SavedAdd your journal

Journals / Pamukkale Üniversitesi Mühendislik Bilimleri Dergisi / 2018 / Cilt: 24 - Sayı: 2

Analysis of injury traffic accidents with machine learning methods: Adana case

Makine öğrenmesi yöntemleri ile yaralanmalı trafik kazalarının analizi: Adana örneği

Cevher ÖZDEN
Çiğdem ACI
Pages
266–275
Publication Date
2018-04-30
DOI
—
🏛️Bibliographic metadata and full text access for this article are provided via DergiPark.
DergiPark Record ↗
✨

AI Summary & Key Takeaways

AI Insight
⚡ TL;DR(Too Long; Didn't Read)

In addition, it has concluded that it is possible to take precautions using road and weather data of the accidents which occurred in previous years.

📌 3 Key Takeaways

🎯
Objective & Hypothesis:In this study, a dataset is created using numeric data of injury traffic accidents in monthly base between 2005 and 2014 years in Adana province and meteorological data of the same years in order to develop prediction models which estimate number of traffic accidents involving injury and number of injured people.
📊
Key Findings & Data:Feedforward Multilayer Artificial Neural Network, Function Fitting Artificial Neural Network, Generalized Regression Artificial Neural Network, Regression Tree, Support Vector Machine and Multiple Linear Regression Analysis methods were used in the prediction models.
💡
Conclusion & Impact:In addition, it has concluded that it is possible to take precautions using road and weather data of the accidents which occurred in previous years.
🔬Design:Modeling & Simulation
📍Scope:2005 Verileri
⚙️Variables:Trafik kazası · Tahmin modeli · Makine öğrenmesi

Abstract

In this study, a dataset is created using numeric data of injury traffic accidents in monthly base between 2005 and 2014 years in Adana province and meteorological data of the same years in order to develop prediction models which estimate number of traffic accidents involving injury and number of injured people. Feedforward Multilayer Artificial Neural Network, Function Fitting Artificial Neural Network, Generalized Regression Artificial Neural Network, Regression Tree, Support Vector Machine and Multiple Linear Regression Analysis methods were used in the prediction models. As a result of the study, SVM gives the most successful results for both prediction scenarios. Prediction of the number of traffic accidents involving injury is more successful than prediction of number of injured people except Regression Tree method. In addition, it has concluded that it is possible to take precautions using road and weather data of the accidents which occurred in previous years.

Özet

Bu çalışmada, Adana ilinde 2005 ile 2014 yılları arasında meydana gelen yaralanmalı trafik kazalarına ait aylık bazdaki sayısal veriler ile aynı yıllara ait aylık bazdaki meteorolojik verilerden oluşturulan bir veri kümesi kullanılarak yaralanmalı kaza sayısı ve yaralı sayısı tahmini yapacak modeller geliştirilmiştir. Tahmin modellerinde, İleri Beslemeli Çok Katmanlı Yapay Sinir Ağı (İBÇK-YSA), Fonksiyon Uydurma Yapay Sinir Ağı (FU-YSA), Genelleştirilmiş Regresyon Yapay Sinir Ağı (GR-YSA), Regresyon Ağacı (RA), Destek Vektör Makinesi (DVM) ve Çoklu Doğrusal Regresyon (ÇDR) Analizi yöntemleri kullanılmıştır. Çalışma sonucunda, DVM yönteminin her iki tahmin senaryosunda da en başarılı sonuçları verdiği görülmüştür. Yaralanmalı Kaza Sayısı tahminlerinin RA yöntemi dışında Yaralı Sayısı tahminlerinden daha başarılı olduğu saptanmıştır. Ayrıca, önceki yıllarda gerçekleşen kazalara ait yol ve hava verilerini kullanarak gelecek yıllar için uygun önlemler almanın mümkün olduğu sonucuna varılmıştır.

🔖

Cite This Article

ÖZDEN, C., ACI, Ç. (2018). Analysis of injury traffic accidents with machine learning methods: Adana case. Pamukkale Üniversitesi Mühendislik Bilimleri Dergisi, Cilt: 24 - Sayı: 2, 266–275. https://ajindex.com/articles/42388

📄 Full Text PDF Viewer

📄

PDF görüntüleyici hazırlanıyor...

References (17)

  1. Baş Fİ. Geçici Fiziksel Özelliklerden Yorgunluk ve Uykusuzluğun Sürücü Davranışı Üzerine Etkisi. Yüksek Lisans Tezi, Atatürk Üniversitesi,
  2. Erzurum, Türkiye, 2015.
  3. Sohn SY, Shin H. “Pattern recognition for road traffic accident severity in Korea”. Ergonomics, 44(1), 107-117, 2010.
  4. Özgan E, Ulusu H, Yıldız K. “Trafik kaza verilerinin analizi ve kaza tahmin modeli”. SAU Fen Bilimleri Enstitüsü Dergisi, 8(1), 160-166, 2004.
  5. Chong M, Abraham A, Paprzycki M. “Traffic accident analysis using machine learning paradigms”. Informatica, 29, 89-98, 2005.
  6. Chang L, Wang H. “Analysis of traffic i njury severity: an application of non-parametric classification tree techniques”, Accident Analysis and Prevention, 38(5), 1019-1027, 2006.
  7. Murat YŞ, Şekerler A. “Trafik kaza verilerinin kümelenme analizi yöntemi ile modellenmesi”. İMO Teknik Dergi, Yazı 311, 4759-4777, 2009.
  8. Qiuping W, Subing L. “An information renewal GNN model for road traffic accident forecasting”, International Conference on Transportation Engineering, Chengdu, China, 25-27 July 2009.
  9. Durduran SS. “A decision making system to automatic recognize of traffic accidents on the basis of GIS platform”, Expert Systems with Applications, 37(12), 7729–7736, 2010.
  10. Akgüngör AP, Doğan E. “Farklı yöntemler kullanılarak geliştirilen trafik kaza tahmin modelleri ve analizi”, International Journal of Engineering, Research and Development, 2(1), 16-22, 2010.
  11. Wang H, Zheng L, Meng X. “Traffic accidents prediction model based on fuzzy logic”, Advances in Information Technology and Education, 201, 101-108, 2011.
  12. Yu R, Abdel-Aty M. “Utilizing support vector machine in real-time crash risk evaluation”, Accident Analysis and Prevention, 51, 252-259, 2013.
  13. Li Z, Liu P, Wang W, Xu C. “Using support vector machine models for crash ınjury severity analysis”, Accident Analysis and Prevention, 45, 478-486, 2012.
  14. Çelik AK, Oktay E. “A multinomial logit analysis of risk factors in fluencing road traafic injury severities in the Erzurum and Kars Provinces of Turkey”, Accident Analysis and Prevention, 72, 66-77, 2014.
  15. Kwon OH, Rhee W, Yoon Y, “Application of classification algorithms for analysis of road safety risk factor dependencies”, Journal of Accident Analysis and Prevention, 75, 1-15, 2015.
  16. Yapraklı TŞ, Erdal H. “Firma başarısızlığı tahminlemesi: makine öğrenmesine dayalı bir uygulama”, Bilişim Teknolojileri Dergisi, 9(1), 21-31, 2016.
  17. Garret GJ, Wu C, “Knowledge‐based modeling of material behavior with neural networks”. Journal of