مدل سازی شبکه مبنای تصادفات جرحی عابر پیاده به کمک شبکه عصبی در محیط GIS (مطالعه ی موردی: شهر مشهد)

نوع مقاله : علمی - پژوهشی

نویسندگان

1 استادیار، دانشکده عمران و حمل و نقل، دانشگاه اصفهان، اصفهان، ایران

2 دانش آموخته کارشناسی ارشد، دانشکده عمران و حمل و نقل، دانشگاه اصفهان، اصفهان، ایران

3 استادیار، دانشکده مهندسی، دانشگاه فردوسی، مشهد، ایران

چکیده

در این مقاله با در نظر گرفتن 23 پارامتر مؤثر بر تصادفات جرحی عابر پیاده شهر مشهد (در چهار گروه) در سال‌های 1391 تا 1393 و آماده­سازی لایه­های رستری لازم در محیط GIS، تأثیر هر یک از آن­ها در قالب ارزیابی عملکرد شبکه عصبی پرسپترون چندلایه، اولویت­بندی گردید. در اغلب تحقیقات انجام‌شده، مدل‌سازی بردار مبنا مدنظر قرار گرفته و به انعطاف‌پذیری و دقت پیش‌بینی رستر مبنای تصادفات در راستای تعیین تأثیر مکانی پارامترها توجهی نشده است. در مقاله پیش ­رو علاوه بر در نظر گرفتن متغیرهای رایج، متغیرهای فرم شهری و جمعیتی-اجتماعی نیز لحاظ شدند و 38 متغیر مستقلاز چهار حوزة مختلف به‌طور همزمان ارزیابی گردیدند. به این ترتیب که با انجام پردازش‌های مکانی-آماری، ابتدا داده‌های رستری ورودی با ابعاد 20*20 متر در یک پایگاه داده مکانی آماده‌سازی و به‌منظور پیاده­سازی مدل شبکه عصبی پرسپترون چند لایه، در محیط برنامه‌نویسی MATLAB فراخوانی شدند. در ادامه، مجموعة داده‌های رستری شامل 111537 پیکسل تحلیل شده و با تغییر تعداد نورون­ها، تعداد لایه­ها، توابع انتقال، توابع آموزش و ترکیب­های متفاوت آموزشی و آزمون، 25 طرح مختلف شبکه عصبی به کمک پارامترهای MSE و  ارزیابی گردیدند. نتایج حاکی از آن است که بهترین مدل با 0/95  و  MSE=0/0020در بیان ارتباط تعداد تصادفات جرحی عابر پیاده درون­شهری و پارامترهای مرتبط با آن بسیار کارآمد و دقیق عمل نموده است. با پیاده­سازی مدل مذکور در محدوده مطالعاتی شهر مشهد، مشخص گردید که پارامترهای تراکم خالص مسکونی در نواحی شهرداری،‌ بافت ارگانیک ­شهری و طبقة اول منزلت اجتماعی به ترتیب دارای بیشترین تأثیر و پارامترهای عرض پیاده­روی بالای 10 متر، معابر شریانی درجه دو اصلی و طبقه سوم منزلت اجتماعی به ترتیب دارای کمترین تأثیر در تصادفات عابر پیاده هستند.

کلیدواژه‌ها

موضوعات

عنوان مقاله [English]

The Raster Based Simulation of Pedestrian Injury Crashes using Artificial Neural Network in GIS (Case Study: Mashhad City)

نویسندگان [English]

  • Gholamreza Shiran 1
  • Maryam Hasanpour 2
  • Ruzbeh Shad 3
  • Abolfazl Mohammadzadeh Moghaddam 3
1 Assistant Professor, Department of Civil and Transportation Engineering, University of Isfahan, Isfahan, Iran
2 MSc. Grad, Department of Civil and Transportation Engineering, University of Isfahan, Isfahan, Iran
3 Department of Civil Engineering, Ferdowsi University of Mashhad, Mashhad, Iran
چکیده [English]

This paper evaluates different MLPs (multi-layer perceptron neural networks) whilst considering 23 pedestrian injury accident parameters (in four categories) for time period of 3 years (1391-1393). The data belongs to the city of Mashhad in Iran. For this purpose, after preparing required raster layers in GIS, the influence of each parameter has been assessed through evaluation of different structures of MLP. It is worth noting that in the most works undertaken, the vector based modeling has been considered to determine the effect of spatial parameters; and the flexibility and the accuracy of raster-based prediction has been neglected. In the present study, authors have considered demographic characteristics and urban form factors in addition to the common variables in the simulation of pedestrian injury accidents. Furthermore, a total of 38 independent variables in four classes have been assessed. At first, the input raster data with the pixel size of 20 meters were created by employing geo_statistical processing in GIS and then MLPs algorithms have been programed using MATLAB language. A set of raster data containing 111,537 pixels has been analyzed using MLP changing the neurons, the layers, the transfer functions, the training functions and different combination of training and testing sets. Performance of 25 different neural network structures were validated by MSE and R-squared. The results indicate that a model with three-layer, 70 neurons, the RADBAS transfer function and Levenberg_Marquardt training function (= 0.95 and MSE = 0.0020) has the most efficient and optimum design for representing the relationship among the number of pedestrian injury accidents and the effective input parameters. By implementing this model to the study area of the city of, it was revealed that the residential density, the street network and the first level of social status characteristics have the highest impact on the pedestrian crashes. However, the sidewalks having   more than 10 meters width, the fourth type of road and the second level of social status have the least impacts.

کلیدواژه‌ها [English]

  • multi-layer perceptron model
  • Pedestrian Injury Accidents
  • Kernel density estimation
  • GIS

مراجع

-Abdel-Aty, M. A. and Abdelwahab, H. T. (2004) "Predicting injury severity levels in traffic crashes: a modeling comparison", Journal of Transportation Engineering, Vol. 130, No. 2, pp. 204-210.
-Abdel-Aty, M. A. and Radwan, A. E. (2000) "Modeling traffic accident occurrence and involvement", Accident Analysis and Prevention, Vol. 32, No. 5, pp. 633-642.
-Aidoo, E. N. Amoh-Gyimah, R., and Ackaah, W. (2013) "The effect of road and environmental characteristics on pedestrian hit-and-run accidents in Ghana", Accident Analysis and Prevention, Vol. 53, No. 1, pp. 23-27.
-Akgüngör, A. P. and Doğan, E. (2009) "An application of modified Smeed, adapted Andreassen and artificial neural network accident models to three metropolitan cities of Turkey", Scientific Research and Essays, Vol. 4, No. 9, pp. 906-913.
-Anderson, T. K. (2009) "Kernel density estimation and K-means clustering to profile road accident hotspots", Accident Analysis and Prevention, Vol. 41, No. 3, pp. 359-364.
-Braddock, M., Lapidus, G., Cromley, E., Cromley, R., Burke, G. and Banco, L. (1994) "Using a geographic information system to understand child pedestrian injury", American Journal of Public Health, Vol. 84, No. 7, pp. 1158-1161.
-Broujerdian, A. M., Dehqani, S. P. and Fetanat, M. (2016) "Estimation Model of Two-Lane Rural Roads Safety Index According to Characteristics of the Road and Drivers’ Behavior", International Journal of Transportation Engineereing, Vol. 3, No. 1, pp. 17-29.
-Chang, L.-Y. (2005) "Analysis of freeway accident frequencies: negative binomial regression versus artificial neural network", Safety Science, Vol. 43, No. 8, pp. 541-557.
-Chen, X., Fang, Z., Li, G. and Tao, B. (1989) "Non-parametric statistics", Shanghai Science and Technology Press, Shanghai, pp. 284-292.
-Chin, H. C. and Quddus, M. A. (2003) "Applying the random effect negative binomial model to examine traffic accident occurrence at signalized intersections", Accident Analysis and Prevention, Vol. 35, No. 2, pp. 253-259.
-Chiou, Y.-C. (2006) "An artificial neural network-based expert system for the appraisal of two-car crash accidents", Accident Analysis and Prevention, Vol. 38, No. 4, pp. 777-785.
-Cottrill, C. D. and Thakuriah, P. V. (2010) "Evaluating pedestrian crashes in areas with high low-income or minority populations", Accident Analysis and Prevention, Vol. 42, No. 6, pp. 1718-1728.
-Delen, D., Sharda, R. and Bessonov, M. (2006) "Identifying significant predictors of injury severity in traffic accidents using a series of artificial neural networks", Accident Analysis and Prevention, Vol. 38, No. 3, pp. 434-444.
-Dumbaugh, E. and Rae, R. (2009) "Safe urban form: revisiting the relationship between community design and traffic safety", Journal of the American Planning Association, Vol. 75, No. 3, pp. 309-329.
-Erdogan, S., Yilmaz, I., Baybura, T. and Gullu, M. (2008) "Geographical information systems aided traffic accident analysis system case study: city of Afyonkarahisar". Accident Analysis and Prevention, Vol. 40, No. 1, pp. 174-181.
-FHWA (2006) "Draft 2005 New Orleans Metropolitan Bicycle and Pedestrian Plan", Regional Planning Commission (Ed.).
-Fish, K. E. and Blodgett, J. G. (2003) "A visual method for determining variable importance in an artificial neural network model: an empirical benchmark study", Journal of Targeting, Measurement and Analysis for Marketing, Vol. 11, No. 3, pp. 244-254.
-Fotheringham, A. S., Brunsdon, C. and Charlton, M. (2000) "Quantitative geography: perspectives on spatial data analysis", Sage Publications.
-Frost, J. (2013) "Multiple regression analysis: Use adjusted R-squared and predicted R-squared to include the correct number of variables", Minitab Blog.
-Hashimoto, T. (2005) "Spatial analysis of pedestrian accidents", Graduate Thesis and Dissertations. Department of Environmental Science and Policy College of Arts and Science University of South Florida .
-Hornik, K., Stinchcombe, M. and White, H. (1989) "Multilayer feedforward networks are universal approximators", Neural Networks, Vol. 2, No. 5, pp. 359-366.
-Hosseinpour, M., Yahaya, A. S., Ghadiri, S. M. and Prasetijo, J. (2013) "Application of adaptive neuro-fuzzy inference system for road accident prediction", KSCE Journal of Civil Engineering, Vol. 17, No. 7, pp. 1761-1772.
-Huang, H., Zeng, Q., Pei, X., Wong, S. C. and Xu, P. (2016) "Predicting crash frequency using an optimised radial basis function neural network model", Transportmetrica A: Transport Science, Vol. 12, No. 4, pp. 330-345.
-Liu, X. and Yang, J. (2002) "Development of child pedestrian mathematical models and evaluation with accident reconstruction", Traffic Injury Prevention, Vol. 3, No. 4, pp. 321-329.
-Loo, B. P., Yao, S. and Wu, J. (2011) "Spatial point analysis of road crashes in Shanghai: A GIS-based network kernel density method", Paper presented at the Geoinformatics, 2011 19th. International Conference on.
-Mahmoudabadi, A. (2010) "Comparison of weighted and simple linear regression and artificial neural network models in freeway accidents prediction", Paper presented at the Computer and Network Technology (ICCNT), Second International Conference.
-Marzban, C. and Witt, A. (2001) "A Bayesian neural network for severe-hail size prediction", Weather and Forecasting, Vol. 16, No. 5, pp. 600-610.
-Miaou, S. P. (1994) "The relationship between truck accidents and geometric design of road sections: Poisson versus negative binomial regressions", Accident Analysis and Prevention, Vol. 26, No. 4, pp. 471-482.
-Miaou, S. P., Lu, A. and Lum, H. (1996) "Pitfalls of using R 2 to evaluate goodness of fit of accident prediction models", Transportation Research Record: Journal of the Transportation Research Board, Vol. 1542, pp. 6-13.
-Miaou, S.-P. and Lum, H. (1993) "Modeling vehicle accidents and highway geometric design relationships", Accident Analysis and Prevention, Vol. 25, No. 6, pp. 689-709.
-Moghaddam, F. R., Afandizadeh, S. and Ziyadi, M. (2011) "Prediction of accident severity using artificial neural networks", International Journal of Civil Engineering, Vol. 9, No. 1, pp. 41.
-Nie, J., Li, G. and Yang, J. (2015) "A study of fatality risk and head dynamic response of cyclist and pedestrian based on passenger car accident data analysis and simulations", Traffic Injury Prevention, Vol. 16, No. 1, pp. 76-83.
-O'Sullivan, D. and Wong, D. W. (2007) "A surface‐based approach to measuring spatial segregation", Geographical Analysis, Vol. 39, No. 2, pp. 147-168.
-Oh, J., Washington, S. P. and Nam, D. (2006) "Accident prediction model for railway-highway interfaces", Accident Analysis and Prevention, Vol. 38, No. 2, pp. 346-356.
-Polat, K. and Durduran, S. S. (2011) "Subtractive clustering attribute weighting (SCAW) to discriminate the traffic accidents on Konya–Afyonkarahisar highway in Turkey with the help of GIS", Advances in Engineering Software, Vol. 42, No. 7, pp. 491-500.
-Prato, C. G., Gitelman, V. and Bekhor, S. (2012) "Mapping patterns of pedestrian fatal accidents in Israel", Accident Analysis and Prevention, Vol. 44, No. 1, pp. 56-62.
-Pulugurtha, S. S., Krishnakumar, V. K. and Nambisan, S. S. (2007) "New methods to identify and rank high pedestrian crash zones: An illustration", Accident Analysis and Prevention, Vol. 39, No. 4, pp. 800-811.
-Ramli, M. Z. (2011) "Development of accident prediction model by using artificial neural network (ANN)", Doctoral dissertation, Universiti Tun Hussein Onn Malaysia.  
-Santosh, T., Srivastava, A., Rao, V. S., Ghosh, A., and Kushwaha, H. (2009) "Diagnostic system for identification of accident scenarios in nuclear power plants using artificial neural networks", Reliability Engineering and System Safety, Vol. 94, No. 3, pp. 759-762.
-Siddiqui, C., Abdel-Aty, M., and Huang, H. (2012) "Aggregate nonparametric safety analysis of traffic zones", Accident Analysis and Prevention, Vol. 45, pp. 317-325.
-Song, J. J., Ghosh, M., Miaou, S., and Mallick, B. (2006) "Bayesian multivariate spatial models for roadway traffic crash mapping", Journal of multivariate analysis, Vol. 97, No. 1, pp. 246-273.
-Vogt, A., and Bared, J. (1998) "Accident models for two-lane rural segments and intersections", Transportation Research Record: Journal of the Transportation Research Board, Vol. 1635, pp. 18-29.
-Wang, Y., and Kockelman, K. M. (2013) "A Poisson-lognormal conditional-autoregressive model for multivariate spatial analysis of pedestrian crash counts across neighborhoods", Accident Analysis and Prevention, Vol. 60, pp. 71-84.
-WHO. (2013) "World Health Organization, global status report on road safety: supporting a decade of action".
-WHO. (2015) "World Health Organization, Global status report on road safety"
-Xie, Y., Lord, D., and Zhang, Y. (2007) "Predicting motor vehicle collisions using Bayesian neural network models: An empirical analysis", Accident Analysis and Prevention, Vol. 39, No. 5, pp. 922-933.
-Xie, Z., and Yan, J. (2008) "Kernel density estimation of traffic accidents in a network space", Computers, Environment and Urban Systems, Vol. 32, No. 5, pp. 396-406.
-Yu, H., Liu, P., Chen, J., and Wang, H. (2014) "Comparative analysis of the spatial analysis methods for hotspot identification", Accid Anal Prev, Vol. 66, pp. 80-88.
-بهزادفر، مصطفی (1394) "محیط های پاسخده"، دانشگاه علم و صنعت ایران، تهران.
-داگلاس، مونتگمری و الیزابت، پک (1382) "مقدمه ای بر تحلیل رگرسیون خطی"، انتشارات دانشگاه شهید باهنر کرمان، کرمان.
-سازمان ‌پزشکی ‌قانونی‌ کشور (1394) "مقایسه آمار متوفیات و مصدومین حوادث رانندگی"  تهران: سازمان نظام پزشکی
-سازمان ‌حمل‌ونقل‌ و ترافیک‌‌ شهرداری ‌مشهد (1393) "تصادفات جرحی عابرپیاده شهر مشهد.، مشهد: سازمان حمل وو نقل و ترافیک
-فرید، یدالله (1394) "جغرافیا و شهرشناسی"، انتشارات دانشگاه تبریز، تبریز.
-معاونت ‌مطالعات‌ و برنامه‌ریزی، سازمان‌ حمل‌ونقل‌ و ترافیک ‌شهرداری ‌مشهد (1394) "یازدهمین آمارنامه حمل و نقل شهر مشهد" .
-منهاج،  محمد باقر (1392) "مبانی شبکه های عصبی (جلد اول)"، انتشارات دانشگاه صنعتی امیر کبیر، تهران.
-یوسفی، علی (1389) "تأملی بر مرزبندی اجتماعی فضای شهری مشهد: طبقه بندی منزلتی نواحی شهر"، مجلة علوم اجتماعی دانشکده  ادبیات و علوم انسانی دانشگاه فردوسی مشهد، ص. 61-91. 

فایل ها

سابقه مقاله

  • تاریخ دریافت: 07 دی 1395
  • تاریخ بازنگری: 03 مرداد 1396
  • تاریخ پذیرش: 04 مرداد 1396

هم رسانی

ارجاع به این مقاله

آمار