1.School of Transportation Science and Engineering,Harbin Institute of Technology,Harbin 150090,China
2.National Engineering Laboratory for Prevention and Control Technology of Land Transport Meteorological Disasters,Yunnan Provincial Transportation Planning and Design Research Institute Co. ,Ltd. ,Kunming 650200,China
To improve the prediction accuracy and reduce the robustness of the traffic accident prediction model, this paper uses the Stacking integration strategy to construct an integrated traffic accident prediction model. Firstly, single traffic accident prediction models based on eight machine learning models, such as Decision Tree and Extra Tree, were constructed and the MIC test was used to measure the similarity of each traffic prediction model with the graph coloring method, and the models with low similarity and high diversity were selected to participate in the integration. Secondly, Box-Cox transformations were applied to the results of the single accident prediction models and different weights were assigned to each single model separately using feature weighting method. Finally, models such as BP neural network and Logistic regression were selected as meta-learners for Stacking integration. The results of the study show that the prediction accuracy of the integrated model with BP neural network selected for the meta-learner is higher than other integrated models, and the MAE and RMSE of the integrated model have been respectively reduced by 24% and 14% and the R2 has been improved by 6% compared to the single accident prediction model with the highest prediction accuracy.
选用最大信息系数(Maximal information coefficient,MIC)进行单一事故预测模型的预测结果相似度度量。对所选取的8种单一模型进行最大信息系数检验,其结果如表6和图2所示。通过检验结果可以看出,不同单一模型的相似性存在较大的差异,ET模型和GBDT模型之间的相似度接近1,说明两者的预测结果相似,可只选择一种模型参与后续模型集成;LightGBM模型和CatBoost模型相较于其他单一事故预测模型存在较大的差异。
ZhangXian-qiang, HeZhong-hua, LiangYong-na, et al. Fractal characteristics of road and its impact mechanism on traffic accidents in Guizhou Province[J]. Highway, 2017, 62(6): 197-203.
[3]
MacedoM R, MaiaM L A, RabbaniE R K, et al. Traffic accident prediction model for rural highways in Pernambuco[J]. Case Studies on Transport Policy, 2022, 10(1): 278-286.
MaZhuang-lin, ShaoChun-fu, LiXia. Analysis of factors affecting accident severity in highway tunnels based on Logistic model[J]. Journal of Jilin University(Engineering and Technology Edition), 2010, 40(2): 423-426.
ChenYing, YuanHua-zhi, HuangZhong-xiang, et al. Modeling intersection traffic crashes using a zero-truncated negative binomial model[J]. China Journal of Highway and Transport, 2020, 33(4): 146-154.
[8]
RolandJ, WayP D, FiratC, et al. Modeling and predicting vehicle accident occurrence in Chattanooga, Tennessee[J]. Accident Analysis & Prevention, 2021(149): 105-117.
[9]
IhuezeC C, OnwurahU O. Road traffic accidents prediction modelling: an analysis of Anambra State, Nigeria[J]. Accident Analysis & Prevention, 2018(7), 112: 21-29.
XieXue-bin, KongLing-yan. On the ways to the traffic accident prediction based on the ARIMA and XGBoost combined model[J]. Journal of Safety and Environment, 2021, 21(1): 277-284.
JiJun-hong, ChangRun-qi, WenTing-xin. Prediction of traffic accident death toll based on GSK-AdaBoost-LightGBM[J]. Safety and Environmental Engineering, 2021, 28(1): 24-28.
[14]
VilaaM, MacedoE, CoelhoM C. A rare event modelling approach to assess injury severity risk of vulnerable road users[J]. Safety, 2019, 5(2): 29-38.
[15]
XingL, HeJ, LiY, et al. Comparison of different models for evaluating vehicle collision risks at upstream diverging area of toll plaza[J]. Accident Analysis and Prevention, 2020(135): 86-97.
[16]
KwonO H, RheeW, YoonY, et al. Application of classification algorithms for analysis of road safety risk factor dependencies[J]. Accident Analysis and Prevention, 2015(75): 1-15.
[17]
ZengK H, ChouS H, ChanF H, et al. Agent-centric risk assessment: accident anticipation and risky region localization[C]∥Proceedings of the IEEE Conference on Computer Vision and Pattern Recognition, Honolulu, USA, 2017: 2222-2230.
NingJing, SheHong-yan, ZhaoDong, et al. A road-level traffic accident risk prediction method[J]. Journal of Beijing University of Posts and Telecommunications, 2022, 45(2): 72-78.
[20]
LinL, WangQ, SadekA W. A novel variable selection method based on frequent pattern tree for real-time traffic accident risk prediction[J]. Transportation Research Part C: Emerging Technologies, 2015(55): 444-459.
SunDi-hua, TangLiang, FuQing-song, et al. Road traffic accidents forecasting based on quantum neural network[J]. Journal of Transportation Systems Engineering and Information Technology, 2010, 10(5): 104-109.
QinWei. Neural network crash prediction model of freeway based on negative binomial regression analysis[D]. Harbin: School of Transportation Science and Engineering of Harbin Institute of Technology, 2017.
FanZhong-zhou, ZhaoYi, ZhouNing, et al. Integrated model for forecasting waterway traffic accidents based on the Gray-BP neural network[J]. Journal of Safety and Environment, 2020, 20(3): 857-861.