A Novel Hybrid Model Based on Rule Learning and Dilated Convolution for Vehicle Collision Prediction


autonomous driving
collision prediction
dilated convolution
rule learning
feature construction

How to Cite

Wu, N., Liu, X., & lv , Z. (2024). A Novel Hybrid Model Based on Rule Learning and Dilated Convolution for Vehicle Collision Prediction. Annals of Applied Sciences. https://doi.org/10.55085/aas.2024.720


Vehicle collisions are a significant concern in road accidents, particularly with the rise of autonomous driving technology. However, existing studies often struggle to accurately predict collisions due to inconsistent correlations between collected data and collision labels. Therefore, this work quantitatively analyzes traffic accident data and constructs new features with strong correlations to the labels. In this study, a rule classification-dilated convolution network (R-DCN) model, which combines rule learning with dilated convolutional networks, is proposed. The rule learning model predicts partially collided vehicles using predefined rules, resulting in interpretability, high prediction efficiency, and quick computation. The remaining vehicle collisions are estimated using dilated convolutional layers, addressing the issue of missing important features in conventional convolution models. To distinguish between intense collisions (predicted by rule learning) and nonintense collisions (predicted by the dilated convolutional model), the data for training the network are those that remove the intense collision predicted by the rule learning model. The proposed model exhibits enhanced sensitivity to nonintense collision data. Compared to existing models, the approach presented in this work demonstrates superior evaluation metrics and training speed.



Xu Z, Lv Z, Chu B, Sheng Z, Li J. Progress and prospects of future urban health status prediction. Eng Appl Artif Intell. 2024; 129: 107573. https://doi.org/10.1016/j.engappai.2023.107573

Lv Z, Wang X, Cheng Z, Li J, Li H, Xu Z. A new approach to COVID-19 data mining: A deep spatial–temporal prediction model based on tree structure for traffic revitalization index. Data Knowl Eng. 2023 Jul; 146:102193. https://doi.org/10.1016/j.datak.2023.102193

Wang X, Liu J, Qiu T, Mu C, Chen C, Zhou P. A real-time collision prediction mechanism with deep learning for intelligent transportation system. IEEE transactions vehic tech. 2020; 69(9): 9497-9508. https://doi.org/10.1109/TVT.2020.3003933

Fujita Y, Akuzawa K, Sato M. Radar brake system. J sae Review. 1995; 1(16): 113. https://doi.org/10.1016/0389-4304(95)94949-N

Kononen DW, Flannagan CA, Wang SC. Identification and validation of a logistic regression model for predicting serious injuries associated with motor vehicle crashes. Accid Anal Prev. 2011 Jan;43(1):112-22. https://doi.org/10.1016/j.aap.2010.07.018

Gerla M, Lee EK, Pau G, Lee U. Internet of vehicles: From intelligent grid to autonomous cars and vehicular clouds. IEEE world forum on internet of things (WF-IoT). 2014; 241-246. https://doi.org/10.1109/WF-IoT.2014.6803166

Huang T, Wang S, Sharma A. Highway crash dectection and risk estimation using deep learning. Accid Anal Prevent. 2020; 135: 105392. https://doi.org/10.1016/j.aap.2019.105392

Yuan J, Abdel-Aty M, Gong Y, Cai Q. Real-time crash risk prediction using long short-term memory recurrent neural network. Transport research record. 2019; 2673(4): 314-326. https://doi.org/10.1177%2F0361198119840611

Qiu T, Li B, Qu W, Ahmed E, Wang X. TOSG: A topology optimization scheme with global small world for industrial heterogeneous Internet of Things. IEEE Transactions Industr Infor. 2018; 15(6): 3174-3184. https://doi.org/10.1109/TII.2018.2872579

Wang X, Fan T, Chen M, Deng B, Wu B, Tremont P. Safety modeling of urban arterials in Shanghai, China. Accident Analysis Prevent. 2015: 83; 57-66. https://doi.org/10.1016/j.aap.2015.07.004

Xu C, Wang W, Liu P. A genetic programming model for real-time crash prediction on freeways. IEEE Transactions on Intelligent Transportation Systems. 2012; 14(2): 574-586. https://doi.org/10.1109/TITS.2012.2226240

Lee D, Yeo H. Real-time rear-end collision-warning system using a multilayer perceptron neural network. IEEE Transactions on Intelligent Transportation Systems. 2016; 17(11): 3087-3097. https://doi.org/10.1109/TITS.2016.2537878

Chawla NV, Bowyer KW, Hall LO, Kegelmeyer WP. SMOTE: synthetic minority over-sampling technique. J artificial intelligence research. 2002; 16: 321-357. https://doi.org/10.1613/jair.953

Li J, Cheng K, Wang S, Morstatter F, Trevino RP, Tang J, et al. Feature selection: A data perspective. ACM computing surveys (CSUR). 2017; 50(6): 1-45. https://doi.org/10.1145/3136625

Benesty J, Chen J, Huang Y. On the importance of the Pearson correlation coefficient in noise reduction. IEEE/ACM Trans. Audio Speech Lang. Process. 2008; 16(4): 757-765. http://dx.doi.org/10.1109/TASL.2008.919072

Stahl DO. Boundedly rational rule learning in a guessing game. Games Eco Behav. 1996; 16(2): 303-330. https://doi.org/10.1006/game.1996.0088

Basso F, Basso LJ, Bravo F, Pezoa R. Real-time crash prediction in an urban expressway using disaggregated data. Transp Res Part C Emerg techn. 2018; 86: 202-219. https://doi.org/10.1016/j.trc.2017.11.014

Cai Q, Abdel-Aty M, Yuan J, Lee J, Wu Y. Real-time crash prediction on expressways using deep generative models. Transp Res Part C Emerg techn. 2020 ; 117 : 102697. https://doi.org/10.1016/j.trc.2020.102697

Wang L, Abdel-Aty M, Lee J, Shi Q. Analysis of real-time crash risk for expressway ramps using traffic, geometric, trip generation, and socio-demographic predictors. Accid Anal Prev. 2019 Jan;122:378-384. https://doi.org/10.1016/j.aap.2017.06.003

O'Shea K, Nash R. An introduction to convolutional neural networks. arXiv. 2015; 1511 08458. https://doi.org/10.48550/arXiv.1511.08458

Li J, Yuan G, Yang Z. Edge-assisted Object Segmentation Using Multimodal Feature Aggregation and Learning. ACM Transactions on Sensor Net. 2023; 20(1): 1-22. https://doi.org/10.1145/3612922

Sheng Z, Lv Z, Li J, Xu Z, Sun H, Liu X, et al. Taxi travel time prediction based on fusion of traffic condition features. Computers Elect Engin. 2023; 105: 108530. https://doi.org/10.1016/j.compeleceng.2022.108530

Gu S, Yang L, Li Y, Li H. Multi-label Learning by Exploiting Imbalanced Label Correlations. In Pacific Rim International Conference on Artificial Intelligence. 2021; 585-596. https://doi.org/10.1007/978-3-030-89363-7_44

Xu Z, Lv Z, Chu B, Li J. Fast autoregressive tensor decomposition for online real-time traffic flow prediction. Knowledge-Based Systems. 2023; 282: 111125. https://doi.org/10.1016/j.knosys.2023.111125

Lv Z, Li J, Dong C, Li H, Xu Z. Deep learning in the COVID-19 epidemic: A deep model for urban traffic revitalization index. Data Knowl Eng. 2021 Sep:135:101912. https://doi.org/10.1016/j.datak.2021.101912

Lv Z, Li J, Xu Z, Wang Y, Li H. (). Parallel computing of spatio-temporal model based on deep reinforcement learning. In International Conference on Wireless Algorithms, Systems, and Applications. Cham: Springer International Publishing. 2021 Jun; 391-403. https://doi.org/10.1007/978-3-030-85928-2_31

Fenili A. Nonlinear velocity and shape control of a rotating smart flexible beam-like structure. Annals of Applied Sciences. 2022. https://doi.org/10.55085/aas.2022.669

Li J, Lv Z, Ma Z, Wang X, Xu Z. Optimization of spatial-temporal graph: A taxi demand forecasting model based on spatial-temporal tree. Info Fusion. 2024; 104: 102178. https://doi.org/10.1016/j.inffus.2023.102178

Lv Z, Cheng Z, Li J, Xu Z, Yang Z. TreeCN: time series prediction with the tree convolutional network for traffic prediction. IEEE Transactions on Intelligent Transportation Systems. 2023.

Creative Commons License

This work is licensed under a Creative Commons Attribution 4.0 International License.

Copyright (c) 2024 Wu N et al.