ارایه روشی جهت تحلیل شدت تصادفات راه های برون شهری مبتنی بر توابع خوشه‌بندی مکانی و داده‌کاوی به روش درخت تصمیم، محور مورد مطالعه: آزادراه قزوین-لوشان

نوع مقاله : مقاله پژوهشی

نویسندگان

1 دانشکده مهندسی عمران، دانشگاه علم‌و‌صتعت ایران، تهران، ایران

2 استادیار، گروه مهندسی عمران (راه و ترابری) دانشکده فنی، دانشگاه گیلان

3 دانشکده مهندسی عمران، دانشگاه علم‌و‌صنعت ایران، تهران، ایران

چکیده

تحلیل مکانی تصادفات رخ داده در راه های برون شهری با هدف شناسایی پارامترهای مؤثر بر افزایش شدت تصادفات، می تواند در تصمیم‌گیری متخصصین و دستاندرکاران اصلاح و بهبود ایمنی راه ها به منظور کاهش شدت تصادفات جاده ای موثر باشد. هدف این تحقیق ارایه روشی جهت تحلیل شدت تصادفات و تعیین عوامل موثر بر آن در آزادراه‌های برون شهری مبتنی بر توابع خوشه‌بندی مکانی و مدل داده کاوی درخت طبقه بندی و رگرسیون است. روش پیشنهادی در آزادراه قزوین-لوشان مورد ارزیابی و آزمون قرار می‌گیرد. در این راستا به منظور بررسی توزیع مکانی تصادفات در محور مورد مطالعه طی دوره 6 ساله 1390 تا 1395 شمسی، از توابع خودهمبستگی مکانی گتیس-ارد جی استار و تراکم کرنل استفاده شده است. خروجی تحلیل‌های مکانی نشان داد، که تمرکز تصادفات در بخش اعظمی از قوس‌های افقی محور مورد مطالعه بیشتر می‌باشد. باتوجه به این دستاورد در فاز بعدی تحقیق به منظور بررسی عوامل موثر بر شدت تصادفات، از مدل داده کاوی درخت طبقه بندی و رگرسیون بر روی تصادفات رخ داده در کل محور و به طور خاص تصادفات رخ داده در قوس‌های افقی استفاده گردید. نتایج حاکی از آن بود که مهم‌ترین عوامل موثر بر افزایش شدت تصادفات در محور مورد مطالعه، دو متغیر نوع تصادفات و عامل انسانی با ضرایب اهمیت نسبی متغیرهای مستقل به ترتیب 100 و 7/39 درصد برای کل محور و 100و 9/65 درصد برای قوس‌های افقی هستند. بررسی اهمیت نسبی سایر متغیرهای مدل پیشنهادی نیز نشان داد که طرح هندسی، نحوه برخورد و روز وقوع تصادف از جمله عوامل موثر در افزایش تصادفات با شدت خسارتی در آزادراه قزوین-لوشان می‌باشد. این تحقیق نشان داد که تلفیق توابع مکانمند GIS با تحلیل‌های ناپارامتریک داده‌کاوی مبتنی بر درخت تصمیم که قابلیت مدل‌سازی توامان داده‌های کمی و کیفی را همزمان دارا می‌باشد، در تعیین عوامل موثر بر شدت تصادفات و تحلیل مکانمند الگوهای رایج تصادفات در محورهای برونشهری کارا و موثر است.

کلیدواژه‌ها

موضوعات


عنوان مقاله [English]

Providing a Method for Accident Severity Analysis Using Geospatial Clustering Functions and Decision Tree, Case Study: Qazvin-Loshan Freeway

نویسندگان [English]

  • hamid behbahani 1
  • Meysam Effati 2
  • Samane Mortezaei 3
1 Department of Road and Transportion, Faculty of Civil Engineering, The University Of Elmo-Sanat,Tehran, Iran
2 Assistant Professor, Department of Civil Engineering, Faculty of Engineering The University of Guilan
3 Department of Road and Transportion, Faculty of Civil Engineering, The University Of Elmo-Sanat,Tehran, Iran
چکیده [English]

Spatial analysis of accidents occurred in freeways and identifying effective parameters can help researchers and authorities to improve road safety by reducing the severity of accidents. The purpose of this study is to provide a method to analyze the accident severity and determine related effective parameters in freeways based on spatial clustering functions and regression and classification tree data mining method. Proposed method was assessed in Qazvin-Loshan freeway. In this study, to study the spatial distribution of the accidents in the aforementioned axis during the period from 2011 to 2016, the spatial functions such as Getis-Ord G* autocorrelation and Kernel Density Functions were Used. The results of spatial analysis showed that the spatial gathering of accidents in most of horizontal curves was greater. According to this achievement, in the next phase of the study, in order to study the factors affecting the severity of accidents, the Regression and Classification Tree was used on accidents that occurred in the whole axis and specifically the crashes which occurred in the horizontal curves. Results of this part of the study showed that the type of accidents (overturning and falling, exit from the road, multi-vehicle collisions, etc.) and human factors are the most important factors in the severity of accidents in this axis. Relative importance coefficients for these two independent variables are 100 and 39.7 percent for the whole axis and 100 and 65.9 percent for horizontal curves. The study of the relative importance of other variables used in the proposed model showed that the geometric design, type and date of crashes are among the most effective factors in increasing the property damage only crashes in Qazvin-Loshan Freeway. This study showed that the integration of GIS functions with non-parametric data mining algorithms such as decision tree, which is capable of simultaneous modeling of quantitative and qualitative data, is an effective approach to determine the factors affecting the severity of accidents and to analyze the spatial patterns of accidents in freeways.

کلیدواژه‌ها [English]

  • Road Safety
  • Accidents Severity
  • Getis-Ord G* Autocorrelation
  • kernel Density Functions
  • Classification and Regression Tree
[1]Y .-B. Zhou, S. Liang, G.-X. Chen, C. Rea, S.-M. Han, Z.-G. He, Y.-P. Li, J.-G. Wei, G.-M. Zhao, Q.-W. Jiang, Spatial-temporal variations of Schistosoma japonicum distribution after an integrated national control strategy: a cohort in a marshland area of China, BMC Public Health, 13(1) (2013) 297.
[2] R.R. Vatsavai, A. Ganguly, V. Chandola, A. Stefanidis, S. Klasky, S. Shekhar, Spatiotemporal data mining in the era of big spatial data: algorithms and applications, in: Proceedings of the 1st ACM SIGSPATIAL international workshop on analytics for big geospatial data, 2012, pp. 1-10.
[3] J. Mennis, D. Guo, Spatial data mining and geographic knowledge discovery—An introduction, Computers, Environment and Urban Systems, 33(6) (2009) 403-408.
[4] S. Erdogan, I. Yilmaz, T. Baybura, M. Gullu, Geographical information systems aided traffic accident analysis system case study: city of Afyonkarahisar, Accident Analysis & Prevention, 40(1) (2008) 174-181.
[5] I.B. Gundogdu, Applying linear analysis methods to GISsupported procedures for preventing traffic accidents:Case study of Konya, Safety Science, 48(6) (2010) 763-769.
[6] M. Effati, Determining Roads Black Spots Using Spatial Information Systems and Multicriteria Decision Making Processes, Transportation engineering, 4 (2012) 349-363.
[7] T. Steenberghen, T. Dufays, I. Thomas, B. Flahaut, Intraurban location and clustering of road accidents using GIS: a Belgian example, International Journal of Geographical Information Science, 18(2) (2004) 169-181.
[8] G.A. Shafabakhsh, A. Famili, M.S. Bahadori, GIS-based spatial analysis of urban traffic accidents: Case study in Mashhad, Iran, Journal of traffic and transportation engineering )English edition), 4(3) (2017) 290-299.
[9] M.B. Ulak, E.E. Ozguven, L. Spainhour, O.A. Vanli, Spatial investigation of aging-involved crashes: A GIS-based case study in Northwest Florida, Journal of transport geography, 58 (2017) 71-91.
[10] C.A. Blazquez, B. Picarte, J.F. Calderón, F. Losada, Spatial autocorrelation analysis of cargo trucks on highway crashes in Chile, Accident Analysis & Prevention, 120 (2018) 195-210.
[11] R. Yu, M. Abdel-Aty, Using hierarchical Bayesian binary probit models to analyze crash injury severity on high speed facilities with real-time traffic data, Accident Analysis & Prevention, 62(2014) 161-167.
[12] Z. Yang, L. Zhibin, L. Pan, Z. Liteng, Exploring contributing factors to crash injury severity at freeway diverge areas using ordered probit model, Procedia Engineering, 21 (2011) 178-185.
[13] T. Abegaz, Y. Berhane, A. Worku, A. Assrat, A. Assefa, Effects of excessive speeding and falling asleep while driving on crash injury severity in Ethiopia: A generalized ordered logit model analysis, Accident Analysis & Prevention, 71 (2014) 15-21.
[14] Z. Ma, I. Steven, J. Chien, C. Dong, D. Hu, T. Xu, Exploring factors affecting injury severity of crashes in freeway tunnels, Tunnelling and underground space technology, 59 (2016) 100-104.
[15]  H. Huang, Y. Peng, J. Wang, Q. Luo, X. Li, Interactive risk analysis on crash injury severity at a mountainous freeway with tunnel groups in China, Accident Analysis & Prevention, 111 (2018) 56-62.
[16] G. Yannis, E. Papadimitriou, E. Dupont, H. Martensen, Estimation of fatality and injury risk by means of in-depth fatal accident investigation data, Traffic injury prevention, 11(5) (2010) 492-502.
[17] M. Effati, A. Sadeghi‐Niaraki, A semantic‐based classification and regression tree approach for modelling complex spatial rules in motor vehicle crashes domain, Wiley Interdisciplinary Reviews: Data Mining and Knowledge Discovery, 5(4) (2015) 181-194.
[18] A. Tavakoli Kashani, M.M. Besharati, An analysis of vehicle occupants’ injury severity in crashes occurred on rural freeways and multilane highways in Iran, International Journal of Transportation Engineering, 4(2) (2016) 137-146.
[19] A.T. Kashani, R. Rabieyan, M.M. Besharati, A data mining approach to investigate the factors influencing the crash severity of motorcycle pillion passengers, Journal of safety research, 51 (2014) 93-98.
[20]S. Jung, X. Qin, C. Oh, Improving strategic policies for pedestrian safety enhancement using classification tree modeling, Transportation Research Part A: Policy and Practice, 85 (2016) 53-64.
[21]  G. Prati, L. Pietrantoni, F. Fraboni, Using data mining techniques to predict the severity of bicycle crashes, Accident Analysis & Prevention, 101 (2017) 44-54.
[22] K. Haleem, A. Gan, Effect of driver’s age and side of impact on crash severity along urban freeways: A mixed logit approach, Journal of safety research, 46 (2013) 67-76.
[23] R. Yu, M. Abdel-Aty, Analyzing crash injury severity for a mountainous freeway incorporating real-time traffic and weather data, Safety science, 63 (2014) 50-56.
[24] L.-Y. Chang, J.-T. Chien, Analysis of driver injury severity in truck-involved accidents using a non-parametric classification tree model, Safety science, 51(1) (2013) 17.22
[25] Z. Wang, H. Chen, J.J. Lu, Exploring impacts of factors contributing to injury severity at freeway diverge areas, Transportation Research Record, 2102(1) (2009) 43-52.
[26] H.H. Bissell, G. Pilkington, J. Mason, D. Woods, Roadway cross section and alinement, in:  Synthesis of Safety Research Related to Traffic Control and Roadway Elements, vol. 1, US Department of Transportation, Federal Highway Administration Washington, DC, 1982.
[27] D.A. Walmsley, I. Summersgill, The relationship between road layout and accidents on modern rural trunk roads, Transport Research Laboratory, 1998.
[28] G. Gibreel, S. Easa, Y. Hassan, I. El-Dimeery, State of the art of highway geometric design consistency, Journal of transportation engineering, 125(4) (1999) 305-313.
[29]T. Ikeda, N. Mori, Analysis of correlation between roadway alignment and traffic accidents, in:  3rd International Symposium on Highway Geometric DesignTransportation Research BoardAmerican Association of State Highway and Transportation Officials (AASHTO) Federal Highway AdministrationAmerican Society of Civil EngineersAssociation Mondiale de la RouteInternational Road FederationInstitute of Transportation Engineers (ITE) National Association of County EngineersTransportation Association of Canada (TAC) Chicago Department of TransportationIllinois Department of TransportationIllinois State Toll Highway Authority, 2005.
[30] J.C. Glennon, T.R. Neuman, J.E. Leisch, SAFETY AND OPERATIONAL CONSIDERATIONS FOR DESIGN OF RURAL HIGHWAY CURVES. FINAL REPORT, in, 1983.
[31]M. SAFAARZADEH, S. SHAABANI, A. AZARMI, Accident Prediction Model on Curves for Two-Lane Rural Road,  (2007).
[32] L. Breiman, J. Friedman, C.J. Stone, R.A. Olshen, Classification and regression trees, CRC press, 1984.
[33] L.-Y. Chang, H.-W. Wang, Analysis of traffic injury severity: An application of non-parametric classification tree techniques, Accident Analysis & Prevention, 38(5) (2006) 1019-1027.
[34] J.R. Stewart, Applications of classification and regression tree methods in roadway safety studies, Transportation Research Record, 1542(1) (1996) 1-5.
[35]E.L. Allwein, R.E. Schapire, Y. Singer, Reducing multiclass to binary: A unifying approach for margin classifiers, Journal of machine learning research, 1(Dec) (2000) 113-141.
[36]D. Delen, R. Sharda, M. Bessonov, Identifying significant predictors of injury severity in traffic accidents using a series of artificial neural networks, Accident Analysis & Prevention, 38(3) (2006) 434-444.
[37] S. Dissanayake, J.J. Lu, Factors influential in making an injury severity difference to older drivers involved in fixed object–passenger car crashes, Accident Analysis & Prevention, 34(5) (2002) 609-618.
[38] D.M. Tax, R.P. Duin, Using two-class classifiers for multiclass classification, in:  Object recognition supported by user interaction for service robots, IEEE, 2002, pp. 124-127.
[39] C. Zegeer, R. Stewart, D. Reinfurt, F. Council, T. Neuman, E. Hamilton, T. Miller, W. Hunter, Cost-effective geometric improvements for safety upgrading of horizontal curves, (1991).
[40] J. Pahukula, S. Hernandez, A. Unnikrishnan, A time of day analysis of crashes involving large trucks in urban areas, Accident Analysis & Prevention, 75 (2015) 155-163.
[41] H.-C. Chu, Assessing factors causing severe injuries in crashes of high-deck buses in long-distance driving on freeways, Accident Analysis & Prevention, 62 (2014) 130-136.
[42] W.Y. Mergia, D. Eustace, D. Chimba, M. Qumsiyeh, Exploring factors contributing to injury severity at freeway merging and diverging locations in Ohio, Accident Analysis & Prevention, 55 (2013) 202-210.
[43] N. Amarasingha, S. Dissanayake, Gender differences of young drivers on injury severity outcome of highway crashes, Journal of safety research, 49 (2014) 113. e111.021
[44] G.F. Ulfarsson, F.L. Mannering, Differences in male and female injury severities in sport-utility vehicle, minivan, pickup and passenger car accidents, Accident Analysis & Prevention, 36(2) (2004) 135-147.
[45] S.H. Al-Senan, P.H. Wright, Prediction of head-on accident sites, Transportation research record, 1122 (1987) 79-85.
[46] C.V. Zegeer, R.C. Deen, J.G. Mayes, The Effect of lane and shoulder widths on accident reductions on rural, two-lane roads,  (1980).
[47]  J.E. Leisch, TRAFFIC CONTROL & ROADWAY ELEMENTS-THEIR RELATIONSHIP TO HIGHWAY SAFETY/REVISED. CHAPTER 12 ALINEMENT,  (1971).
[48] K.R. Agent, R.C. Deen, Relationships between roadway geometrics and accidents,  (1974).
[49] M. Hosseinpour, A.S. Yahaya, A.F. Sadullah, Exploring the effects of roadway characteristics on the frequency and severity of head-on crashes: Case studies from Malaysian Federal Roads, Accident Analysis & Prevention, 62 (2014) 209-222.
[50] P. Gårder, Segment characteristics and severity of headon crashes on two-lane rural highways in Maine, Accident Analysis & Prevention, 38(4) (2006) 652-661.
[51] C. Chen, G. Zhang, R. Tarefder, J. Ma, H. Wei, H. Guan, A multinomial logit model-Bayesian network hybrid approach for driver injury severity analyses in rear-end crashes, Accident Analysis & Prevention, 80 )2015) 7688.
[52] S.A.   Mohamed, K. Mohamed, H.A. Al-Harthi,  Investigating factors affecting the occurrence and severity of rear-end crashes, Transportation research procedia, 25 (2017) 2098-2107.