Research Article
BibTex RIS Cite

İstanbul Boğazı’ndaki ticari gemi kazalarının karar ağacı yöntemiyle analizi

Year 2021, , 10 - 20, 21.10.2020

Erkan Çakır Bünyamin Kamal

https://doi.org/10.3153/AR21002

Abstract

Bu çalışmada İstanbul Boğaz bölgesi olarak İstanbul Gemi Trafik Hizmetlerinin kapsama alanına giren Türkeli, Kandilli, Kadıköy ve Marmara sektörlerinde 2001-2016 yılları arasında meydana gelen ticari gemi kazaları incelemeye tabi tutulmuştur. Ulaştırma ve Altyapı Bakanlığı Ana Arama Kurtarma Koordinasyon Merkezi (AAKKM) veri tabanındaki kaza kayıtlarına uygulanan filtrelemeler sonucunda 500 groston üzeri ticari yük gemilerinin karıştığı 535 adet gemi kazası analiz edilmiştir. Belirtilen sektörlerde meydana gelen ticari yük gemi kazaları Ki-kare Otomatik Etkileşim Dedektörü (CHAID) karar ağacı yöntemi ile incelenmiştir. CHAID karar ağacı yöntemi sınıflandırma ve büyük veri kümelerinden anlamlı kurallar çıkarmada en yaygın kullanılan karar ağacı algoritmalarından biridir. CHAID karar ağacı yöntemi icra edilerek ticari yük gemilerinde meydana gelen kazaların tipi (çatışma/çatma, karaya oturma ve diğer) ile gemi faktörleri (gemi tipi, gemi boyu, gemi tonajı, gemi yaşı, gemi bayrağı, gemi yüklülük durumu), zaman faktörleri (kaza zamanı ve kaza mevsimi) ve diğer faktörler (kazanın meydana geldiği sektör, kaza nedeni ve gemiye pilot alınması durumu) arasındaki ilişki incelemeye alınmıştır. Kazanın meydana geldiği sektör, gemide pilot bulunması durumu, gemi tipi ve kaza zamanı kaza tipini etkileyen en önemli girdi değişkenleri olarak bulunmuştur. Veri setine uygulanan Karar Ağacı yöntemi sonucuna göre Kadıköy sektöründe meydana gelen kazaların % 86 olasılıkla çatışma/çatma, Kandilli veyahut Marmara sektörlerinde meydana gelen kazaların % 48 olasılıkla çatışma/çatma ve Türkeli sektöründe ise kazaların % 36 olasılıkla çatışma/çatma ve diğer kaza tipleri ile sonuçlandığı görülmüştür.

Keywords

İstanbul Boğazı Gemi kazaları Kaza analizi Karar ağacı

References

  • Akten, N. (2003). The Strait of Istanbul (Bosphorus): The seaway separating the continents with its dense shipping traffic. Turkish J. Marine Sciences, 9(3), 241-265.
  • Althuwaynee, O. F., Pradhan, B., Lee, S. (2016). A novel integrated model for assessing landslide susceptibility mapping using CHAID and AHP pair-wise comparison. International Journal of Remote Sensing, 37(5), 1190-1209. https://doi.org/10.1080/01431161.2016.1148282
  • Bayar, N., Özüm, S., Yılmaz, H. (2008). Analysis of Accidents in Istanbul Strait. http://web.deu.edu.tr/maritime/imla2008/Papers/43.pdf Erişim Tarihi: 15.04.2020
  • De Oña, J., López, G., Abellán, J. (2013). Extracting decision rules from police accident reports through decision trees. Accident Analysis & Prevention, 50, 1151-1160. https://doi.org/10.1016/j.aap.2012.09.006
  • Deniz Ticareti İstatistikleri (2018) Filo, Denizyolu Taşıma, Teşvik, Gemi Sanayi, Gemi Denetim, Türk Boğazları Geçiş İstatistikleri. https://denizcilik.uab.gov.tr/uploads/pages/yayinlar/deniz-ticaret-2018-istatistikleri.pdf Erişim Tarihi: 15.03.2020
  • Díaz-Pérez, F.M., Bethencourt-Cejas, M. (2016). CHAID algorithm as an appropriate analytical method for tourism market segmentation. Journal of Destination Marketing & Management, 5(3), 275-282. https://doi.org/10.1016/j.jdmm.2016.01.006
  • Ece, N.J. (2011). İstanbul Boğazı’nda Meydana Gelen Deniz Kazalarının İncelenmesi ve Analizi. Dokuz Eylül Üniversitesi Denizcilik Fakültesi Dergisi, 3(2), 37-59. Ece, N.J. (2016). Kılavuzluk Hizmetlerinin Deniz Emniyetine Katkısı: İstanbul Boğazı’nda Kazaya Karışan Gemiler İle Kılavuz Kaptan Almaları Arasındaki İlişkinin Analizi. Journal of ETA Maritime Science, 4(1), 3-21.
  • Erol, S., Başar, E. (2015). The analysis of ship accident occurred in Turkish search and rescue area by using decision tree. Maritime Policy & Management, 42(4), 377-388. https://doi.org/10.1080/03088839.2013.870357
  • Erol, S., Demir, M., Çetişli, B., Eyüboğlu, E. (2018). Analysis of ship accidents in the Istanbul Strait using neuro-fuzzy and genetically optimised fuzzy classifiers. The Journal of Navigation, 71(2), 419-436. https://doi.org/10.1017/S0373463317000601
  • Galguera, L., Luna, D., Méndez, M.P. (2006). Predictive segmentation in action-Using CHAID to segment loyalty card holders. International Journal of Market Resear-ch, 48(4), 459-479. https://doi.org/10.1177/147078530604800407
  • Han, J., Kamber, M., Pei, J. (2012). Data mining: concepts and techniques. Waltham, MA., Morgan Kaufman Publishers.
  • İstikbal, C. (2020). Strait of Istanbul, major accidents and abolishment of left-hand side navigation. Aquatic Resear-ch, 3(1), 40-65. https://doi.org/10.3153/AR20005
  • Kass, G.V. (1980). An exploratory technique for investigating large quantities of categorical data. Journal of the Royal Statistical Society: Series C (Applied Statistics), 29(2), 119-127. https://doi.org/10.2307/2986296
  • KEGM. (2020). Türk Boğazları Gemi Trafik Hizmetleri Kullanıcı Rehberi, https://kiyiemniyeti.gov.tr/Data/1/Files/Document/Documents/pH/EG/cT/iV/T%C3%9CRK%20BO%C4%9EAZLARI%20GEM%C4%B0%20TRAF%C4%B0K%20H%C4%B0ZMETLER%C4%B0%20KULLANICI%20REHBER%C4%B0.pdf. Erişim Tarihi: 10.05.2020
  • Kiel Canal. (2018). The Kiel Canal A major waterway of international importance, https://www.gdws.wsv.bund.de/SharedDocs/Downloads/DE/Publikationen/NOK_englisch.pdf?__blob=publicationFile&v=4 Erişim Tarihi: 22.06.2020
  • Lin, C.L., Fan, C.L. (2019). Evaluation of CART, CHAID, and QUEST algorithms: a case study of construction defects in Taiwan. Journal of Asian Architecture and Building Engineering, 18(6), 539-553. https://doi.org/10.1080/13467581.2019.1696203
  • Mistikoglu, G., Gerek, I.H., Erdis, E., Usmen, P.M., Cakan, H., Kazan, E.E. (2015). Decision tree analysis of construction fall accidents involving roofers. Expert Systems with Applications, 42(4), 2256-2263. https://doi.org/10.1016/j.eswa.2014.10.009
  • Otay, N.E., Özkan, Ş. (2005). “Risk Map for the Strait of Istanbul,” Proc. of the 5th Natl Conf on Coastal Engineering, May 2005, p19-32.
  • Özdemir, M. (2019). Türk Boğazları’nda Meydana Gelen Gemi Kazalarının Konumsal Analizi ve Değerlendirilmesi, Karadeniz Teknik Üniversitesi Fen Bilimleri Enstitüsü Yüksek Lisans Tezi, Trabzon.
  • Panama Canal (2019). Panama Canal Traffic Fiscal Years 2017 Through 2019, https://www.pancanal.com/eng/op/transit-stats/2019/Table-01-Rev.pdf Erişim Tarihi: 22.06.2020
  • Prati, G., Pietrantoni, L., Fraboni, F. (2017). Using data mining techniques to predict the severity of bicycle crashes. Accident Analysis & Prevention, 101, 44-54. https://doi.org/10.1016/j.aap.2017.01.008
  • Rokach, L., & Maimon, O. Z. (2008). Data mining with decision trees: theory and applications (Vol. 69). World scientific. https://doi.org/10.1142/6604
  • Sezgin, F., Kadıoğlu, M. (2000). İstanbul Boğazı'ndaki Deniz Kazalarının İstatistiksel Analizi, Marmara Denizi 2000 Sempozyumu (Öztürk, B., Kadıoğlu, M. ve Öztürk, H. Ed.) TÜDAV 11-12 Kasım 2000, Ataköy Marina/ İstanbul, s. 149-160.
  • SPSS. (1998). Answer Tree 2.0: User‘s Guide. Chicago, IL: SPSS.
  • Suez Canal (2019). Navigation Statistics, https://www.suezcanal.gov.eg/English/Navigation/Pages/NavigationStatistics.aspx Erişim Tarihi: 22.06.2020
  • Ulaştırma ve Altyapı Bakanlığı (2019). Türk Boğazları Gemi Geçiş İstatistikleri, https://atlantis.udhb.gov.tr/istatistik/gemi_gecis.aspx Erişim Tarihi: 10.03.2020
  • Virens, M. (2001). Market segmentation. Analytical developments and application guidelines. Millward Brown IntelliQuest.
  • Yılmaz, F., İlhan, M. (2018). Türk Bayraklı Gemilerin Karıştığı Deniz Kazaları ve Denizcilere Etkilerine İlişkin Bir Analiz. Gemi ve Deniz Teknolojisi, (211), 80-95.

Analysis of merchant vessel accidents in Istanbul strait through decision tree method

Year 2021, , 10 - 20, 21.10.2020

Erkan Çakır Bünyamin Kamal

https://doi.org/10.3153/AR21002

Abstract

In this study merchant vessel accidents which occured between 2001 and 2016 in the sectors of Türkeli, Kandilli, Kadıköy, Marmara which constitutes Istanbul Strait region under Istanbul Vessel Traffic Services scope have been examined. Data was obtained from database of Ministry of Transport and Infrastructure Main Search and Rescue Coordination Center, and after data cleansing process, 535 vessel accidents which involve merchant cargo vessels of above 500 grosston have been analyzed. Merchant cargo vessel accidents which were taken place in the specified sectors have been examined with CHAID (Chi-square Automatic Interaction Detector) Decision Tree method. CHAID Decision Tree method is one of the most common used decision tree algorithms in extracting meaningful rules from big datasets and for classification. Through conducting CHAID Decision Tree method for merchant vessel accidents relationship between accident type (collision/contact, grounding and other) and vessel factors (vessel type, Length overall (LOA), vessel gross tonnage, vessel age, flag, loading condition), time factors (accident time, season of accident) and other factors (sector where accident occured, pilot on board or not) has been analyzed. Accident occuring sector, pilot on board/not, vessel type and accident time have been found as the most important input variables. Based on the result of the Decision Tree method applied to the data set, it was observed that the accidents occurring in the Kadıköy sector were collision / contact with 86% probability, the accidents occurring in the Kandilli or Marmara sectors were collision / contact with 48% probability and in the Türkeli sector, both collision / contact and other accident types had 36% occurring probability.

Keywords

Istanbul Strait Vessel accidents Accident analysis Decision tree

References

  • Akten, N. (2003). The Strait of Istanbul (Bosphorus): The seaway separating the continents with its dense shipping traffic. Turkish J. Marine Sciences, 9(3), 241-265.
  • Althuwaynee, O. F., Pradhan, B., Lee, S. (2016). A novel integrated model for assessing landslide susceptibility mapping using CHAID and AHP pair-wise comparison. International Journal of Remote Sensing, 37(5), 1190-1209. https://doi.org/10.1080/01431161.2016.1148282
  • Bayar, N., Özüm, S., Yılmaz, H. (2008). Analysis of Accidents in Istanbul Strait. http://web.deu.edu.tr/maritime/imla2008/Papers/43.pdf Erişim Tarihi: 15.04.2020
  • De Oña, J., López, G., Abellán, J. (2013). Extracting decision rules from police accident reports through decision trees. Accident Analysis & Prevention, 50, 1151-1160. https://doi.org/10.1016/j.aap.2012.09.006
  • Deniz Ticareti İstatistikleri (2018) Filo, Denizyolu Taşıma, Teşvik, Gemi Sanayi, Gemi Denetim, Türk Boğazları Geçiş İstatistikleri. https://denizcilik.uab.gov.tr/uploads/pages/yayinlar/deniz-ticaret-2018-istatistikleri.pdf Erişim Tarihi: 15.03.2020
  • Díaz-Pérez, F.M., Bethencourt-Cejas, M. (2016). CHAID algorithm as an appropriate analytical method for tourism market segmentation. Journal of Destination Marketing & Management, 5(3), 275-282. https://doi.org/10.1016/j.jdmm.2016.01.006
  • Ece, N.J. (2011). İstanbul Boğazı’nda Meydana Gelen Deniz Kazalarının İncelenmesi ve Analizi. Dokuz Eylül Üniversitesi Denizcilik Fakültesi Dergisi, 3(2), 37-59. Ece, N.J. (2016). Kılavuzluk Hizmetlerinin Deniz Emniyetine Katkısı: İstanbul Boğazı’nda Kazaya Karışan Gemiler İle Kılavuz Kaptan Almaları Arasındaki İlişkinin Analizi. Journal of ETA Maritime Science, 4(1), 3-21.
  • Erol, S., Başar, E. (2015). The analysis of ship accident occurred in Turkish search and rescue area by using decision tree. Maritime Policy & Management, 42(4), 377-388. https://doi.org/10.1080/03088839.2013.870357
  • Erol, S., Demir, M., Çetişli, B., Eyüboğlu, E. (2018). Analysis of ship accidents in the Istanbul Strait using neuro-fuzzy and genetically optimised fuzzy classifiers. The Journal of Navigation, 71(2), 419-436. https://doi.org/10.1017/S0373463317000601
  • Galguera, L., Luna, D., Méndez, M.P. (2006). Predictive segmentation in action-Using CHAID to segment loyalty card holders. International Journal of Market Resear-ch, 48(4), 459-479. https://doi.org/10.1177/147078530604800407
  • Han, J., Kamber, M., Pei, J. (2012). Data mining: concepts and techniques. Waltham, MA., Morgan Kaufman Publishers.
  • İstikbal, C. (2020). Strait of Istanbul, major accidents and abolishment of left-hand side navigation. Aquatic Resear-ch, 3(1), 40-65. https://doi.org/10.3153/AR20005
  • Kass, G.V. (1980). An exploratory technique for investigating large quantities of categorical data. Journal of the Royal Statistical Society: Series C (Applied Statistics), 29(2), 119-127. https://doi.org/10.2307/2986296
  • KEGM. (2020). Türk Boğazları Gemi Trafik Hizmetleri Kullanıcı Rehberi, https://kiyiemniyeti.gov.tr/Data/1/Files/Document/Documents/pH/EG/cT/iV/T%C3%9CRK%20BO%C4%9EAZLARI%20GEM%C4%B0%20TRAF%C4%B0K%20H%C4%B0ZMETLER%C4%B0%20KULLANICI%20REHBER%C4%B0.pdf. Erişim Tarihi: 10.05.2020
  • Kiel Canal. (2018). The Kiel Canal A major waterway of international importance, https://www.gdws.wsv.bund.de/SharedDocs/Downloads/DE/Publikationen/NOK_englisch.pdf?__blob=publicationFile&v=4 Erişim Tarihi: 22.06.2020
  • Lin, C.L., Fan, C.L. (2019). Evaluation of CART, CHAID, and QUEST algorithms: a case study of construction defects in Taiwan. Journal of Asian Architecture and Building Engineering, 18(6), 539-553. https://doi.org/10.1080/13467581.2019.1696203
  • Mistikoglu, G., Gerek, I.H., Erdis, E., Usmen, P.M., Cakan, H., Kazan, E.E. (2015). Decision tree analysis of construction fall accidents involving roofers. Expert Systems with Applications, 42(4), 2256-2263. https://doi.org/10.1016/j.eswa.2014.10.009
  • Otay, N.E., Özkan, Ş. (2005). “Risk Map for the Strait of Istanbul,” Proc. of the 5th Natl Conf on Coastal Engineering, May 2005, p19-32.
  • Özdemir, M. (2019). Türk Boğazları’nda Meydana Gelen Gemi Kazalarının Konumsal Analizi ve Değerlendirilmesi, Karadeniz Teknik Üniversitesi Fen Bilimleri Enstitüsü Yüksek Lisans Tezi, Trabzon.
  • Panama Canal (2019). Panama Canal Traffic Fiscal Years 2017 Through 2019, https://www.pancanal.com/eng/op/transit-stats/2019/Table-01-Rev.pdf Erişim Tarihi: 22.06.2020
  • Prati, G., Pietrantoni, L., Fraboni, F. (2017). Using data mining techniques to predict the severity of bicycle crashes. Accident Analysis & Prevention, 101, 44-54. https://doi.org/10.1016/j.aap.2017.01.008
  • Rokach, L., & Maimon, O. Z. (2008). Data mining with decision trees: theory and applications (Vol. 69). World scientific. https://doi.org/10.1142/6604
  • Sezgin, F., Kadıoğlu, M. (2000). İstanbul Boğazı'ndaki Deniz Kazalarının İstatistiksel Analizi, Marmara Denizi 2000 Sempozyumu (Öztürk, B., Kadıoğlu, M. ve Öztürk, H. Ed.) TÜDAV 11-12 Kasım 2000, Ataköy Marina/ İstanbul, s. 149-160.
  • SPSS. (1998). Answer Tree 2.0: User‘s Guide. Chicago, IL: SPSS.
  • Suez Canal (2019). Navigation Statistics, https://www.suezcanal.gov.eg/English/Navigation/Pages/NavigationStatistics.aspx Erişim Tarihi: 22.06.2020
  • Ulaştırma ve Altyapı Bakanlığı (2019). Türk Boğazları Gemi Geçiş İstatistikleri, https://atlantis.udhb.gov.tr/istatistik/gemi_gecis.aspx Erişim Tarihi: 10.03.2020
  • Virens, M. (2001). Market segmentation. Analytical developments and application guidelines. Millward Brown IntelliQuest.
  • Yılmaz, F., İlhan, M. (2018). Türk Bayraklı Gemilerin Karıştığı Deniz Kazaları ve Denizcilere Etkilerine İlişkin Bir Analiz. Gemi ve Deniz Teknolojisi, (211), 80-95.
There are 28 citations in total.

Details

Primary Language Turkish
Subjects Maritime Engineering
Journal Section Research Articles
Authors

Erkan Çakır 0000-0001-8486-3310

Bünyamin Kamal 0000-0002-9885-114X

Publication Date October 21, 2020
Submission Date June 1, 2020
Published in Issue Year 2021

Cite

APA Çakır, E., & Kamal, B. (2021). İstanbul Boğazı’ndaki ticari gemi kazalarının karar ağacı yöntemiyle analizi. Aquatic Research, 4(1), 10-20. https://doi.org/10.3153/AR21002

16291

is licensed under a CreativeCommons Attribtion-ShareAlike 4.0 International Licence 14628   1325927040

Diamond Open Access refers to a scholarly publication model in which journals and platforms do not charge fees to either authors or readers.

Open Access Statement:

This is an open access journal which means that all content is freely available without charge to the user or his/her institution. Users are allowed to read, download, copy, distribute, print, search, or link to the full texts of the articles, or use them for any other lawful purpose, without asking prior permission from the publisher or the author. This is in accordance with the BOAI definition of open access.

Archiving Policy:

Archiving is done according to TÜBİTAK ULAKBİM "DergiPark" publication policy (LOCKSS).