پیش‌بینی ایمنی ترافیک با استفاده از روش بهینه‌سازی گروه‌ ذرات و ماشین ‌راهنمای ‌پشتیبان

نوع مقاله : مقاله پژوهشی

نویسندگان

1 دانشکده عمران دانشگاه علم و صنعت ایران

2 دانشکده عمران، دانشگاه علم و صنعت ایران،

3 دانشکده عمران، دانشگاه علم و صنعت ایران

4 دانشکده مهندسی، دانشگاه فردوسی مشهد، مشهد، ایران

5 دانشکده مهندسی، دانشگاه فردوسی مشهد، مشهد، ایران.

چکیده

تصادفات جاده‌ای و تلفات ناشی از آن ‌یکی از چالش‌های کنونی جوامع بشری است که هزینه‌های اقتصادی زیادی را بر اقتصاد کشورها تحمیل نموده است. با توجه به اطلاعات مربوط به ایمنی ترافیک در مطالعات پیشین، تعیین برنامه‌ریزی ایمنی ترافیک با پیش‌بینی افزایش تصادفات رانندگی، بسیار حائز اهمیت می‌باشد. مدل های شبکه عصبی استفاده شده در این زمینه دارای خلاءهایی همچون ضعف در نقاط با تعداد تصادفات صفر و تفاوت نتایج در هر بار آزمایش می­باشند، در این مطالعه به‌منظور حل مشکلات شبکه عصبی پس انتشار، یک روش جدید که ترکیب بهینه‌سازی گروه­ ذرات و ماشین ­راهنمای ­پشتیبان (PSO-SVM) می­باشد با هم ترکیب می شوند تا به منظور پیش‌بینی ایمنی ترافیک مورد استفاده قرار گیرد. ابتدا عوامل مؤثر بر ایمنی ترافیک و شاخص‌های ارزیابی مورد تجزیه‌وتحلیل قرار می‌گیرند، سپس مدل پیش‌بینی ایمنی ترافیک توسط بهینه‌سازی گروه­ ذرات و ماشین ­راهنمای ­پشتیبان با­توجه به عوامل مؤثر ایجاد می­شود. در نهایت، داده‌های مربوط به ایمنی ترافیک از سال 1376 تا 1397 برای تحقیق در مورد توانایی پیش‌بینی روش پیشنهادی بکار گرفته می‌شوند. نتایج تجربی نشان می‌دهد که پیش‌بینی ایمنی ترافیک توسط بهینه‌سازی گروه­ ذرات و ماشین ­راهنمای ­پشتیبان برتر از شبکه عصبی پس انتشار است. مقادیر میانگین مطلق خطا برای پیش‌بینی تعداد تصادفات توسط بهینه‌سازی گروه­ ذرات و ماشین ­راهنمای ­پشتیبان و شبکه عصبی پس انتشار به ترتیب مقادیر 0281/0 و 0498/0 را به خود اختصاص دادند. مدل‌های ساخته شده در این مطالعه دارای نوسانات بیشتری نسبت به داده‌های مشاهده می­باشند، بنابراین می‌توان به­منظور تنظیم مدل‌های مذکور، مدل‌های دقیق­تری ایجاد نمود. میزان خطا در مدل های مربوط به تعداد مجروحین کمتر از داده‌های تعداد تصادفات و تلفات می‌باشد، که می‌توان علت این موضوع را به تعداد داده‌های بیشتر مربوط دانست.

کلیدواژه‌ها


عنوان مقاله [English]

Predicting Traffic Safety Using PSO-SVM Method and Back Propagation Neural Network

نویسندگان [English]

  • Mahmoud Ameri 1
  • hamid bigdeli rad 1
  • Hamid Shaker 2
  • Amirhosein Ameri 1
  • Seyed Amir Saadatjoo 3
  • Saeed Fatemi 4
  • Seyed Ali Ziaee 5
1 Director of Department of Road and Transportation, Faculty of Civil Engineering, University of Science and Technology
2 Department of Civil Engineering, Iran University of Science and Technology,
3 Faculty of Civil Engineering, Iran University of Science and Technology
4 Department of Civil Engineering, Faculty of Engineering, Ferdowsi University of Mashhad, Mashhad, Iran
5 Department of Civil Engineering, Faculty of Engineering, Ferdowsi University of Mashhad, Mashhad, Iran.
چکیده [English]

Road accidents and the resulting casualties are one of the current challenges of human societies that have imposed great economic costs on the economies of countries. Given the information on traffic safety in previous studies, it is very important to determine traffic safety planning in anticipation of an increase in traffic accidents. The neural network models used in this field have gaps. In this study, in order to solve the neural network problems after diffusion, a new method that combines particle group optimization and support machine (PSO - SVM) combined to be used to predict traffic safety. First, the factors affecting traffic safety and evaluation indicators are analyzed, then the traffic safety forecasting model is created by PSO - SVM according to the effective factors. Finally, traffic safety data from 1997 to 2018 are used to investigate the predictive ability of the proposed method. Experimental results show that traffic safety prediction by PSO - SVM is superior to post - diffusion neural network. MAPE values for predicting the number of events by PSO-SVM and post-diffusion neural network were 0.0281 and 0.0498, respectively. Models have more fluctuations than observation data, so more accurate models can be created to adjust these models. Due to the fact that the error in the data related to the number of injured is less than the data on the number of accidents and casualties, the cause can be related to the number of more data

کلیدواژه‌ها [English]

  • Neural Network
  • PSO
  • SVM
  • Traffic Safety Methods
  • Back Propagation Algorithm
  1. Ameri, A., Bigdeli Rad, H., Shaker, H., & Ameri, M., "Cellular Transmission and Optimization Model Development to Determine the Distances between Variable Message Signs",Journal of Transportation Infrastructure Engineering, 7(1), (2021).
  2. Rad, V. B., Najafpour, H., Ngah, I., Shieh, E., Rashvand, P., & Rad, H. B., "What Are The Safety Factors Associating with Physical Activity in Urban Neighborhoods?(A Systematic Review)",Journal of Applied Environmental and Biological Sciences, Vol. 5(3), pp. 259-266, (2015).
  3. Abdi, A., Mosadeq, Z., & Bigdeli Rad, H., "Prioritizing Factors Affecting Road Safety Using Fuzzy Hierarchical Analysis", Journal of Transportation Research,Vol. 17(3), pp. 33-44, (2020).
  4. Xiao, J., "SVM and KNN ensemble learning for traffic incident detection. Physica A: Statistical Mechanics and its Applications", Vol. 517, pp. 29-35, (2019).
  5. Huang, J., Zhou, J., Wang, Z., wang, Q., & Peng, Y., "Network Anomaly Traffic Classification and Optimization Based on PSO-SVM", In Proceedings of the 2nd International Conference on Artificial Intelligence and Advanced Manufacture, Vol. 9, pp. 173-180, October, (2020).
  6. Duan, M., "Short-time prediction of traffic flow based on PSO optimized SVM", In 2018 international conference on intelligent transportation, big data & smart city (ICITBS), Vol. 34, pp. 41-45, IEEE, January, (2018).
  7. Radja, D. I. A. F., TOLBA, C., & Moh, A. N. S., "Traffic Urban Control Using an Intelligent PSO Algorithm Based on Integrated Approach", (2020).
  8. Ali, E. M., Ahmed, M. M., & Wulff, S. S., "Detection of critical safety events on freeways in clear and rainy weather using SHRP2 naturalistic driving data: Parametric and non-parametric techniques", Safety Science,Vol. 119, pp. 141-149, (2019).
  9. Rovšek, V., Batista, M., & Bogunović, B., "Identifying the key risk factors of traffic accident injury severity on Slovenian roads using a non-parametric classification tree", Transport,Vol. 32(3), pp. 272-281, (2017).
  10. Duo, M., Qi, Y., Lina, G., & Xu, E., "A short-term traffic flow prediction model based on EMD and GPSO-SVM", In 2017 IEEE 2nd Advanced Information Technology, Electronic and Automation Control Conference (IAEAC), Vol. 15, pp. 2554-2558, IEEE, March, (2017).
  11. Shaker, H., & Bigdeli Rad, H., "Evaluation and Simulation of New Roundabouts Traffic Parameters by Aimsun Software", Journal of Civil Engineering and Materials Application,Vol. 2(3), pp. 146-158, (2018).
  12. Sarkar, S., Vinay, S., Raj, R., Maiti, J., & Mitra, P., "Application of optimized machine learning techniques for prediction of occupational accidents", Computers & Operations Research,Vol. 106, pp. 210-224, (2019).
  13. Bener, A., Al Maadid, M. G. A., zkan, T., Al-Bast, D. A. E., Diyab, K. N., & ajunen, T., "The impact of four-wheel drive on risky driver behaviours and road traffic accidents", Transportation Research Part F: Traffic Psychology and Behaviour, Vol. 11(5), pp. 324–333, (2008).
  14. Bonnet, E., Lechat, L., & Ridde, V., "What interventions are required to reduce road traffic injuries in Africa? A scoping review of the literature", PLoS One,Vol. 13(11), e0208195, (2018).
  15. Aldegheishem, A., Yasmeen, H., Maryam, H., Shah, M. A., Mehmood, A., Alrajeh, N., & Song, H., "Smart road traffic accidents reduction strategy based on intelligent transportation systems (tars)", Sensors, Vol. 18(7), pp. 1983, (2018).
  16. Marusin, A., Marusin, A., & Ablyazov, T., "Transport infrastructure safety improvement based on digital technology implementation", In International Conference on Digital Technologies in Logistics and Infrastructure (ICDTLI 2019), pp. 348-352, Atlantis Press, September, (2019).
  17. Najaf, P., Isaai, M. T., Lavasani, M., & Thill, J. C., "Evaluating traffic safety policies for developing countries based on equity considerations", Journal of Transportation Safety & Security,9(sup1), pp. 178-203, (2017).
  18. Lee, J.-Y., Chung, J.-H., & Son, B., "Analysis of traffic accident size for Korean highway using structural equation models", Accident Analysis and Prevention, Vol. 40(6), pp. 1955–1963, (2008).
  19. Kweon, K. S., Moon, J. M., Kyung-Kyu, K. I. M., Chang, Y. B., & Jung, J. S., U.S. Patent No. 10,163,342. Washington, DC: U.S. Patent and Trademark Office, (2018).
  20. Yilma, H., Rimal, R., & Ryskulova, N., "Road Traffic Behaviors by Gender in Serbia", Health Science Research commons, Vol. 2, pp.214-223, (2017).
  21. Zheng, X. I. A. O., Ye, T. I. A. N., Dongsheng, C. A. O., & ZHANG, Z., "Road Traffic Risk Safety Prediction Based on BP Neural Network", In 2020 IEEE 9th Joint International Information Technology and Artificial Intelligence Conference (ITAIC), Vol. 9, pp. 527-533, IEEE, December, (2020).
  22. Wu, D., & Wang, S., "Comparison of road traffic accident prediction effects based on SVR and BP neural network", In 2020 IEEE International Conference on Information Technology, Big Data and Artificial Intelligence (ICIBA), Vol. 1, pp. 1150-1154, IEEE, November, (2020).
  23. Goniewicz, K., Goniewicz, M., Pawłowski, W., & Fiedor, P., "Road accident rates: strategies and programmes for improving road traffic safety", European journal of trauma and emergency surgery,Vol. 42(4), pp. 433-438, (2016).
  24. Mallia, L., Lazuras, L., Violani, C., & Lucidi, F., "Crash risk and aberrant driving behaviors among bus drivers: the role of personality and attitudes towards traffic safety", Accident Analysis & Prevention,Vol. 79, pp. 145-151, (2015).
  25. Pedrycz, W., Park, B. J., & Pizzi, N. J., "Identifying core sets of iscriminatory features using particle swarm optimization", Expert Systems with Applications, Vol. 36(3), pp. 4610–4616, (2009).
  26. Jun, C., Congying, L., & Guangming, D., "Traffic safety assessment of freeway based on BP neural network", Journal of Tongji University Natural Science,7, Vol. 36, pp. 83-92, (2008).
  27. Gang, R., & Zhuping, Z., "Traffic safety forecasting method by particle swarm optimization and support vector machine", Expert Systems with Applications,Vol. 38(8), pp. 10420-10424, (2011).
  28. Cui, J., Zhang, H., Zhao, J., & Zhang, Y., "Research on SVM-Based Highway Traffic Safety Evaluation Model", In International Conference on Green Intelligent Transportation System and Safety, pp. 799-809, Springer, Singapore, July, (2017).
  29. Doğan, A. A. E., & ANgüngör, A. P., "Estimating road accidents of Turkey based on regression analysis and artificial neural network approach",Advances in transportation studies,Vol. 16, 11Y22, (2008).
  30. Afandi, Z. S., Bigdeli, R. H., & Shaker, H. (2019). Using optimization and metaheuristic method to reduce the bus headway (Case study: Qazvin Bus Routes).
  31. Yasin Çodur, M., & Tortum, A., "An artificial neural network model for highway accident prediction: A case study of Erzurum", Turkey. PROMET-Traffic&Transportation,Vol. 27(3), pp. 217-225, (2015).
  32. Graham, D. J., Naik, C., McCoy, E. J., & Li, H., "Do speed cameras reduce road traffic collisions?", PLoS one,Vol. 14(9), e0221267, (2019).
  33. Chokotho, L., Mulwafu, W., Singini, I., Njalale, Y., Maliwichi-Senganimalunje, L., & Jacobsen, K. H., "First responders and prehospital care for road traffic injuries in Malawi", Prehospital and disaster medicine,Vol. 32(1), pp. 14, (2017).
  34. Anstey, K. J., Eramudugolla, R., Ross, L. A., Lautenschlager, N. T., & Wood, J., "Road safety in an aging population: risk factors, assessment, interventions, and future directions", International Psychogeriatrics,Vol. 28(3), pp. 349-356, (2016).
  35. Linder, A., & Svensson, M. Y., "Road safety: the average male as a norm in vehicle occupant crash safety assessment", Interdisciplinary Science Reviews,Vol. 44(2), pp. 140-153, (2019).
  36. Castillo-Manzano, J. I., Castro-Nuño, M., & Fageda, X., "Can cars and trucks coexist peacefully on highways? Analyzing the effectiveness of road safety policies in Europe", Accident Analysis & Prevention,Vol. 77, pp. 120-126, (2015).
  37. Jain, P., Rahman, I., & Kulkarni, B. D., "Development of a soft sensor for a batch distillation column using support vector regression techniques", Chemical, (2007).
  38. Tasgetiren, M. F., Liang, Y.-C., Sevkli, M., & Gencyilmaz, G., "A particle swarm optimization algorithm for makespan and total flowtime minimization in the permutation flowshop sequencing problem", European Journal of Operational Research, Vol. 177(3), pp. 1930–1947, (2007).
  39. Nobile, M. S., Besozzi, D., Cazzaniga, P., Mauri, G., & Pescini, D., "A GPU-based multi-swarm PSO method for parameter estimation in stochastic biological systems exploiting discrete-time target series", In European Conference on Evolutionary Computation, Machine Learning and Data Mining in Bioinformatics, pp. 74-85, Springer, Berlin, Heidelberg, April, (2012).
  40. Deng, W., Yao, R., Zhao, H., Yang, X., & Li, G., "A novel intelligent diagnosis method using optimal LS-SVM with improved PSO algorithm", Soft Computing,Vol. 23(7), pp. 2445-2462, (2019).
  41. Hu, W., Yan, L., Liu, K., & Wang, H., "A short-term traffic flow forecasting method based on the hybrid PSO-SVR", Neural Processing Letters,Vol. 43(1), pp. 155-172, (2016).

 

CAPTCHA Image