The Optimization Technique for Traffic Accident Prediction Based on Big Data

Shiyu Tang

doi:10.47297/taposatWSP2633-456904.20240501

PDF
导出
分享
收藏
专辑

The Optimization Technique for Traffic Accident Prediction Based on Big Data

5卷第1期

浏览量: 0 Downloads: 2

The Optimization Technique for Traffic Accident Prediction Based on Big Data
The Optimization Technique for Traffic Accident Prediction Based on Big Data
School of Computer Science and Technology, Wuhan University of Science and Technology, Wuhan Hubei 430081, P.R. China
2024年5卷第1期页码：24-28
纸质出版日期： 2024-06-30 ，
DOI：10.47297/taposatWSP2633-456904.20240501
Accepted：

Scan QR Code

(2024). The Optimization Technique for Traffic Accident Prediction Based on Big Data. 科技理论与实践（英文版）, 5(1), 24-28.

Tang Shiyu.The Optimization Technique for Traffic Accident Prediction Based on Big Data[J].Theory and Practice of Science and Technology,2024,05(01):24-28.
(2024). The Optimization Technique for Traffic Accident Prediction Based on Big Data. 科技理论与实践（英文版）, 5(1), 24-28. DOI： 10.47297/taposatWSP2633-456904.20240501.

Tang Shiyu.The Optimization Technique for Traffic Accident Prediction Based on Big Data[J].Theory and Practice of Science and Technology,2024,05(01):24-28. DOI： 10.47297/taposatWSP2633-456904.20240501.

摘要

Abstract

The lives of people are strongly correlated with road traffic safety. Research and prediction of traffic accidents can ensure road traffic safety. This study built three prediction models: Random Forest

Decision Tree

and Naive Bayes. Comparing and analyzing the three models through experiments

the findings indicate that the Random Forest model prediction has a better impact on predicting the severity of traffic accidents and has a higher accuracy rate. The important factors affecting the severity of traffic accidents are identified through the processing and analysis of real road traffic accident data to predict their severity. Based on these factors

recommendations for preventing

reducing

and improving the likelihood of traffic accidents are made to lessen the safety risks associated with transportation.

关键词

Keywords

SparkRandom Forest ClassifierDecision Tree ClassifierNaive Bayes

references

Zhu, Y. (2023). Research on the construction of a big data processing platform based on Hadoop and Spark. Internet Weekly, 07:87-89.

Tian, F. (2022). A big data-based traffic supervision system - an example of traffic congestion and visual blind spot problem. Computer Knowledge and Technology, 18(36):59-61+70.

Xuan, Z. (2022). Research on data processing and fault diagnosis of rolling stock based on big data. Thesis of China Academy of Railway Science.

Huang, Q. (2021). Huang. Research on urban road network state monitoring and traffic accident risk assessment method based on multi-source data. Thesis of Jilin University.

Guo, X. (2020). Research on road traffic accident severity prediction based on Spark platform. Thesis of Yunnan University.

Luo, Y. (2020). Highway traffic risk prediction based on big data. Thesis of Changsha University of Technology.

Seong, H., Young, G., et al. (2014). Large imbalance data classification based on MapReduce for traffic accident prediction. In: 2016 International Conference on Big Data and Smart Computing (Big Comp). IEEE, 2014.

Breiman, L. (2001). Random forests. Machine Learning, 45(1):5-32.

文章被引用时，请邮件提醒。

Submit

No data

Related Author

No data

Related Institution

No data

⁰