Bayesian Network Model for Analysis of Traffic Accidents

Yıl 2013, Cilt: 6 Sayı: 2, 41 - 52, 28.05.2013

Esma Nur Çinicioğlu , Muhammet Atalay , Harun Yorulmaz

Öz

The use of high ways as the major means of transportation in Turkey causes a rapid increase in traffic intensity. As a result of the fact that the current infrastructure is unable to respond this rapid increase of traffic intensity, in addition to the traffic infringements made both by drivers and pedestrians, each year a huge number of traffic accidents occur. To prevent the traffic accidents with tangible and intangible losses resulting from it, and to take the necessary precautions in that purpose, it is necessary to conduct a detailed analysis of traffic accidents and the factors influencing its happening. In this research, traffic accidents and the factors influencing traffic accident occurrences are analyzed via Bayesian networks. As a graphical model, Bayesian networks possess a special importance with its abilities such as showing the conditional dependencies between the variables, not being limited to only one output variable, the ability to update the network through evidence observation and the capability to transfer all these information through a graphical interface. In this research, using the official traffic accident reports obtained from Silivri Regional Branch Office and County Gendarmerie Traffic Command a data set is constructed and the corresponding Bayesian network is learned from this data set. Prediction capability of the network is verified through the test data set and the efficiency of the learned model is confirmed with the lift over marginal resulting as positive. Sensitivity analysis is performed for the variables in the network. The proposed model in this research is an exemplary model to analyze the dependency structure between the effects, causes and outcomes of traffic accidents.

Anahtar Kelimeler

― Bayesian networks, analysis of traffic accidents, sensitivity analysis

Trafik Kazaları Analizi için Bayes Ağları Modeli

Öz

Türkiye'de başlıca ulaşım yolu olarak karayollarının kullanılması trafik yoğunluğunda hızlı bir artışa neden olmaktadır. Mevcut altyapının hızla artan bu yoğunluğa karşılık vermekte zorlanmasına ek olarak sürücü ve yayalar tarafından yapılan trafik ihlalleri sonucunda ülkemizde her yıl çok sayıda trafik kazası meydana gelmektedir. Trafik kazalarının ve kazaların sonucunda oluşan maddi ve manevi kayıpların önlenebilmesi, bu doğrultuda gerekli tedbirlerin alınabilmesi için trafik kazalarının ve kazalara neden olan etmenlerin detaylı bir şekilde analiz edilmesi gerekmektedir. Bu çalışmada trafik kazaları ve trafik kazalarına neden olan etmenler Bayes Ağları aracılığıyla analiz edilmektedir. Bayes Ağları değişkenler arasındaki koşullu bağımlılık ilişkilerini yansıtması, tek bir bağımsız değişkene bağımlı kalmaması, yapılan gözlemler uyarınca ağın ve çıkarımların yenilenebilmesi ve tüm bu çıkarımların görsel bir dil ile kullanıcıya aktarılabilmesi açısından önemli grafiksel bir modeldir. Bu çalışmada Silivri Bölge Trafik Şube Müdürlüğü ve İlçe Jandarma Trafik Tim Komutanlığı'ndan elde edilen maddi hasarlı trafik kaza tespit tutanakları ve trafik kaza tespit tutanaklarının içerdiği bilgiler doğrultusunda oluşturulan veri setinden ilgili Bayes Ağı öğrenilmiştir. Oluşturulan Bayes Ağı'nın doğru tahminleme oranı ayrılan test datası aracılığıyla sınanmış ve oluşturulan modelin etkinliği, model için hesaplanan logskorun marjinal modelin logskoru ile karşılaştırılması sonucu teyit edilmiştir. Ağda yer alan değişkenler için duyarlılık analizleri yapılmıştır. Çalışma, trafik kazalarına neden olan etkenlerin birbirleri ve kaza sonuçları ile ilişkilerini analiz edebilen,  örnek bir model oluşturması açısından önemlidir.

Anahtar Kelimeler

Bayes Ağları, Trafik Kazaları Analizi, Duyarlılık Analizi

Kaynakça

• (REFERENCES) B. Güvenal, A. Çabuk, M. Yavuz, “Trafik kazaları verilerine bağlı olarak CBS destekli ulaşım planlaması: Eskişehir kenti örneği”, Harita ve Kadastro Mühendisleri Odası, Mühendislik Ölçmeleri STB Komisyonu 2. Mühendislik Ölçmeleri Sempozyumu, İstanbul, 2005.
• E. Özgan, Bolu Dağı Dahil D100-11 Devlet Karayolu Kesiminin Çok Yönlü Klinik İncelenmesi ve Kaza Kara Noktalarının Belirlenmesi Sonuç Raporu, Düzce, 2007.
• M. Tuncuk, Coğrafi Bilgi Sistemi Yardımıyla Trafik Kaza Analizi: Isparta Örneği, Yüksek Lisans Tezi, Süleyman Demirel Üniversitesi, Fen Bilimleri Enstitüsü, 2004.
• X. Hongguo, Z. Huiyong, Z. Fang, “Bayesian Network-Based Road Traffic Accident Causality Analysis”, WASE International Conference on Information Engineering, 3, 413417, Beidaihe, Hebei, 2010.
• İnternet: Karayolları Genel Müdürlüğü, Trafik Kazaları Özeti 2011, http://www.kgm.gov.tr/SiteCollectionDocuments/KGMdocum ents/Trafik/TrafikKazaOzet.pdf, 15.04.2013.
• İnternet: TCDD, Cumhuriyetimizin 80 Yıllık Tarihinde Devlet Demiryolları, www.tcdd.gov.tr/home/detail/?id=267, 02013.
• İnternet: T.C. Ulaştırma Bakanlığı, Türkiye Ulaşım ve İletişim Stratejisi, Sayfa 20-34, http://www.sp.gov.tr/upload/xSPTemelBelge/files/93C5Y+Tur kiye_Ulasim_veIletisim_Stratejisi.pdf, 15.04.2013.
• A. S. Al-Ghamdi, “Using logistic regression to estimate the influence of accident factors on accident severity”, Accident Analysis and Prevention, 34, 729–741, 2002.
• M. Bédard, G. H. Guyatt, M. J. Stones, J. P. Hirdes, “The independent contribution of driver, crash, and vehicle characteristics to driver fatalities”, Accident Analysis and Prevention, 34, 717–727, 2002.
• K. M. Kockelman, Y. J. Kweon, “Driver injury severity: an application of ordered probit models”, Accident Analysis and Prevention, 34, 313–321, 2002.
• J. C. Milton, V. N. Shankar, F. L. Mannering, “Highway accident severities and the mixed logit model: An exploratory empirical analysis”, Accident Analysis and Prevention, 40, 260–266, 2008.
• T. Yamamoto, V. N. Shankar, “Bivariate ordered-response probit model of driver's and passenger's injury severities in collisions with fixed objects”, Accident Analysis and Prevention, 36, 869– 876, 2004.
• K. K. W. Yau, H. P. Lo, S. H. H. Fung, “Multiple-vehicle traffic accidents in Hong Kong”, Accident Analysis and Prevention, 38, 1157–1161, 2006.
• L. Y. Chang, H. W. Wang, “Analysis of traffic injury severity: An application of non-parametric classification tree techniques”, Accident Analysis and Prevention, 38, 1019–1027, 2006.
• S. X. Zhu, J. Lu, Q. J. Xiang, L. Yan, “Intersection safety evaluation method based on Bayesian network”, International Conference on Measuring Technology and Mechatronics Automation, 3, 234–237, Zhangjiajie, Hunan, 2009.
• A. Gregoriades, K. C. Mouskos, “Black spots identification through a Bayesian Networks quantification of accident risk index”, Transportation Research Part C: Emerging Technologies, 28, 28-43, 2013.
• Y. Tian, H. Chen, B. Liu, D. Xiao, “Safety Evaluation of BridgeTunnel Sections on Mountainous Expressway Based on Bayesian Network”, 10th International Conference of Chinese Transportation Professionals, Beijing, China, 2010.
• M. Hänninen, P. Kujala, “Influences of variables on ship collision probability in a Bayesian belief network model”, Reliability Engineering ve System Safety, 102, 27-40, 2012.
• W. Marsh, G. Bearfield, “Using Bayesian networks to model accident causation in the UK railway industry”, International Conference on Probabilistic Safety Assessment and Management PSAM7, Berlin, 2004.
• M. Atalay, H. Yorulmaz, O. Onay, E.N. Çinicioğlu, “Trafik Kazaları Analizi için Bayes Ağları Modeli”, Yöneylem Araştırması ve Endüstri Mühendisliği 31. Ulusal Kongresi, Sakarya, 2011.
• J. de Oña, R. O. Mujalli, F. J. Calvo, “Analysis of traffic accident injury severity on Spanish rural highways using Bayesian Networks”, Accident Analysis and Prevention, 43(1), 402-411, 20 R. O. Mujalli, J. de Ona, “A method for simplifying the analysis of traffic accidents injury severity on two-lane highways using Bayesian Networks”, Journal of Safety Research, 42(5), 317-326, 20 J. K. Kihlberg, K. J. Tharp, Accident rates as related to design elements of rural highways, NCHRP Report, 47, 1968.
• Y. G. Qi, B. L. Smith, J. Guo, “Freeway Accident Likelihood Prediction Using a Panel Data Analysis Approach”, ASCE Journal Of Transportation Engineering, 149- 156, 2007.
• E. Bayam, J. Liebowitz, W. Agresti, “Older drivers and accidents: A meta analysis and data mining application on traffic accident data”, Expert Systems with Applications, 29, 598–629, 200 A. Gregoriades, “Road safety assessment using bayesian belief networks and agent-based simulation”, IEEE International Conference on Systems, Man and Cybernetics (ISIC), IEEE, 615-620, 2007.
• S. Hu, X. Li, Q. Feng, Z. Yang, “Use of Bayesian Method for Assessing Vessel Traffic Risk At Sea”, International Journal of Information Technology and Decision Making, 7, 627-638, 2008. Z. X. Xu, Y. Jiang, F. Lin, L. Dai, “The Analysis and Prevent in Traffic Accidents Based on Bayesian Network”, Advanced Engineering Forum, 1, 21-25, 2011.
• Y. Xie, D. Lord, Y. Zhang, “Predicting motor vehicle collisions using Bayesian neural network models: An empirical analysis”, Accident Analysis and Prevention, 39, 922 – 933, 2007.
• H. Wang, Z. Lai, M. Xianghai, “Traffic Accidents Prediction Model Based on Fuzzy Logic”, Advances in Information Technology and Education, Communications in Computer and Information Science, 201, 101-108, 2011.
• M. Neil, B. Malcom, R. Shaw, “Modelling an Air Traffic Control Environment Using Bayesian Belief Network”, 21 st International System Safety Conference, Ottawa, Ontario, Canada, 2003.
• N. Friedman, M. Goldszmidt, D. Heckerman, S. Russell, “Challenge: what is the impact of Bayesian Networks on learning?”, 15th international joint conference on artifical intelligence, Morgan Kaufmann Publishers Inc., 1, 10-15, 19 Y. Bayraktarli, J. Ulfkjaer, U. Yazgan, M. Faber, “On the Application of Bayesian Probabilistic Networks for Earthquake Risk Management”, Ninth International Conference on Structural Safety and Reliability (ICOSSAR 05), Rome, 2005. E. N. Cinicioglu, P. P. Shenoy, C. Kocabasoglu, “Use of radio frequency identification for targeted advertising: A collaborative filtering approach using Bayesian Networks”, 9th European Conference on Symbolic and Quantitative Approaches to Reasoning with Uncertainty, ECSQARU’07, Heidelberg, Springer-Verlag, 889–900, Berlin, 2007.
• D. Nikovski, “Constructing Bayesian Networks for Medical Diagnosis from Incomplete and Partially Correct Statistics,” IEEE Transactions on Knowledge and Data Engineering, 12(4), 509516, 2000.
• N. E. Fenton, M. Neil, “The Jury Observation Fallacy and the Use of Bayesian Networks to Present Probabilistic Legal Arguments”, Mathematics Today, 36(6), 180–187, 2000.
• E. J. Lauria, P. J. Duchessi, “A methodology for developing Bayesian networks: An application to information technology (IT) implementation”, European Journal of operational research, 79(1), 234-252, 2007.
• F. Liu, F. Tian, Q. Zhu, “An Improved Greedy Bayesian Network Learning Algorithm on Limited Data”, Artificial Neural Networks-ICANN Porto 2007 17th International Conference Proceedings, Lecture Notes in Computer Science, 4668, 49–57, 200 İnternet: Karayolları Trafik Kanunu, http://www.trafik.gov.tr/mevzuat/karayollari_trafik_yonetmeligi.a sp , 002011.
• D. Heckerman, D.M. Chickering, C. Meek, R. Rounthwaite, C. Kadie, “DependencyNetworks for Inference, Collaborative Filtering and Data Visualization”, Journal of Machine Learning Research, 1, 49–75, 2000.