Data Mining as a Method for Comparison of Traffic Accidents in Şişli District of Istanbul
DOI:
https://doi.org/10.25034/ijcua.2022.v6n2-2Keywords:
Geographic Information Systems, Kernel Density Method, Traffic Accidents, Decision Trees, Artificial Neural Networks, Logistic Regression, Naive BayesAbstract
Studies to reduce traffic accidents are of great importance, especially for metropolitan cities. One of these metropolitan cities is undoubtedly Istanbul. In this study, a perspective on reducing traffic accidents was trying to be revealed by analyzing 3833 fatal and injury traffic accidents that occurred in the Şişli district of Istanbul between 2010-2017, with Data Mining (DM), Machine Learning (ML) and Geographic Information Systems methods (GIS), as well as traditional methods. It is aimed to visually determine the streets where traffic accidents are concentrated, to examine whether the accidents show anomalies according to the effect of the days of the week, to examine the differences according to the accidents that occur in the regions and to develop a model. For this purpose Kernel Density, decision trees, artificial neural networks, logistic regression and Naive Bayes methods were used. From the results obtained, it has been seen that some days are different from other days in terms of traffic accidents, according to the accident intensities and the performances of the modelling techniques used vary according to the regions. This study revealed that the ‘day of the week effect’ can also be applied to traffic accidents
Downloads
References
Aharon, D. Y., & Qadan, M. (2019). Bitcoin and the day-of-the-week effect. Finance Research Letters, 31. https://doi.org/10.1016/j.frl.2018.12.004
Bayrak, E. A., & Kirci, P. (2019). Intelligent Big Data Analytics in Health. Early Detection of Neurological Disorders Using Machine Learning Systems (pp:252-291), IGI Global. https://doi.org/10.4018/978-1-5225-8567-1.ch014
Bil, M., Andrasik, R., & Janoska, Z. (2013). Identification of hazardous road locations of traffic accidents by means of kernel density estimation and cluster significance evaluation. Accident Analysis & Prevention, 55, 265-273. https://doi.org/10.1016/j.aap.2013.03.003.
Budak, H., & Erpolat, S. (2012). Kredi Risk Tahmininde Yapay Sinir Ağları ve Lojistik Regresyon Analizi Karşılaştırılması [Comparison of Artificial Neural Networks and Logistic Regression Analysis in the Credit Risk Prediction]. AJIT‐e: Online Academic Journal of Information Technology, 3(9), 23-30. https://doi.org/10.5824/1309-1581.2012.4.002.x
Camkesen, N., & Bayrakdar, Z. (1999). Alan Analizi Yöntemi ile Kazaların Gerçek Nedenlerinin Saptanması [Field Analysis Method Determining the Real Causes of Situations], II. Transportation and Traffic Congress Book of Proceedings, Ankara. Available Online:https://docplayer.biz.tr/25379493-Ii-ulasim-ve-trafik-kongresi-sergisi-bildiriler-kitabi.html (Accessed on: 02.12.2021).
Cengiz, H., Bilen, Ö., Büyüklü, A. H., & Damgacı, G. (2017). Stock market anomalies: the day of the week effects, evidence from Borsa Istanbul. Journal of Global Entrepreneurship Research, 7(4). https://doi.org/10.1186/s40497-017-0062-6
Çalış, A., Kayapınar, S., & Çetinyokuş, T. (2014). Veri Madenciliğinde Karar Ağacı Algoritmaları ile Bilgisayar ve İnternet Güvenliği Üzerine Bir Uygulama [An Application on Computer and Internet Security with Decision Tree Algorithms in Data Mining]. Endüstri Mühendisliği Dergisi, 25(3), 2-19. https://dergipark.org.tr/tr/pub/endustrimuhendisligi/issue/46771/586362
Dereli, M. A., & Erdogan, S. (2017). A new model for determining the traffic accident black spots using GIS-aided spatial statistical methods. Transportation Research Part A: Policy and Practice, 103, 106-117. https://doi.org/10.1016/j.tra.2017.05.031
Duran, E. A., Pamukçu, A., & Bozkurt, H. (2014). Comparison of Data Mining Techniques for Direct Marketing Campaings. Sigma Journal of Engineering and Natural Sciences, 32, 142-152. https://sigma.yildiz.edu.tr/storage/upload/pdfs/1636023750-en.pdf
Emel, G. G., & Taşkın, Ç. (2005). Veri Madenciliğinde Karar Ağaçları ve Bir Satış Analizi Uygulaması [Decision Trees in Data Mining and a Sales Analysis Application]. Eskişehir Osmangazi Üniversitesi Sosyal Bilimler Dergisi, 6(2), 221-239. https://dergipark.org.tr/tr/pub/ogusbd/issue/10987/131495
Erdogan, S., Yılmaz, İ., Baybura, T., & Gullu, M. (2008). Geographical information systems aided traffic accident analysis system case study: city of Afyonkarahisar. Accident Analysis & Prevention, 40, 174–181. https://doi.org/10.1016/j.aap.2007.05.004
Ersen, M., Büyüklü, A. H., & Taşabat, S. E. (2021). Analysis of Fatal and Injury Traffic Accidents in Istanbul Sarıyer District with Spatial Statistics Methods. Sustainability. 13, 11039. https://doi.org/10.3390/su131911039
Evci, S. (2020). Bitcoin Piyasasında Haftanın Günü Anomalisi [The Day of the Week Anomaly in Bitcoin Market]. Alanya Akademik Bakış Dergisi, 4(1), 53-61. https://doi.org/10.29023/alanyaakademik.664776
Gujarati, D. N., & Porter, D. C. (2009). Basic Econometrics, 5th ed.; McGraw-Hill: New York, NY, USA.
Gündoğdu, G. (2010). Coğrafi Bilgi Teknolojileri Kullanılarak Trafik Kaza Analizi: Adana Örneği [Analysing the Traffic Accidents Using Geographical Information Technologies: Adana Case Study]. Master’s Thesis, Çukurova University, Graduate School of Science and Engineering, Department of Remote Sensing and Geographical Information Systems.
Khokale, R., & Ghate, A. (2017). Data Mining for Traffic Prediction and Analysis using Big Data. International Journal of Engineering Trends and Technology (IJETT), 48(3). https://doi.org/10.14445/22315381/IJETT-V48P227
Le, K. G., Liu, P., & Lin, L. T. (2019). Determining the road traffic accident hotspots using GIS-based temporal-spatial statistical analytic techniques in Hanoi, Vietnam. Geo-spatial Information Science, 23(6), 1-12. https://doi.org/10.1080/10095020.2019.1683437
Lin, L., Wang, Q., & Sadek, A. W. (2014). Data Mining and Complex NetworkAlgorithms for Traffic Accident Analysis. Transportation Research Record, 2460, 128-136. https://doi.org/10.3141/2460-14
Long, W. J., Griffith, J. L., Selker, H. P., & D'Agostino, R. B. (1993). A Comparison of Logistic Regression to Decision-Tree Induction in a Medical Domain. Computers and Biomedical Research, 26(1), 74-97. https://doi.org/10.1006/cbmr.1993.1005
Mohaymany, A. S., Shahri, M., & Mirbagheri, B. (2013). GIS-based method for detecting high-crash-risk road segments using network kernel density estimation. Geo-spatial Information Science, 16(2), 113-119. https://doi.org/10.1080/10095020.2013.766396
Olutayo, V. A., & Eludire, A. A. (2014). Traffic Accident Analysis Using Decision Trees and Neural Networks. I.J. Information Technology and Computer Science, 02, 22-28. https://doi.org/10.5815/ijitcs.2014.02.03
Orhan, A., Emikönel, M., & Emikönel, M. (2021). Volatility and the Day of the Week Effect on Bitcoin Returns. Journal Of Emerging Economies And Policy, 6(2), 51-58. https://dergipark.org.tr/tr/pub/joeep/issue/60720/905965
Orhan, U., & Adem, K. (2012). Naive Bayes Yönteminde Olasılık Çarpanlarının Etkileri [The Effects of Probability Factors in Naive Bayes Method]. Elektrik - Elektronik ve Bilgisayar Mühendisliği Sempozyumu, (s.723). Available Online: https://www.emo.org.tr/ekler/3896071e2f0ee60_ek.pdf (Accessed on: 05.12.2021).
Örnek, Ö., Vatan, S., Sarıoğlu, S., & Yazıcı, A. (2018). Trafik Ağlarında Anomali Tespiti [Anomaly Detection in Traffic Networks]. Eskişehir Osmangazi Üniversitesi Mühendislik ve Mimarlık Fakültesi Dergisi, 26(3), 132-138. https://doi.org/10.31796/ogummf.440285
Özden, C., & Acı, Ç. (2018). Makine öğrenmesi yöntemleri ile yaralamalı trafik kazalarının analizi: Adana örneği [Analysis of injury traffic accidents with machine learning methods: Adana case]. Pamukkale Üniversitesi Mühendislik Bilimleri Dergisi, 24(2), 266-275. https://doi.org/10.5505/pajes.2016.87847
Saplıoğlu, M., & Karaşahin, M. (2006). Coğrafi Bilgi Sistemi yardımı ile Isparta ili kent içi trafik kaza analizi [Urban Traffic Accident Analysis By Using Geographic Information System]. Pamukkale Üniversitesi Mühendislik Bilimleri Dergisi, 12(3), 321-332. https://dergipark.org.tr/tr/pub/pajes/issue/20521/218519
Singh, M., & Kaur, A. (2016). A Review on Road Accident in Traffic System using Data Mining Techniques. International Journal of Science and Research (IJSR), 5(1), 1530-1535. https://doi.org/10.21275/v5i1.nov153099
Şahin, M. (2018). Karar Ağaçları ve Yapay Sinir Ağları Kullanılarak Kasko Sigortalarında Risk Değerlendirme [Risk Assessment in Car Insurance Using Decision Trees and Artificial Neural Networks], Master’s Thesis, Yıldız Technical University, Graduate School of Science and Engineering, Department of Statistics.
Şen, K. (2014). Bankacılıkta Müşteri Terk Modeli [Customer Churn Modelling in Banking], Master’s Thesis, Yıldız Technical University, Graduate School of Science and Engineering, Department of Mathematical Engineering.
Thakali, L., Kwon, T. J., & Fu, L. (2015). Identification of crash hotspots using kernel density estimation and kriging methods: a comparison. Journal of Modern Transportation, 23, 93-106. https://doi.org/10.1007/s40534-015-0068-0
TURKSTAT. (2020). Highway Traffic Accident Statistics. Available Online: https://data.tuik.gov.tr/Bulten/Index?p=Road-Traffic-Accident-Statistics-2020-37436 (Accessed on: 05.12.2021).
Walsh, S. (2005). Applying Data Mining Techniques Using SAS® Enterprise Miner-Course Notes. North Carolina: SAS Institute Inc.
Xie, Z., & Yan, J. (2008). Kernel Density Estimation of traffic accidents in a network space. Computers, Environment and Urban Systems, 32(5), 396-406. https://doi.org/10.1016/j.compenvurbsys.2008.05.001
Xie, Z., & Yan, J. (2013). Detecting traffic accident clusters with network kernel density estimation and local spatial statistics: an integrated approach. Journal of Transport Geography, 31, 64-71. https://doi.org/10.1016/j.jtrangeo.2013.05.009
Yavuz, A. A., Ergül, B., & Aşık, E. G. (2021). Trafik Kazalarının Makine Öğrenmesi Yöntemleri Kullanılarak Değerlendirilmesi [Evaluation of Traffic Accidents Using Machine Learning Methods]. Uluslararası Mühendislik Araştırma ve Geliştirme Dergisi, 13(1), 66-73. https://doi.org/10.29137/umagd.705156
Yavuz, A., & Çilengiroğlu, Ö. V. (2020). Lojistik Regresyon ve CART Yöntemlerinin Tahmin Edici Performanslarının Yaşam Memnuniyeti Verileri İçin Karşılaştırılması [Comparison of Predictive Performance of Logistic Regression and CART Methods for Life Satisfaction Data]. Avrupa Bilim ve Teknoloji Dergisi, 18, 719-727. https://doi.org/10.31590/ejosat.691215
Yılmaz, E. (2012). İstatistiksel Analiz Yöntemi Olarak Veri Madenciliğinde CHAID Algoritması ve Türkiye’de İşgücü Piyasasının Durumunun ve Bunun Nedenlerinin Belirlenmesine İlişkin Bir Uygulama [The Chaid Algorithm in Data Mining As A Statistical Analysis Method and An Application Including Determination to the Situation of Labour Market and Its Reasons in Turkey], Master’s Thesis, Yıldız Technical University, Graduate School of Social Sciences, Department of Business Administration.
Yılmaz, F., & Akkaya, G. C. (2020). Kripto Para Piyasalarında Etkinlik; Haftanın Günü Etkisi: Bitcoin ve Litecoin Örneği [The Efficiency in Cryptocurrency Markets; The Day of the Week Effect: Bitcoin and Litecoin Example]. Girişimcilik İnovasyon ve Pazarlama Araştırmaları Dergisi, 4(8), 166-178. https://doi.org/10.31006/gipad.767255
Zhao, Y., & Zhang, Y. (2008). Comparison of decision tree methods for finding active objects. Advances in Space Research, 41(12), 1955-1959. https://doi.org/10.1016/j.asr.2007.07.020
Published
How to Cite
Issue
Section
License
Copyright (c) 2022 Ph.D. Candidate Mert Ersen, Professor Dr. Ali Hakan Büyüklü, Professor Dr. Semra Erpolat Taşabat

This work is licensed under a Creative Commons Attribution 4.0 International License.