ReMAHA–CatBoost: Addressing Imbalanced Data in Traffic Accident Prediction Tasks
Source abstract
Abstract
Using historical information from traffic accidents to predict accidents has always been an area of active exploration by researchers in the field of transportation. However, predicting only the occurrence of traffic accidents is insufficient for providing comprehensive information to relevant authorities. Therefore, further classification of predicted traffic accidents is necessary to better identify and prevent potential hazards and the escalation of accidents. Due to the significant disparity in the occurrence rates of different severity levels of traffic accidents, data imbalance becomes a critical issue. To address the challenge of predicting extremely imbalanced traffic accident events, this paper introduces a predictive framework named ReMAHA–CatBoost. To evaluate the effectiveness of ReMAHA–CatBoost, we conducted experiments on the US–Accidents traffic accident dataset, where the class label imbalance reaches up to 91.40 times. The experimental results demonstrate that the proposed model in this paper exhibits exceptional predictive performance in the domain of imbalanced traffic accident prediction.
Source: crossref · Quality: baseline
Research context
OpenAlex topics: Traffic Prediction and Management Techniques · Traffic and Road Safety · Occupational Health and Safety Research
SciVX discovery tags are terminology-based. OpenAlex topics are source-provided classifications.
Affiliations
School of Computer Science and Engineering, Sichuan University of Science and Engineering, Yibin 644002, China
Sichuan Provincial Engineering Laboratory of Big Data Visual Analysis, Yibin 644002, China
School of Automation and Information Engineering, Sichuan University of Science and Engineering, Yibin 644002, China
Sichuan Key Provincial Research Base of Intelligent Tourism, Zigong 643000, China
Funding
Sichuan University of Science and Engineering Graduate Student Innovation Fund · Sichuan Provincial Science and Technology Department Project · Sichuan Province Intelligent Tourism Research Base Project
References (49)
Show source-provided references
1. World Health Organization (2023, October 31). Road Traffic Injuries. Available online: https://www.who.int/news-room/fact-sheets/detail/road-traffic-injuries.
2. World Health Organizat (2023, October 31). Seize the Moment to Tackle Road Crash Deaths and Build a Safe and Sustainable Future. Available online: https://www.who.int/news/item/25-06-2023-seize-the-moment-to-tackle-road-crash-deaths-and-build-a-safe-and-sustainable-future.
3. Integrated Pairwise Testing based Genetic Algorithm for Test Optimization
4. A deep spatiotemporal network for forecasting the risk of traffic accidents in low-risk regions10.1007/s00521-022-07971-2 ↗
5. Prokhorenkova, L., Gusev, G., Vorobev, A., Dorogush, A.V., and Gulin, A. (2018, January 3–8). CatBoost: Unbiased boosting with categorical features. Proceedings of the 32nd International Conference on Neural Information Processing Systems, Montréal, QC, Canada.
6. Exploring Traffic Crash Occurrence Mechanism toward Cross-Area Freeways via an Improved Data Mining Approach10.1061/JTEPBS.0000698 ↗
7. Spatio-Temporal Feature Encoding for Traffic Accident Detection in VANET Environment10.1109/TITS.2022.3147826 ↗
8. Guru, J., and Devi, N. (2018). Road Traffic Accidents Analysis Using Data Mining Techniques. JITA-J. Inf. Technol. Appl.-APEIRON, 14.10.7251/JIT1702084J ↗
9. A literature review of machine learning algorithms for crash injury severity prediction10.1016/j.jsr.2021.12.007 ↗
10. Yaacob, N.F.F., Rusli, N., and Bohari, S.N. (2019, January 8–9). Relationship of Environmental Factors Toward Accident Cases using GIS Application in Kedah. Proceedings of the 2019 IEEE 15th International Colloquium on Signal Processing & Its Applications (CSPA), Penang, Malaysia.
11. Li, L., Shrestha, S., and Hu, G. (2017, January 7–9). Analysis of road traffic fatal accidents using data mining techniques. Proceedings of the 2017 IEEE 15th International Conference on Software Engineering Research, Management and Applications (SERA), London, UK.10.1109/SERA.2017.7965753 ↗
12. Wang, J., Ma, S., Jiao, P., Ji, L., Sun, X., and Lu, H. (2023). Analyzing the Risk Factors of Traffic Accident Severity Using a Combination of Random Forest and Association Rules. Appl. Sci., 13.10.3390/app13148559 ↗
13. A Road-Level Traffic Accident Risk Prediction Method
14. Survey of multi-class imbalanced data classification methods
15. Survey on imbalanced multi-class classification algorithms
16. Multi-granularity relabeled under-sampling algorithm for imbalanced data10.1016/j.asoc.2022.109083 ↗
17. Wei, W., Jiang, F., Yu, X., and Du, J. (2022, January 21–23). An Under-sampling Algorithm Based on Weighted Complexity and Its Application in Software Defect Prediction. Proceedings of the 2022 5th International Conference on Software Engineering and Information Management, Yokohama, Japan.10.1145/3520084.3520091 ↗
18. Oversampling With Reliably Expanding Minority Class Regions for Imbalanced Data Learning
19. SMOTE: Synthetic minority over-sampling technique
20. An Over Sampling Method of Unbalanced Data Based on Ant Colony Clustering10.1109/ACCESS.2021.3114443 ↗
21. Bennin, K.E., Keung, J., Phannachitta, P., Monden, A., and Mensah, S. (June, January 27). [Journal First] MAHAKIL: Diversity Based Oversampling Approach to Alleviate the Class Imbalance Issue in Software Defect Prediction. Proceedings of the 2018 IEEE/ACM 40th International Conference on Software Engineering (ICSE), Gothenburg, Sweden.10.1145/3180155.3182520 ↗
22. Wang, Q., Lee, K.J., and Hong, J. (2018, January 21–23). DOSS: Dual Over Sampling Strategy for Imbalanced Data Classification. Proceedings of the IECON 2018—44th Annual Conference of the IEEE Industrial Electronics Society, Washington, DC, USA.10.1109/IECON.2018.8591109 ↗
23. Towards hybrid over- and under-sampling combination methods for class imbalanced datasets: An experimental study10.1007/s10462-022-10186-5 ↗
24. A comprehensive review on ensemble deep learning: Opportunities and challenges
25. Automated COVID-19 Detection From Exhaled Human Breath Using CNN-CatBoost Ensemble Model10.1109/LSENS.2023.3318995 ↗
26. Spatial Distribution-Based Imbalanced Undersampling
27. Wu, Q., Lin, Y., Zhu, T., and Wei, J. (2019, January 2–4). HUSBoost: A Hubness-Aware Boosting for High-Dimensional Imbalanced Data Classification. Proceedings of the 2019 International Conference on Machine Learning and Data Engineering (iCMLDE).10.1109/iCMLDE49015.2019.00018 ↗
28. A cost-sensitive Imprecise Credal Decision Tree based on Nonparametric Predictive Inference10.1016/j.asoc.2022.108916 ↗
29. Chen, Y. (2021, January 28–30). Research on Cost-sensitive Classification Methods for Imbalanced Data. Proceedings of the 2021 International Conference on Artificial Intelligence, Big Data and Algorithms (CAIBDA), Xi’an, China.10.1109/CAIBDA53561.2021.00054 ↗
30. Exploring factors associated with crash severity on motorways in Pakistan
31. Moosavi, S., Samavatian, M.H., Parthasarathy, S., Teodorescu, R., and Ramnath, R. (2019, January 1–4). Accident 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, New York, NY, USA.10.1145/3347146.3359078 ↗
32. Moosavi, S., Samavatian, M.H., Parthasarathy, S., and Ramnath, R. (2019). A Countrywide Traffic Accident Dataset. arXiv.
33. Economic valuation of temperature-related mortality attributed to urban heat islands in European cities10.1038/s41467-023-43135-z ↗
34. Tracking lake drainage events and drained lake basin vegetation dynamics across the Arctic10.1038/s41467-023-43207-0 ↗
35. A Relief-PGS algorithm for feature selection and data classification10.3233/IDA-216493 ↗
36. An Improved MAHAKIL Oversampling Method for Imbalanced Dataset Classification10.1109/ACCESS.2020.3047741 ↗
37. Abdel-Basset, M., Mohamed, R., Abouhawwash, M., Chakrabortty, R.K., and Ryan, M.J. (2021). A Simple and Effective Approach for Tackling the Permutation Flow Shop Scheduling Problem. Mathematics, 9.10.3390/math9030270 ↗
38. Identification of Dry Bean Varieties Based on Multiple Attributes Using CatBoost Machine Learning Algorithm
39. Fire Prediction Based on CatBoost Algorithm10.1155/2021/1929137 ↗
40. Zhang, S., Liu, H., Yang, Y., Zhang, S., Zhang, Z., Wang, C., and Wang, M. (2023). SPIE Proceedings, SPIE.
41. Guyon, I., Nikravesh, M., Gunn, S., and Zadeh, L.A. (2006). Feature Extraction: Foundations and Applications, Springer.10.1007/978-3-540-35488-8 ↗
42. Haibo, H., Yang, B., Garcia, E.A., and Shutao, L. (2008, January 1–8). ADASYN: Adaptive synthetic sampling approach for imbalanced learning. Proceedings of the 2008 IEEE International Joint Conference on Neural Networks (IEEE World Congress on Computational Intelligence), Hong Kong, China.10.1109/IJCNN.2008.4633969 ↗
43. Schapire, R.E. (August, January 31). A brief introduction to boosting. Proceedings of the 16th International Joint Conference on Artificial Intelligence—Volume 2, Stockholm, Sweden.
44. Ye, J., Chow, J.-H., Chen, J., and Zheng, Z. (2009, January 2–6). Stochastic gradient boosted distributed decision trees. Proceedings of the 18th ACM Conference on Information and Knowledge Management, Hong Kong, China.10.1145/1645953.1646301 ↗
45. Chen, T., and Guestrin, C. (2016, January 13–17). XGBoost: A Scalable Tree Boosting System. Proceedings of the 22nd ACM SIGKDD International Conference on Knowledge Discovery and Data Mining, San Francisco, CA, USA.10.1145/2939672.2939785 ↗
46. Ke, G., Meng, Q., Finley, T., Wang, T., Chen, W., Ma, W., Ye, Q., and Liu, T.-Y. (2017, January 4–9). LightGBM: A highly efficient gradient boosting decision tree. Proceedings of the 31st International Conference on Neural Information Processing Systems, Long Beach, CA, USA.
47. A study of dealing class imbalance problem with machine learning methods for code smell severity detection using PCA-based feature selection technique10.1038/s41598-023-43380-8 ↗
48. MS_HGNN: A hybrid online fraud detection model to alleviate graph-based data imbalance10.1080/09540091.2023.2191893 ↗
49. Improving classification of mature microRNA by solving class imbalance problem10.1038/srep25941 ↗