Traffic accident characteristics and association analysis of electric bicycles based on data mining

Yantao Lin; Fengchun Han; Sheqiang Ma

doi:10.1117/12.2652811

21 November 2022 Traffic accident characteristics and association analysis of electric bicycles based on data mining

Yantao Lin, Fengchun Han, Sheqiang Ma

Proceedings Volume 12340, International Conference on Frontiers of Traffic and Transportation Engineering (FTTE 2022); 123400P (2022) https://doi.org/10.1117/12.2652811
Event: International Conference on Frontiers of Traffic and Transportation Engineering (FTTE 2022), 2022, Lanzhou, China

Abstract

With the increasing number of electric bicycles in cities, traffic safety is confronted with serious challenges. To prevent and control electric bicycle traffic accidents and further explore accident characteristics, this paper screens all 1555 general accident data records involving electric bicycles in Shenzhen from 2016-2021, 19 main impact factors are counted, and divided into three categories: accident information, personnel information, and road and facility information. Data mining is performed on the full accident set and each of the three single-dimensional accident sets: fatal accidents, escape accidents and accidents caused by electric bicycles. The Apriori algorithm is used to calculate and explore association rules, and the ones with better support, confidence and lift indexes are selected from them. From the association rules, this paper derives the relevant factors of electric bicycle traffic accidents, analyzes the coupling mechanism within the accidents, and provides suggestions on the countermeasures against the risk of electric bicycle traffic accidents.

Citation Download Citation

Yantao Lin, Fengchun Han, and Sheqiang Ma "Traffic accident characteristics and association analysis of electric bicycles based on data mining", Proc. SPIE 12340, International Conference on Frontiers of Traffic and Transportation Engineering (FTTE 2022), 123400P (21 November 2022); https://doi.org/10.1117/12.2652811

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