Optimal structure exploration of Bayesian network based on dealing with the route choice model

Ziyi Wang; Yufei Zeng; Rui Wang

doi:10.1117/12.3004079

11 October 2023 Optimal structure exploration of Bayesian network based on dealing with the route choice model

Ziyi Wang, Yufei Zeng, Rui Wang

Proceedings Volume 12800, Sixth International Conference on Computer Information Science and Application Technology (CISAT 2023); 128004A (2023) https://doi.org/10.1117/12.3004079
Event: 6th International Conference on Computer Information Science and Application Technology (CISAT 2023), 2023, Hangzhou, China

Abstract

Route selection in residents' travel is a key link in travel decision-making in transportation systems. In existing studies, discrete choice models are often used to describe residents' travel path choices. However, with today's highly developed big data, the traditional discrete choice model is too simple to represent residents' travel path choices, ignoring the connection between various factors. Therefore, a big data-driven approach is proposed to solve this problem in this paper. Driven by research data and with the introduction of the Bayesian network model, the paper adopts a hill-climbing search strategy to improve the search efficiency, uses a variety of scoring functions to train data, which optimizes the Bayesian network structure. The experimental results show that the model fully considers the causation between the independent variables, which is more logical and makes the construction of the resident travel route selection model more accurate and efficient.

(2023) Published by SPIE. Downloading of the abstract is permitted for personal use only.

Citation Download Citation

Ziyi Wang, Yufei Zeng, and Rui Wang "Optimal structure exploration of Bayesian network based on dealing with the route choice model", Proc. SPIE 12800, Sixth International Conference on Computer Information Science and Application Technology (CISAT 2023), 128004A (11 October 2023); https://doi.org/10.1117/12.3004079

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