Railway Traffic Accident Forecast Based on an Optimized Deep Auto-encoder

  • Fenling Feng Central South University
  • Wan Li Central South University
  • Qiwei Jiang Central South University
Keywords: railway traffic accident, deep auto-encoder, particle swarm optimization algorithm

Abstract

Safety is the key point of railway transportation, and railway traffic accident prediction is the main content of safety management. There are complex nonlinear relationships between an accident and its relevant indexes. For this reason, triangular gray relational analysis (TGRA) is used for obtaining the indexes related to the accident and the deep auto-encoder (DAE) for finding out the complex relationships between them and then predicting the accident. In addition, a nonlinear weight changing particle swarm optimization algorithm, which has better convergence and global searching ability, is proposed to obtain better DAE structure and parameters, including the number of hidden layers, the number of neurons at each hidden layer and learning rates. The model was used to forecast railway traffic accidents at Shenyang Railway Bureau, Guangzhou Railway Corporation, and Nanchang Railway Bureau. The results of the experiments show that the proposed model achieves the best performance for predicting railway traffic accidents.

Author Biographies

Fenling Feng, Central South University

FENLING FENG earned her Ph.D degree from Central South University in 2009 and now she is an associate professor at Central South University. Her research interests include transportation enterprise marketing, railway logistics, international multimodal transport and so on.

Wan Li, Central South University

Wan Li earned his B.E. degree from Changsha University of Science and Technology in 2015 and he is studying at Central South University for pursuing a M.E. degree.

Qiwei Jiang, Central South University

Qiwei Jiang earned his Ph.D degree from Central South University and now he is an associate professor at Central South University. Her research interests include logistics and transportation economic management, logistics and transportation system analysis.

References

[1] Feng F, Xu Y, Tang Z. Research on the charge rate of railway value-guaranteed transportation based on competitive and cooperative relationships. Advances in Mechanical Engineering. 2018;10(1): 1-11.
[2] Ma X, Li K, Luo Z, Zhou J. Analyzing the causation of a railway accident based on a complex network. Chinese Physics B. 2014;23(2): 1674-1056.
[3] Ross DA, Jodi LC. An alternative accident prediction model for highway-rail interfaces. Accident Analysis and Prevention. 2002;34(1): 31-42.
[4] Oh J, Washington SP, Nam D. Accident prediction model for railway-highway interfaces. Accident Analysis and Prevention. 2006;38(2): 346−356.
[5] Yan X, Stephen R, Su X. Using hierarchical tree-based regression model to predict train-vehicle crashes at passive highway-rail grade crossings. Accident Analysis and Prevention. 2010;42(1): 64-74.
[6] Lu P, Tolliver D. Accident prediction model for public highway-rail grade crossings. Accident Analysis and Prevention. 2016;90: 73-81.
[7] Wen C. Prediction methods of train operation conflict for high-speed railway. Journal of Transportation Security. 2010;3(4): 275-286.
[8] Akram KG B, Farnoosh N, Viliam M. Highway accident modeling and forecasting in winter. Transportation Research Part A: Policy and Practice. 2014;59: 384-396.
[9] Mao M, Chirwa EC. Application of grey model GM(1, 1) to vehicle fatality risk estimation. Technological Forecasting and Social Change. 2006;73(5): 588-605.
[10] Darin A, Blent A. A neural network (NN) model to predict intersection crashes based upon driver, vehicle and roadway surface characteristics. Scientific Research and Essays. 2010;5(19): 2837-2847.
[11] Seung GK, Young GN, Poong HS. Prediction of severe accident occurrence time using support vector machines. Nuclear Engineering and Technology. 2015;47(1): 74-84.
[12] Qu X, Wang W, Wang W, Liu P. Real-time freeway sideswipe crash prediction by support vector machine. Intelligent Transport Systems. 2013;7(4): 445-453.
[13] Partheeban P, Arunbabu E, Hemamalini RR. Road accident cost prediction model using systems dynamics approach. Transport. 2008;23(1): 59-66.
[14] Muhammed YÇ, Ahmet T. An artificial neural network model for highway accident prediction: a case study of Erzurum, Turkey. Promet – Traffic & Transportation. 2015;27(3): 217-225.
[15] Jafari SA, Jahandideh S, Jahandideh M, Asadabadi EB. Prediction of road traffic death rate using neural networks optimised by genetic algorithm. International Journal of Injury Control and Safety Promotion. 2015;22(2): 153-157.
[16] Zhang J, Duan L, Guo J. A genetic algorithm-based BP neural network method for operational performance assessment of ATC sector. Promet – Traffic & Transportation. 2016;28(6): 563-574.
[17] Ding S, Su C, Yu J. An optimizing BP neural network algorithm based on genetic algorithm. Artificial Intelligence Review. 2011;36(2): 153-162.
[18] Hinton GE, Osinder S, Teh YW. A fast learning algorithm for deep belief nets. Neural Computation. 2006;18(7): 1527-1554.
[19] Bo G, Rui Z, Guang X, Chuangming S, Li Y. Predicting students performance in educational data mining. Proceedings of the 2015 International Symposium on Educational Technology; 2015 Jul 27-29; Wuhan, China: IEEE; 2015.
[20] Li N, Lu G, Li X, Yan Y. Prediction of NOx emissions from a biomass fired combustion process based on flame radical imaging and deep learning techniques. Combustion Science and Technology. 2016;188(2): 233-246.
[21] Ong B, Sugiura K, Zettsu K. Dynamically pre-trained deep recurrent neural networks using environmental monitoring data for predicting PM2.5. Neural Computing and Applications. 2016;27(6): 1553-1566.
[22] Kuremoto T, Kimura S, Kobayashi K, Obayashi M. Time series forecasting using a deep belief network with restricted Boltzmann machines. Neurocomputing. 2014;137: 47-56.
[23] Shao H, Jiang H, Zhang X, Niu M. Rolling bearing fault diagnosis using an optimization deep belief network. Measurement Science and Technology. 2015;26(11): 115002.
[24] Cheng G, Yin J, Liu N. Estimation of geophysical properties of sandstone reservoir based on hybrid imensionality
reduction with Elman neural networks. Applied Mechanics and Materials. 2014;668-669: 1509-1512.
[25] Bengio Y, Delalleau O. On the expressive power of deep architectures. Algorithmic Learning Theory. 2011;6925: 18-36.
[26] Song C, Huang Y, Liu F, Wang Z, Wang L. Deep auto-encoder based clustering. Intelligent Data Analysis. 2014;18(6): S65-S76.
[27] Suganthan PN, Hansen N, Liang JJ. Problem definitions and evaluation criteria for the CEC 2005 special session on real-parameter optimization. Singapore: Nanyang Technological University. 2005: 1−50. Available from: http://decsai.ugr.es/~lozano/AEBs-Continuo/Tech-Report-May-30-05.pdf
[28] Shi YH, Eberhart R. A modified particle swarm optimizer. Proceedings of the IEEE International Conference on Evolutionary Computation; 1998 May 4-9; Anchorage, Alaska, USA: IEEE; 1999.
[29] Zhang J, Zhang J, Lok T, Michael RL. A hybrid particle swarm optimization-backpropagation algorithm for feedforward neural network training. Applied Mathematics and Computation. 2007;185: 1026-1037.
Published
2018-08-29
How to Cite
1.
Feng F, Li W, Jiang Q. Railway Traffic Accident Forecast Based on an Optimized Deep Auto-encoder. Promet - Traffic & Transportation [Internet]. 29Aug.2018 [cited 15Oct.2018];30(4):379-94. Available from: http://www.fpz.unizg.hr/traffic/index.php/PROMTT/article/view/2568
Section
Articles