Türkiye’de İş Kazalarından Kaynaklanan Ölüm ve Sürekli İş Göremezlik Vakalarının Regresyonla Tahmini

Year 2016, Volume: 8 Issue: 2, 46 - 54, 15.06.2016

Hüseyin Ceylan

https://doi.org/10.29137/umagd.346156

Abstract

Bu çalışmada Regresyon Analizi
(RA) kullanılarak Türkiye geneli için iş kazası tahmin modelleri
geliştirilmiştir. Bu modeller kullanılarak Türkiye’nin 2025 yılına kadar olan
süreçte, i ve sürekli iş göremezlik vaka sayıları farklı üç senaryo dahilinde
tahmin edilmiştir. Model geliştirilirken sigortalı işçi, işyeri, iş kazası, i
ve sürekli iş göremezlik sayıları model parametreleri olarak kullanılmış ve bu
parametrelere ait 1970-2012 yılları arasındaki resmi verilerden yararlanılmıştır.
Regresyon Analizinde doğrusal fonksiyon kullanılmıştır. Modellerde kullanılan
bu fonksiyonda; x1 sigortalı işçi sayısını, x2 işyeri sayısını, x3 iş kazası
sayısını, y1 i vaka sayısını, y2 ise iş kazası sonucu sürekli iş göremezlik
vaka sayısını temsil etmektedir. ˆ0 , ˆ 1, ˆ 2 ve ˆ3 doğrusal fonksiyonun
sabitleridir. Çalışmada öncelikle 1970- 2012 arasındaki kaza verileri
kullanılarak doğrusal regresyon fonksiyonu elde edilmiştir. Sonra bu regresyon
fonksiyonuna 1970- 2012 arasındaki kaza verileri tahmin ettirilmiştir. Çıkan
sonuç gerçek değerlerle kıyaslanmış ve regresyon analizi metodunun iş kazası
tahmin modelleri için uygun olduğu görülmüştür. Geliştirilen modellerin
performansları Ortalama Mutlak Yüzde Hata (OMYH) ve Ortalama Mutlak Hata (OMH)
ölçütleri içinde değerlendirilmiştir.

Keywords

İş Kazası, Kaza Tahmin Modelleri, Regresyon Analizi, Türkiye

Prediction of Death and Permanent Incapacity Numbers Resulting From Occupational Accidents in Turkey by Using Regression Analysis

Abstract

In this study, occupational
accident estimation models were developed by using regression analysis (RA)
method for Turkey. Using these models death and permanent incapacity numbers
resulting from occupational accidents was estimated for Turkey until the year
2025 by the three different scenarios. In the development of the models,
insured workers, work place, occupational accident, death and permanent
incapacity values were used as model parameters with offical data between 1970
and 2012. In the Regression Analysis linear function is used. According to this
function; x1 represents number of insured workers; x2 represents number of
workplaces; x3 represents number of  occupational
accidents; y1 represents deaths resulting from occupational accidents; y2
represents permanent incapacities resulting from occupational accidents. ˆ0 ,
ˆ 1, ˆ 2 and ˆ3 are the constant of the liner function. First accident data
between 1970-2012 was used to obtain the linear regression function. Then by
using this regression function estimated accident data for the years 1970 to
2012 were evaluated. When real and estimated data compared, it was seen that
regression analysis method is suitable for estimation of occupational
accidents. The performances of developed models were evaluated by the use of
Mean Absolute Percent Errors (MAPE) and Mean Absolute Errors (MAE)')

Keywords

Occupational Accident, Accident Prediction Models, Regression Analysis, Turkey

References

• Ceylan H., "Analysis of Fatal Occupational Accidents In Turkey For The Year 2013", Journal of Multidisciplinary Engineering Science and Technology, Vol. 3-2015, 2015. http://www.jmest.org/volume-3-2015 SSI., Statistical Yearbook, SSI Publication, Ankara, 1970-2012 [in Turkish]. http://www.sgk.gov.tr/wps/portal/tr/kurumsal/istatistikler - Access Date 16.05.2014. Ceylan H., "An Artificial Neural Networks Approach to Estimate Occupational Accident: A National Perspective for Turkey", Mathematical Problems in Engineering, Vol. 2014, Article ID 756326, 10 pages, 2014. Şensoy E Z., "Nonlinear Logistic Regression and Applications", Marmara University Institute of Science and Technology, Master's Thesis, pp 93, 2009, İstanbul [in Turkish]. Akgungor A P, Dogan E. "Estimating road accidents of Turkey based on regression analysis and artificial neural network approach" Advances in Transportation Studies; 2008(16): pp. 11-22, 2008. Doğan E., "Regression Analysis and Artificial Intelligence Approach for Traffic Accident Prediction Models in Turkey and selected some great Provinces", Kırıkkale University Institute of Science and Technology, Master's Thesis, 2007 [in Turkish]. Goldberg D., "The design of innovation lessons from genetic algorithms, lessons fort the real world" Techno Forecast Social Change vol 64 (1), 2000. Yigit V. "Estimation of Turkey Net Electric Energy Consumption Until to Year 2020 Using Genetic Algorithm", International Journal of Engineering Research and Development, Vol 3(2). pp.37-41, 2011. Murat Y S and Ceylan H., "Use of Artificial Neural Networks for Transport Energy Demand Modeling", Energy Policy Vol 34(17). pp 3165-3172, 2006. Chio Y.C. "An ARIMA Modeling: A Case Study of Turkey", Energy Policy, Vol 35, No 2, pp 1129-1146, 2007. Chiou Y.C. "An artificial network-based expert system for appraisal of two-car crash accidents", Accident Analysis and Prevention Vol.38, No.4, pp.777-785, 2006. Akgüngör, A P, Doğan E, "An artificial intelligent approach to traffic accident estimation; Model development and application" Transport, Vol.24 No,2 pp.135-142, 2009. Akgüngör A. P. ve Doğan E., "Traffic Accident Prediction Models Developed Using Different Methods and Analysis"; Int. J. Eng. Research & Development, Vol.2, No.1 January 2010 [in Turkish]. Önal S, "Forecasting of Flow of Kızılırmak River By Using Neural Networks Method", Süleyman Demirel University Institute of Science and Technology, Master's Thesis, pp 129, 2009, Isparta [in Turkish]. Comaniciu D. and Meer P., "Mean Shift Analysis and Applications", IEEE International Conference on Computer Vision, pp. 1197--1203, 1999. Şen, Z, Artificial Neural Networks, Water Foundation Publications, İstanbul pp 183, 2004, [in Turkish]. Mussone L, Ferrari A, Oneta, M. "An analysis of urban collision using an artificial intelligence model" Accident Analysis and Prevention, Vol.3, No.8, pp.705-718, 1999. Abdelwahab H T, Abdel-Aty M A. "Development of artificial neural network models to predict driver injury severity in traffic accident at signalized intersection" Transportation Research Record 1746, pp.6-13, 2001 Delen D, Sharda R, Besson M. "Identifying significant predictors of injury severity in traffic accidents using a series of artificial neural networks" Accident Analysis and Prevention Vol.38, No.3, pp.434-444, 2006. Doğan E. ve Akgüngör A.P., "Investigation of traffic accidents and results with artificial neural networks: Kırıkkale Case" The 8. Transportation Congress, pp. 279-287, September/October 2009 İstanbul. A. P. Akgüngör and E. Dogan, "Artificial Neural Networks and Genetic Algorithm Approach to Accident Prediction Models Own Istanbul Metropolis",Modern Methods in Science Symposium, pp. 883- 891, 15-17 October 2008, Eskişehir.