ABSTRACT
With the development of society, the number of vehicles increases rapidly. The vehicle plays an important role in people's life, however the problem of traffic safety caused by vehicles has also become increasingly prominent. In China, the high crash rate and casualty rate on expressways have always troubled traffic management department. So crash prediction on expressway becomes vital. Conventionally, crash prediction is based on traffic flow data. These data do not contain all the necessary factors. In this paper, we propose a method of prediction using real-world data, including historical accident data, road geometry data, vehicle speed data, and weather data. We treat the crash prediction problem as a binary classification problem. For classification, sample imbalanced is a great challenge in practice. Modifying sample weights is applied to handle this challenge. Three machine learning classification techniques, namely Random Forest (RF), Gradient Boosting Decision Tree (GBDT) and Xgboost, are considered to carry out the crash prediction task respectively. The best recall and precision rate of these models are respectively 0.764253 and 0.01062. The proposed method can be integrated into urban traffic control systems toward police dispatch and crash prevention.
- http://www.mps.gov.cn/n2255079/n5590589/n5747791/n5778470/c5776516/content.htmlGoogle Scholar
- Ren, H. et al. 2017. A Deep Learning Approach to the Prediction of Short-term Traffic Accident Risk. (2017).Google ScholarDigital Library
- Yuan, Q. et al. 2017. Cluster and factor analysis on data of fatal traffic crashes in China. International Conference on Transportation Information and Safety (2017), 211--224.Google Scholar
- Chang, L.Y. et al. 2012. Analysis of Freeway Accident Frequency using Multivariate Adaptive Regression Splines. Procedia Engineering. 45, 2 (2012), 824--829.Google ScholarCross Ref
- Gill, G. et al. 2017. Investigation of Roadway Geometric and Traffic Flow Factors for Vehicle Crashes Using Spatiotemporal Interaction. ISPRS - International Archives of the Photogrammetry, Remote Sensing and Spatial Information Sciences. XLII-2/W7, (2017), 1163--1166.Google Scholar
- Huang, Z. et al. 2017. Utilizing latent class logit model to predict crash risk. Ieee/acis International Conference on Computer and Information Science (2017), 161--165.Google Scholar
- Ahmed, M.M. and Abdel-Aty, M.A. 2012. The Viability of Using Automatic Vehicle Identification Data for Real-Time Crash Prediction. IEEE Transactions on Intelligent Transportation Systems. 13, 2 (2012), 459--468. Google ScholarDigital Library
- Sun, J. and Sun, J. 2016. Real-time crash prediction on urban expressways: identification of key variables and a hybrid support vector machine model. Iet Intelligent Transport Systems. 10, 5 (2016), 331--337.Google ScholarCross Ref
- Abdel-Aty, M. et al. 2004. Predicting Freeway Crashes from Loop Detector Data by Matched Case-Control Logistic Regression. Transportation Research Record Journal of the Transportation Research Board. 1897, 1 (2004), 88--95.Google ScholarCross Ref
- Sun, P. et al. 2017. Traffic crash prediction based on incremental learning algorithm. IEEE International Conference on Big Data Analysis (2017), 182--185.Google Scholar
- You, J. et al. 2017. Real-time crash prediction based on high definition monitoring systems. IEEE International Conference on Intelligent Transportation Engineering (2017), 208--211.Google Scholar
- Chen, Q. et al. 2016. Learning deep representation from big and heterogeneous data for traffic accident inference. Proceedings of the Thirtieth AAAI Conference on Artificial Intelligence (2016), 338--344. Google ScholarDigital Library
- Abdel-Aty, M.A. and Pemmanaboina, R. 2006. Calibrating a real-time traffic crash-prediction model using archived weather and ITS traffic data. IEEE Transactions on Intelligent Transportation Systems. 7, 2 (2006), 167--174. Google ScholarDigital Library
- Xu, X. and Duan, L. 2017. Predicting Crash Rate Using Logistic Quantile Regression with Bounded Outcomes. IEEE Access. PP, 99 (2017), 1--1.Google Scholar
- Alkheder, S. et al. 2016. Severity Prediction of Traffic Accident Using an Artificial Neural Network. Journal of Forecasting. 36, 1 (2016).Google Scholar
- Najada, H.A. and Mahgoub, I. 2016. Big vehicular traffic Data mining: Towards accident and congestion prevention. Wireless Communications and Mobile Computing Conference (2016).Google Scholar
- Rodriguez-Galiano, V.F. et al. 2012. An assessment of the effectiveness of a random forest classifier for land-cover classification. Isprs Journal of Photogrammetry & Remote Sensing. 67, 1 (2012), 93--104.Google ScholarCross Ref
- Wang, Y. et al. 2016. A mobile recommendation system based on logistic regression and Gradient Boosting Decision Trees. International Joint Conference on Neural Networks (2016), 1896--1902.Google Scholar
- Chen, T. and Guestrin, C. 2016. XGBoost:A Scalable Tree Boosting System. ACM SIGKDD International Conference on Knowledge Discovery and Data Mining (2016), 785--794. Google ScholarDigital Library
- Ly, A. et al. 2018. Analytic posteriors for Pearson's correlation coefficient. Statistica Neerlandica. 72, 1 (2018), 4--13.Google ScholarCross Ref
- Dai, J. and Xu, Q. 2013. Attribute selection based on information gain ratio in fuzzy rough set theory with application to tumor classification. Elsevier Science Publishers B. V. Google ScholarDigital Library
- Plackett, R.L. 1983. Karl Pearson and the Chi-Squared Test. International Statistical Review. 51, 1 (1983), 59--72.Google ScholarCross Ref
- He, H. and Garcia, E.A. 2009. Learning from Imbalanced Data. IEEE Transactions on Knowledge & Data Engineering. 21, 9 (2009), 1263--1284. Google ScholarDigital Library
- Holte, R. et al. 1989. Concept Learning and the Problem of Small Disjuncts. University of Texas at Austin. Google ScholarDigital Library
- Kohavi, R. 1995. A study of cross-validation and bootstrap for accuracy estimation and model selection. International Joint Conference on Artificial Intelligence (1995), 1137--1143. Google ScholarDigital Library
- Pedregosa, F. et al. 2013. Scikit-learn: Machine Learning in Python. Journal of Machine Learning Research. 12, 10 (2013), 2825--28 Google ScholarDigital Library
Index Terms
- Expressway Crash Prediction based on Traffic Big Data
Recommendations
Calibrating a real-time traffic crash-prediction model using archived weather and ITS traffic data
Growing concern over traffic safety has led to research efforts directed towards predicting freeway crashes in Advanced Traffic Management and Information Systems (ATMIS) environment. This paper aims at developing a crash-likelihood prediction model ...
A Novel Traffic Prediction System based on Floating Car Data and Machine Learning
NISS '19: Proceedings of the 2nd International Conference on Networking, Information Systems & SecurityIntelligent Transportation Systems have become a necessity with the increasing number of cars running, especially in the urban roads. This paper presents a novel system capable to forecast the traffic in the urban road networks. This study aims to ...
A driver’s car-following behavior prediction model based on multi-sensors data
AbstractThe prerequisite for the effective operation of vehicle collision warning system is that the necessary operation is not implemented. Therefore, the behavior prediction that the driver should perform when the preceding vehicle braking is the key to ...
Comments