تعیین تابع آموزش مناسب مدل شبکه عصبی به منظور ارتقاء ایمنی تردد جاده‌ای

نویسندگان

1 دانش آموخته کارشناسی ارشد، دانشکده مهندسی عمران، دانشگاه یزد، یزد، ایران

2 استادیار، دانشکده مهندسی عمران، دانشگاه یزد، یزد، ایران

3 دانش آموخته کارشناسی ارشد، دانشکده مهندسی عمران، دانشگاه پیام‌نور رضوانشهر، یزد، ایران

4 دانش آموخته کارشناسی ارشد، دانشکده مهندسی عمران، دانشگاه آزاد اسلامی واحد بافق، یزد، ایران

چکیده

­سالانه تعداد زیادی از مردم دنیا در اثر تصادفات جاده­ای جان و مال خود را از دست می­دهند. یکی از روش­های مناسب به منظور کاهش تصادفات، پیش­بینی وقوع تصادفات قبل از رخداد آن­ها می­باشد. در این مقاله به‌طور موردی تصادفات محور نائین-اردکان استان یزد با بهره­گیری از مدل شبکه عصبی مورد ارزیابی قرار گرفت. تاکنون در هیچ مطالعه‌ای به بررسی تاثیر توابع مختلف آموزش مدل شبکه عصبی در دقت نتایج پیش­بینی پرداخته نشده است. هدف این مقاله تعیین تابع آموزش دقیق­تر شبکه عصبی به منظور پیش­بینی تعداد تصادفات محور موردبررسی بود. در این راستا تعداد 4 تابع مختلف ارزیابی گردید. بررسی­های این مقاله حاکی از برتری نسبی مدل شبکه عصبی با تابع آموزش از نوع  trainlmبود. همچنین نتایج نشان داد که عوامل میزان تردد در هر خط و عدم رعایت فاصله ایمن به ترتیب بیشترین تأثیر را در وقوع تصادفات محور موردمطالعه داشتند. کاربرد نتایج تحقیق در بیان دقیق­تر اثر متغیرهای مستقل در وقوع تصادفات است. به بیان دقیق­تر تاثیرگذاری متغیرهای مستقل می­تواند به کارشناسان ایمنی جهت اعمال بهینه­تر سناریو­های کاهش تصادفات کمک کند.

کلیدواژه‌ها


عنوان مقاله [English]

Determining the Proper Training Algorithm of Artificial Neural Network Prediction Model as a Tool for Road Safety Promotion

نویسندگان [English]

  • Abolfazl Khishdari 1
  • Hamed Khani Sanij 2
  • Javad Zaker Harofteh 3
  • Mohsen Dehghan Banadaki 4
1 M.Sc., Grad., Department of Civil Engineering, Yazd University, Yazd, Iran.
2 Assistant Professor, Department of Civil Engineering, Yazd University, Yazd, Iran.
3 M. Sc., Grad., Department of Civil Engineering, Payam Noor Rezvanshahr University, Yazd, Iran.
4 M. Sc., Grad., Department of Civil Engineering, Bafgh Islamic Azad University, Yazd, Iran.
چکیده [English]

Numerous people have died and economically damaged due to the road accidents. One of the efficient ways of reducing crashes is to predict them before happening. This paper investigated the power of artificial-neural network (ANN) model to predict crash frequencies of Naein-Ardakan road, located in Yazd, Iran. To date, there seems no research done to compare the effects of ANN training functions on prediction performance. This research aimed to determine the proper ANN training algorithm for crash frequency prediction. In this regard, four different training algorithms were investigated. The results demonstrated the outperformance of ‘trainlm’ algorithm. Additionally, it was found that the average daily traffic per lane and gap lengths is the most influential factors in crash occurrences, respectively. The present study can be applied to more precisely explain the effects of independent variables on crash outcomes. An in-depth explanation of the effectiveness of independent variables can assist road safety experts in making better decisions for reducing accidents.

کلیدواژه‌ها [English]

  • Neural Network
  • Training Function
  • prediction
  • Crash Frequencies
-سایت سازمان پزشک قانونی کشور، (1395)،
به نشانی: www.lmo.ir.
 
-­Abdelwahab, H. T., and Abdel-Aty, M., (2001), "Development of Artificial Neural Network Models to Predict Driver Injury Severity in Traffic Accidents at Signalized Intersections", Transportation Research Record, Journal of the Transportation Research Board, No. 1746, pp. 6-13.
 
-­Bayata, H. F., Hattatoglu, F., and Karsli, N., (2011), "Modeling of monthly traffic accidents with the artificial neural network method", International Journal of the Physical Sciences, No. 6, pp. 244-254.
 
-­Burattini, E., and De Gregorio, M., (1998),
"A neural network to evaluate congestion levels. In: Mussone, L., Marescotti, L. (eds.)", Urban traffic: control possibility, tools and their effectiveness, Milano.
 
- Can Yilmaz, A., Aci, C., and Aydin, K. (2016). Traffic accident reconstruction and an approach for prediction of fault rates using artificial neural networks: A case study in Turkey. Traffic Injury Prevention, 17(6), pp.585-589.
 
 doi: 10.1080/15389588.2015.1122760.
-­Chang, L. Y., (2005), "Analysis of freeway accident frequencies: Negative binomial regression versus artificial neural network", Safety Science, No. 43, pp. 541-557.
 
-­Dougherty, M., (1995), "A review of neural networks applied to transport", Transportation Research Part C: Emerging Technologies, No. 3, pp. 247-260.
 
-­Dougherty, M., and Joint, M., (1992),
"A behavioural model of driver route choice using neural networks", International Conference on Artificial Intelligence Applications in Transportation Engineering, San Buenaventura, Califomia, USA, pp. 20-24.
 
-­Dougherty, M., Kirby, H., and Boyle, R., (1992), "The use of neural networks to recognize and predict traffic congestion", Congress on Transport Research, Lyon, France, March, pp.10-12.
-­Dougherty, M., Kirby, H., and Boyle, R., (1993), "The use of neural networks to recognize and predict traffic congestion", Traffic Engineering and Control, No. 34,
pp. 311-314.
 
-­Dreyfus, G., (2004), "Neural Networks: Methodology and Applications". 2nd. Edition, Germany: Springer-Verlag Berlin Heidelberg.
 
-­Fischer, M. M., and Gopal, S., (1994), "Artificial neural networks: a new approach to modelling interregional telecommunication flows", Journal of Regional Science, No. 4,
pp. 503-527.
 
-Gargoum, S. A., El-Basyouny, K., and Kim, A., (2016), "Towards setting credible speed limits: Identifying factors that affect driver compliance on urban roads. Accident Analysis & Prevention, 95, pp.138-148.
doi: http://dx.doi.org/10.1016/j.aap.2016.07.001.
 
-­Gustavsson, J., and Svensson, Å., (1976),
"A Poisson Regression Model Applied to Classes of Road Accidents with Small Frequencies", Scandinavian Journal of Statistics, No. 3, pp. 49-60.
 
-­Hasheminejad, S. H.-A., Zahedi, M., and Hasheminejad, S. M. H., (2017), "A hybrid clustering and classification approach for predicting crash injury severity on rural roads. International Journal of Injury Control and Safety Promotion, pp.1-17.
doi: 10.1080/17457300.2017.1341933.
 
-­Khishdari, A., and Fallah Tafti, M., (2017), "Development of crash frequency models for safety promotion of urban collector streets. International Journal of Injury Control and Safety Promotion, pp.1-15.
doi: 10.1080/17457300.2016.1278237.
 
-­Kumara, S. S. P., and Chin, H. C., (2003), "Modeling Accident Occurrence at Signalized Tee Intersections with Special Emphasis on Excess Zeros", Traffic Injury Prevention, No. 4, pp. 53-57.
 
-­Lee, J., and Mannering, F., (2002), "Impact of roadside features on the frequency and severity of run-off-roadway accidents: an empirical analysis", Accident Analysis & Prevention,
No. 34, pp. 149-161.
doi:http://dx.doi.org/10.1016/S00014575(01)00009-4.
 
-­Li, Z., Wang, W., Liu, P., Bigham, J. M., and Ragland, D. R., (2013), "Using Geographically Weighted Poisson Regression for county-level crash modeling in California", Safety Science, No. 58,  pp. 89-97.
doi:http://dx.doi.org/10.1016/j.ssci.2013.04.005.
 
-­Lord, D., Manar, A., and Vizioli, A., (2005), "Modeling crash-flow-density and crash-flow-V/C ratio relationships for rural and urban freeway segments", Accident Analysis & Prevention, No. 37, pp. 185-199.
 
-­Lord, D., Washington, S. P., and Ivan, J. N., (2005), "Poisson, Poisson-gamma and
zero-inflated regression models of motor vehicle crashes: balancing statistical fit and theory", Accident Analysis & Prevention, No. 37, pp. 35-46.
doi:http://dx.doi.org/10.1016/j.aap.2004.02.004.
 
-­Malyshkina, N. V., and Mannering, F. L., (2010), "Zero-state Markov switching count-data models: An empirical assessment", Accident Analysis & Prevention, No. 42,
pp. 122-130.
doi: ttp://dx.doi.org/10.1016/j.aap.2009.07.012.
 
-­MATLAB., (2014), "Neural Network Toolbox", Natick, MA: MathWorks Inc.
 
-­Meng, Q., and Qu, X., (2012), "Estimation of rear-end vehicle crash frequencies in urban road tunnels", Accident Analysis & Prevention, No. 48, pp. 254-263.
doi:http://dx.doi.org/10.1016/j.aap.2012.01.025.
 
-­Miaou, S. P., (1994), "The relationship between truck accidents and geometric design of road sections: Poisson versus negative binomial regressions", Accident Analysis & Prevention, No. 26, pp. 471-482.
doi:­http://dx.doi.org/10.1016/001-4575(94)90038-8
 
-­Milton, J., and Mannering, F., (1998), "The relationship among highway geometrics, traffic-related elements and motor-vehicle accident frequencies", Transportation, No. 25, pp. 395-413. doi: 10.1023/a:1005095725001.
 
-­Mussone, L., Bassani, M., and Masci, P., (2017), Analysis of factors affecting the severity of crashes in urban road intersections. Accident Analysis & Prevention, 103, 112-122. doi: https://doi.org/10.1016/j.aap.2017.04.007.
-­Najaf, P., Duddu, V. R., and Pulugurtha, S. S., (2017), Predictability and interpretability of hybrid link-level crash frequency models for urban arterials compared to cluster-based and general negative binomial regression models. International Journal of Injury Control and Safety Promotion, pp.1-11.
doi: 10.1080/17457300.2017.1285789.
 
-­Pant, E. D., (1994), "Neural network for gap acceptance at stop-controlled intersection", Journal of Transportation Engineering, No. 120, pp. 432-446.
 
-­Pirdavani, A., Brijs, T., Bellemans, T., Kochan, B., and Wets, G., (2013), "Evaluating the road safety effects of a fuel cost increase measure by means of zonal crash prediction modeling", Accident Analysis & Prevention, No. 50,
pp. 186-195.
doi: ttp://dx.doi.org/10.1016/j.aap.2012.04.008.
 
-­Ritchie, S. G., and Cheu, R. L., (1993), "Simulation Of Freeway Incident Detection Using Artificial Neural Networks", Transportation Research Part C: Emerging Technologies, No. 1, pp. 203-217.
 
-­Ritchie, S. G., Cheu, R. L., and Recker, W. W., (1992), "Freeway incident detection using artificial neural networks", International Conference on Artificial Intelligence Applications in Transportation Engineering, San Buenaventura, Califomia, USA, pp.20-24.
 
-­Rodrigue, J. P., (1997), "Parallel modelling and neural networks: An overview for transportation/land use systems", Transportation Research Part C: Emerging Technologies,
No. 5, pp. 259-271.                                                 
 
-­Shi, Q., Abdel-Aty, M., and Lee, J., (2016), "A Bayesian ridge regression analysis of congestion's impact on urban expressway safety", Accident Analysis & Prevention, 88, pp.124-137.
doi:http://dx.doi.org/10.1016/j.aap.2015.12.001.
 
-­Theofilatos, A., and Yannis, G., (2014), "A review of the effect of traffic and weather characteristics on road safety", Accident Analysis & Prevention, 72, pp.244-256.
doi: ttp://dx.doi.org/10.1016/j.aap.2014.06.017.
 
 
-Theofilatos, A., and Yannis, G., (2017), "Investigation of powered 2-wheeler accident involvement in urban arterials by considering real-time traffic and weather data",Traffic Injury Prevention, 18(3), pp.293-298.
doi: 10.1080/15389588.2016.1198871.
 
- WHO, (2015), "Global Status Report on Road Safety".
 
-­Yan, Y., Wang, X., Shi, L., and Liu, H., (2017), "Influence of light zones on drivers' visual fixation characteristics and traffic safety in extra-long tunnels", Traffic Injury Prevention, 18(1), pp.102-110.
doi: 10.1080/15389588.2016.1193170.
 
-­Yang, H., Kitamura, R., Jovanis, P. P., Vaughn, K. M., and Abdel-Aty, M. A., (1993), "Exploration of route choice behavior with advanced traveler information using neural network concepts", Transportation, No. 20, pp.199-223.
 
-­Ye, X., Pendyala, R. M., Shankar, V., and Konduri, K. C., (2013), "A simultaneous equations model of crash frequency by severity level for freeway sections", Accident Analysis & Prevention, No. 57, pp. 140-149.
 
-­Yu, R., and Abdel-Aty, M., (2014), Analyzing crash injury severity for a mountainous freeway incorporating real-time traffic and weather data. Safety Science, 63, pp.50-56.
doi: ttp://dx.doi.org/10.1016/j.ssci.2013.10.012.
 
-­Zhang, H. M., and Ritchie, S. G., (1997), "Freeway ramp metering using artificial neural networks" Transportation Research Part C: Emerging Technologies, No. 5, pp. 273-286. doi: http://dx.doi.org/10.1016/S0968-090X(97)00019-3.
 
-­Zeng, Q., Huang, H., Pei, X., Wong, S. C., and Gao, M., (2016), "Rule extraction from an optimized neural network for traffic crash frequency modeling. Accident Analysis & Prevention", 97, pp.87-95.
doi: http://dx.doi.org/10.1016/j.aap.2016.08.017.