Original scientific paper

https://doi.org/10.7307/ptt.v36i2.366

Analysis of Beijing Traffic Violations Based on the BERT-CRF Model

Jie Li ; North China University of Technology
Yuntao Shi ; North China University of Technology
Shuqin Li ; North China University of Technology

Abstract

Traffic violations are a major cause of traffic accidents, yet current research falls short in comprehensively analysing these violations and the named entity method fails to extract the name of traffic violation events from records, thereby lacking in providing guidance for managing urban traffic violations. By expanding the People’s Daily dataset from 71,456 words to 95,291 words, the BERT-CRF (Bidirectional Encoder Representations from Transformers-Conditional Random Field) model achieves an accuracy rate of 88.53%, a recall rate of 92.90% and an F1 score of 90.66%, successfully identifying event, time and location named entities within traffic violations. The data of traffic violations is then enhanced through forward geocoding and the Bayesian formula, and traffic violations are analysed from time, space, administrative region, gender and weather, to provide support for the dynamic allocation of law enforcement forces on traffic scenes and the precise management of

Keywords

traffic violation; traffic accident; name entity; People's Daily; BERT-CRF; Bayesian formula

Hrčak ID:

318707

URI

https://hrcak.srce.hr/318707

Publication date:

30.4.2024.

Visits: 251 *