Cause Analysis and Accident Classification of Road Traffic Accidents Based on Complex Networks
Source abstract
Abstract
The number of motor vehicles on the road is constantly increasing, leading to a rise in the number of traffic accidents. Accurately identifying the factors contributing to these accidents is a crucial topic in the field of traffic accident research. Most current research focuses on analyzing the causes of traffic accidents rather than investigating the underlying factors. This study creates a complex network for road traffic accident cause analysis using the topology method for complex networks. The network metrics are analyzed using the network parameters to obtain reduced dimensionality feature factors, and four machine learning techniques are applied to accurately classify the accidents’ severity based on the analysis results. The study divides real traffic accident data into three main categories based on the factors that influences them: time, environment, and traffic management. The results show that traffic management factors have the most significant impact on road accidents. The study also finds that Extreme Gradient Boosting (XGBoost) outperforms Logistic Regression (LR), Random Forest (RF) and Decision Tree (DT) in accurately categorizing the severity of traffic accidents.
Source: crossref · Quality: baseline
Research context
OpenAlex topics: Traffic and Road Safety · Traffic Prediction and Management Techniques · Transportation Systems and Logistics
SciVX discovery tags are terminology-based. OpenAlex topics are source-provided classifications.
Affiliations
The School of Building Environmental Engineering, Zhengzhou University of Light Industry, Zhengzhou 450001, China
Funding
Zhengzhou University of Light Industry
References (45)
Show source-provided references
1. World Health Organization (2018). World Health Organization Global Status Report on Road Safety 2018.
2. Soni, A., Dharmacharya, D., Pal, A., Srivastava, V.K., Shaw, R.N., and Ghosh, A. (2021). Machine Learning for Robotics Applications, Springer.
3. Road safety under the environment of intelligent connected vehicles10.1016/j.aap.2022.106645 ↗
4. Fifty years of accidents analysis & prevention: A bibliometric and scientometric overview10.1016/j.aap.2020.105568 ↗
5. Vulnerability modeling and assessment in urban transit systems considering disaster chains: A weighted complex network approach10.1016/j.ijdrr.2020.102033 ↗
6. Complex-network-based traffic network analysis and dynamics: A comprehensive review10.1016/j.physa.2022.128063 ↗
7. Identification of critical causal factors and paths of tower-crane accidents in China through system thinking and complex networks10.1061/(ASCE)CO.1943-7862.0002186 ↗
8. Construction and analysis of a coal mine accidents causation network based on text mining10.1016/j.psep.2021.07.032 ↗
9. Identification of critical stations in a Metro System: A substitute complex network analysis10.1016/j.physa.2022.127123 ↗
10. Identification of the critical accidents causative factors in the urban rail transit system by complex network theory10.1016/j.physa.2022.128404 ↗
11. Node importance evaluation in marine traffic situation complex network for intelligent maritime supervision10.1016/j.oceaneng.2022.110742 ↗
12. A complex network analysis approach for estimation and detection of traffic incidents based on independent component analysis10.1016/j.physa.2021.126504 ↗
13. Percolation on complex networks: Theory and application10.1016/j.physrep.2020.12.003 ↗
14. Promoting metro operation safety by exploring metro operation accidents network
15. Yu, X., Liu, K., Montewka, J., and Yu, Q. (2021, January 22–24). Causal Analysis of Ship Accidents in China Coastal Waters Based on Complex Network Theory. Proceedings of the 2021 6th International Conference on Transportation Information and Safety (ICTIS), Wuhan, China.10.1109/ICTIS54573.2021.9798587 ↗
16. A case study on the construction optimization decision scheme of urban subway tunnel based on the TOPSIS method10.1007/s12205-020-1290-9 ↗
17. A literature review of machine learning algorithms for crash injury severity prediction10.1016/j.jsr.2021.12.007 ↗
18. A comparative study of machine learning classifiers for injury severity prediction of crashes involving three-wheeled motorized rickshaw10.1016/j.aap.2021.106094 ↗
19. Zhao, M., Wei, Z., and Ji, S. (2020, January 23–25). Analyzing the causation of public accidents caused by urban logistics based on complex network. Proceedings of the 2020 2nd International Conference on Machine Learning, Big Data and Business Intelligence (MLBDBI), Taiyuan, China.10.1109/MLBDBI51377.2020.00017 ↗
20. Guo, M., Yuan, Z., Janson, B., Peng, Y., Yang, Y., and Wang, W. (2021). Older pedestrian traffic crashes severity analysis based on an emerging machine learning XGBoost. Sustainability, 13.10.3390/su13020926 ↗
21. Taking a mixed-methods approach to collision investigation: AcciMap, STAMP-CAST and PCM10.1016/j.apergo.2021.103650 ↗
22. Presentation of Machine Learning Approaches for Predicting the Severity of Accidents to Propose the Safety Solutions on Rural Roads10.1155/2022/4857013 ↗
23. Zhang, G., Feng, W., and Lei, Y. (2022). Human factor analysis (HFA) based on a complex network and its application in gas explosion accidents. Int. J. Environ. Res. Public Health, 19.10.3390/ijerph19148400 ↗
24. Exploring the behavioral risk chains of accidents using complex network theory in the construction industry10.1016/j.physa.2020.125012 ↗
25. Traffic accidents risk factor identification based on complex network
26. An effective method for identifying the key factors of railway accidents based on the network model10.1142/S0217979220501921 ↗
27. Zhen, Z., Zhang, Y., and Hu, M. (2021). Propagation Laws of Reclamation Risk in Tailings Ponds Using Complex Network Theory. Metals, 11.10.3390/met11111789 ↗
28. Liu, Y., Wan, C., Yu, Q., and Liu, G. (2023, January 4–6). Risk Evolution Analysis of Maritime Traffic Accidents in Coastal Areas of China. Proceedings of the 2023 7th International Conference on Transportation Information and Safety (ICTIS), Xi’an, China.10.1109/ICTIS60134.2023.10243813 ↗
29. Zhao, H., Cheng, H., Mao, T., and He, C. (2019, January 25–28). Research on traffic accidents prediction model based on convolutional neural networks in VANET. Proceedings of the 2019 2nd International Conference on Artificial Intelligence and Big Data (ICAIBD), Chengdu, China.10.1109/ICAIBD.2019.8837020 ↗
30. Hu, S., Li, Z., Xi, Y., Gu, X., and Zhang, X. (2019). Path analysis of causal factors influencing marine traffic accidents via structural equation numerical modeling. J. Mar. Sci. Eng., 7.10.20944/preprints201903.0226.v2 ↗
31. Data mining and complex network algorithms for traffic accidents analysis10.3141/2460-14 ↗
32. Sun, W., Zhang, X., Yuan, M., and Zhang, Z. (2023). Complex Network Analysis of China National Standards for New Energy Vehicles. Sustainability, 15.10.3390/su15021155 ↗
33. Li, Q., Zhang, Z., and Peng, F. (2021). Causality-network-based critical hazard identification for railway accidents prevention: Complex network-based model development and comparison. Entropy, 23.10.3390/e23070864 ↗
34. Analysis on causes of chemical industry accidents from 2015 to 2020 in Chinese mainland: A complex network theory approach10.1016/j.jlp.2023.105061 ↗
35. Cascading vulnerability analysis of unsafe behaviors of construction workers from the perspective of network modeling10.1108/ECAM-06-2021-0475 ↗
36. Risk propagation analysis of urban rail transit based on network model10.1016/j.aej.2020.02.030 ↗
37. A survey of the analysis of complex systems based on complex network theory and deep learning10.23940/ijpe.22.04.p2.241250 ↗
38. Moosavi, S., Samavatian, M.H., Parthasarathy, S., and Ramnath, R. (2019). A countrywide traffic accidents dataset. arXiv.
39. Moosavi, S., Samavatian, M.H., Parthasarathy, S., Teodorescu, R., and Ramnath, R. (2019, January 5–8). Accidents risk prediction based on heterogeneous sparse data: New dataset and insights. Proceedings of the 27th ACM SIGSPATIAL International Conference on Advances in Geographic Information Systems, Chicago, IL, USA.10.1145/3347146.3359078 ↗
40. Wang, J.S. (2023). KABCO-to-MAIS Translators-2022 Update.
41. Association analysis of accidents factors in petrochemical storage tank farms10.1016/j.jlp.2023.105124 ↗
42. A framework for intersection traffic safety screening with the implementation of complex network theory10.1155/2020/8824447 ↗
43. Quantifying the evolution of settlement risk for surrounding environments in underground construction via complex network analysis10.1016/j.tust.2020.103490 ↗
44. Dynamic risk analysis of accidents chain and system protection strategy based on complex network and node structure importance10.1016/j.ress.2023.109413 ↗
45. Injury severity prediction of traffic crashes with ensemble machine learning techniques: A comparative study10.1080/17457300.2021.1928233 ↗