 12058, Fifth International Conference on Traffic Engineering and Transportation System (ICTETS 2021); 120582S (2021) https://doi.org/10.1117/12.2620238
Event: 5th International Conference on Traffic Engineering and Transportation System (ICTETS 2021), 2021, Chongqing, China

Abstract

Short-term traffic prediction is an important technology for smart city management and scheduling, which can provide accurate predictions for the future status of various traffic systems in the city, such as road traffic and subway traffic. In this paper, an adaptive ensemble prediction model that integrates single-objective model selection, multi-objective ensemble, and deep learning models is proposed. Several deep learning models are trained first, which forms a prediction model pool. A single-objective optimization algorithm is used to perform model selection by selecting several base models from the pool, then a multi-objective optimization algorithm is used for integrating the dynamically selected base models. The model performance is evaluated in a dataset collected from a real-world road node. The results reveal that the proposed adaptive model framework has superior prediction ability.

Citation Download Citation

Ye Li, Hui Liu, Yanfei Li, Zijie Cao, and Zhu Duan "A novel adaptive ensemble model framework for short-term traffic flow prediction based on model selection and multi-objective optimization", Proc. SPIE 12058, Fifth International Conference on Traffic Engineering and Transportation System (ICTETS 2021), 120582S (22 December 2021); https://doi.org/10.1117/12.2620238

ACCESS THE FULL ARTICLE

INSTITUTIONAL
Select your institution to access the SPIE Digital Library.

SELECT YOUR INSTITUTION

PERSONAL
Sign in with your SPIE account to access your personal subscriptions or to use specific features such as save to my library, sign up for alerts, save searches, etc.

PERSONAL SIGN IN

No SPIE Account? Create one

PURCHASE THIS CONTENT

SUBSCRIBE TO DIGITAL LIBRARY

50 downloads per 1-year subscription

Members: $195

Non-members: $335 ADD TO CART

25 downloads per 1 - year subscription

Members: $145

Non-members: $250 ADD TO CART

PURCHASE SINGLE ARTICLE

Includes PDF, HTML & Video, when available

Members: $17.00

Non-members: $21.00 ADD TO CART

PROCEEDINGS
6 PAGES

DOWNLOAD PAPER SAVE TO MY LIBRARY

GET CITATION

RIGHTS & PERMISSIONS

Get copyright permission Get copyright permission on Copyright Marketplace

KEYWORDS

Data modeling

Optimization (mathematics)

Performance modeling

Systems modeling

Roads

Genetic algorithms

Convolution

Show All Keywords

Keywords/Phrases

Search In:

Publication Years