Research on the influencing factors of accident severity based on the optimization of density clustering algorithm

Hairong Ma; Tangyi Guo; Liu He

doi:10.1117/12.2627802

14 March 2022 Research on the influencing factors of accident severity based on the optimization of density clustering algorithm

Hairong Ma, Tangyi Guo, Liu He

Author Affiliations +

Proceedings Volume 12165, International Conference on Intelligent Traffic Systems and Smart City (ITSSC 2021); 121650G (2022) https://doi.org/10.1117/12.2627802
Event: 2021 International Conference on Intelligent Traffic Systems and Smart City, 2021, Zhengzhou, China

Abstract

In order to explore the causes of road traffic accidents and analyze the influencing factors of the severity of the accident, this paper is based on the traffic accident record data of Dallas in 2019. Firstly, it uses Python to preprocess and render the data, and initially analyze the relationship between the independent variables and the severity of the traffic accident. Based on the preprocessed 12,392 pieces of accident data, it is divided into general accidents and major accidents according to the severity; Secondly, the adaptive K-DBSCAN density clustering algorithm is introduced to cluster the effective density according to the severity, to eliminate the noise point data, and reflect the hot spots of traffic accidents in Dallas state; Finally, the parameters of the established XGBoost classification model are traversed, and the parameters with the highest accuracy are selected, the characteristics that have an important impact on the accident severity prediction results in the feature set such as road and environment are sought. The feature importance ranking is obtained, and practical suggestions and measures are put forward from the perspective of model prediction.

Citation Download Citation

Hairong Ma, Tangyi Guo, and Liu He "Research on the influencing factors of accident severity based on the optimization of density clustering algorithm", Proc. SPIE 12165, International Conference on Intelligent Traffic Systems and Smart City (ITSSC 2021), 121650G (14 March 2022); https://doi.org/10.1117/12.2627802

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