Tekstil Sektöründe İş Kazalarına Neden Olan Risk Faktörlerinin Veri Madenciliği Yöntemleriyle Değerlendirilmesi

Öz

Bu çalışma, veri madenciliği yöntemlerinin tekstil sektöründe iş kazalarının önlenmesinde yardımcı olabileceğini önermektedir. Çalışma kapsamında, 2019-2021 yılları arasında tekstil sektöründe meydana gelen 89.963 iş kazası verisi incelenmiş ve veri ön işleme çalışması ile örneklem sayısı 11.710’ a düşürülmüştür. Kaza sonucu oluşan yaralanma türlerinin tahmin edilmesinde model seçme haritası referans alınarak SVM, Ekstra Ağaçlar, Rastgele Orman, Gradient Boosting ve XGBoost algoritmaları seçilmiştir. Modeller makro F-skor performans metriği kullanılarak karşılaştırılmıştır. Veri dengeleme ve parametre optimizasyonu yöntemleri ile modellerin tahmin performansı artış göstermiştir. XGBoost algoritması %70 tahmin başarısı ile diğer algoritmalara göre daha iyi performans göstermiştir. SVM algoritması (%69) ve Ekstra Ağaçlar (%68) algoritması, yüksek makro F-skor değerlerine ulaşarak veri setini doğru yorumlayan modeller arasında yer almıştır. Tahmin sonucuna en çok etki eden özelliklerin sırasıyla kaza sebebi, kaza anında kullanılan araç/metaryel, alt sektör bilgisi ve firma büyüklüğü olduğu görülmüştür.

Anahtar Kelimeler

• Tekstil Sektörü
• İş Kazaları
• İş Güvenliği
• Veri Madenciliği
• Veri Dengeleme ve Hiperparametre Optimizasyonu.

Evaluation of Risk Factors Causing Occupational Accidents in the Textile Sector Using Data Mining Methods

Öz

This study suggests that data mining methods can be helpful in preventing occupational accidents in the textile industry. Within the scope of the study, 89.963 occupational accident data that occurred in the textile sector between the years 2019-2021 were examined and the number of samples was reduced to 11.710 with the data preprocessing study. In estimating accidental injury types, model selection map was taken as reference and SVM, Extra Trees, Random Forest, Gradient Boosting and XGBoost algorithms were chosen. Models were compared using the macro F-score performance metric. The estimation performance of models has increased with data balancing and parameter optimization methods. XGBoost algorithm performed better than other algorithms with 70% prediction success. The SVM (69%) and Extra Trees (68%) have been among the algorithms that correctly interpreted the data set by reaching high macro F-score values. It has been seen that the features that have the most effect on the estimation result are cause of accident, material agent, sub-sector, and company size, respectively.

Anahtar Kelimeler

• Textile Sector
• Occupational Accidents
• Work Safety
• Data Mining
• Data Balancing and Hyperparameter Optimization.

Kaynakça

1. Santos A.J.R. (2021, February 11). Learning from work-related accidents [Conference presentation]. Towards safe, healthy and declared work in Ukraine – ILO, Ukraine. https://www.ilo.org/wcmsp5/groups/public/---europe/---ro-geneva/---sro-budapest/documents/genericdocument/wcms_769666.pdf
2. Güllüoğlu, E. N. & Taçgın, E. (2018). Türkiye Tekstil Sektöründe İstihdam ve İş Kazalarının Analizi. Tekstil ve Mühendis, 25(112), 344-354. https://doi.org/10.7216/1300759920182511208
3. Çakmak H. (2019). Analysis of current occupational accidents raw data by data mining process (Publication No. 614088) [Master's dissertation, Gazi University]. Ulusal Tez Merkezi.
4. Recal, F. & Demirel, T. (2021). Predicting accident severity with machine learning. Journal of Intelligent & Fuzzy Systems, 40, 10981–10998. doi:10.3233/JIFS-202099
5. Recal F. (2022). Creating a decision support framework from national occupational accidents data with machine learning approach (Publication No. 743913) [Doctoral dissertation, Yıldız Teknik University] Ulusal Tez Merkezi.
6. Cheng C. W., Yao H. Q. & Wu T. C. (2013). Applying data mining techniques to analyze the causes of major occupational accidents in the petrochemical industry. Journal of Loss Prevention in the Process Industries, 26(6), 1269-1278. doi: https://doi.org/10.1016/j.jlp.2013.07.002
7. Gül M., Guneri A.F., Yilmaz F. & Celebi O. (2016). Analysis of the relation between the characteristics of workers and occupational accidents using data mining. The Turkish Journal of Occupational / Environmental Medicine and Safety, 1(4), 102-118.
8. Çakır E. (2019). Workplace hazards and occupational risks: A research on occupational accidents aboard merchant ships (Publication No. 564634) [Doctoral dissertation, Dokuz Eylül University]

9. Ayanoğlu C. & Kurt M. (2019). Proposal of an occupational accident forecasting model with data mining methods in metal sector. Ergonomi, 2(2), 78–87. doi: https://doi.org/10.33439/ERGONOMI.481861
10. Choi J., Gu B., Chin S. & Lee J.S. (2020). Machine learning predictive model based on national data for fatal accidents of construction workers. Automation in Construction, 110, 102974. doi: https://doi.org/10.1016/j.autcon.2019.102974
11. Koc K., Ekmekcioğlu Ö. & Gurgun A.P. (2021). Integrating feature engineering, genetic algorithm and tree-based machine learning methods to predict the post-accident disability status of construction workers. Automation in Construction, 131, 103896. doi: https://doi.org/10.1016/j.autcon.2021.103896
12. Kakhki FD., Freeman SA. & Mosher G.A. (2019). Evaluating machine learning performance in predicting injury severity in agribusiness industries. Safety Science, 117, 257-262. doi: https://doi.org/10.1016/j.ssci.2019.04.026
13. Mathews D.G. (2016). Data Mining and Machine Learning Algorithms for Workers' Compensation Early Severity Prediction. [Master’s dissertation, Middle Tennessee State University]
14. Khairuddin M.Z.F., Hui P.L., Hasikin K., Razak N.A.A., Lai K.W., Saudi A.S.M. & Ibrahim S.S. (2022). Occupational Injury Risk Mitigation: Machine Learning Approach and Feature Optimization for Smart Workplace Surveillance. International Journal of Environmental Research and Public Health, 19(21), 13962. doi: https://doi.org/10.3390/ijerph192113962
15. Yang L. & Shami A. (2020). On hyperparameter optimization of machine learning algorithms: Theory and practice. Neurocomputing, 415, 295-316. doi: https://doi.org/10.1016/j.neucom.2020.07.061
16. Sarkar S., Vinay S., Raj R., Maiti J. & Mitra P. (2019). Application of optimized machine learning techniques for prediction of occupational accidents. Computers & Operations Research, 106, 210-224. doi: https://doi.org/10.1016/j.cor.2018.02.021
17. Wu J., Chen X.Y., Zhang H., Xiong L.D., Lei H. & Deng S.H. (2019). Hyperparameter Optimization for Machine Learning Models Based on Bayesian Optimization. Journal of Electronic Science and Technology, 17(1), 26-40. https://doi.org/10.11989/JEST.1674-862X.80904120
18. Shekar B.H. & Dagnew G. (2019). Grid Search-Based Hyperparameter Tuning and Classification of Microarray Cancer Data [Conference presentation]. Second International Conference on Advanced Computational and Communication Paradigms (1-8), Gangtok, Hindistan. doi:10.1109/ICACCP.2019.8882943
19. Sarkar S., Khatedi N., Pramanik A. & Maiti J. (2019). An Ensemble Learning-Based Undersampling Technique for Handling Class-Imbalance Problem. Lecture Notes in Electrical Engineering, Springer.
20. Bulut F. (2016). Performance Analysis of Ensemble Methods on Imbalanced Datasets. Bilişim Teknolojileri Dergisi, 9(2), 153-159. doi: 10.17671/btd.81137
21. Koc K. & Gurgun A.P. (2022). Scenario-based automated data preprocessing to predict severity of construction accidents. Automation in Construction, 140, 104351. doi: https://doi.org/10.1016/J.AUTCON.2022.104351
22. Fernández A., García S., Herrera F. & Chawla N.V. (2018). SMOTE for Learning from Imbalanced Data: Progress and Challenges, Marking the 15-year Anniversary. Journal of Artificial Intelligence Research, 61, 863-905. doi: https://doi.org/10.1613/jair.1.11192
23. Li Z., Liu P., Wang W. & Xu C. (2012). Using support vector machine models for crash injury severity analysis. Accident Analysis & Prevention, 45, 478-486. doi: https://doi.org/10.1016/j.aap.2011.08.016
24. Sánchez A.S., Fernández P.R., Lasheras F.S., Juez F.J. & Nieto P.G. (2011). Prediction of work-related accidents according to working conditions using support vector machines. Applied Mathematics and Computation, 218(7), 3539-3552. doi: https://doi.org/10.1016/j.amc.2011.08.100
25. Yang Y., Li J., & Yang Y. (2015). The research of the fast SVM classifier method. In 2015 12th international computer conference on wavelet active media technology and information processing (ICCWAMTIP), Chengdu, China, 121-124.
26. Baby D., Devaraj S. J., & Hemanth J. (2021). Leukocyte classification based on feature selection using extra trees classifier: Atransfer learning approach. Turkish Journal of Electrical Engineering and Computer Sciences, 29(8), 2742-2757. doi: 10.3906/elk-2104-183
27. Abhishek L. (2020). Optical character recognition using ensemble of SVM, MLP and extra trees classifier. In 2020 International Conference for Emerging Technology (INCET), Belgaum, India, 1-4.
28. Bahad P. & Saxena P. (2020). Study of adaboost and gradient boosting algorithms for predictive analytics. In International Conference on Intelligent Computing and Smart Communication 2019: Proceedings of ICSC 2019, Singapore, 235-244.
29. Parsa A. B., Movahedi A., Taghipour H., Derrible S. & Mohammadian A. K. (2020). Toward safer highways, application of XGBoost and SHAP for real-time accident detection and feature analysis. Accident Analysis & Prevention, 136, 105405. doi: https://doi.org/10.1016/j.aap.2019.105405
30. Friedman J.H. (2001). Greedy function approximation: a gradient boosting machine. The Annals of Statistics, 29(5), 1189-1232. doi: 10.1214/aos/1013203451
31. Dhaliwal S.S., Nahid A.A. & Abbas R. (2018). Effective intrusion detection system using XGBoost. Information, 9(7), 149. doi: https://doi.org/10.3390/info9070149
32. Samur O. (2020). Boosting Algorithms. Retrieved from https://www.datasciencearth.com/boosting-algoritmalari/
33. Çelik H.İ., Dülger L.C., Öztaş B., Kertmen M. & Gültekin E. (2022). A Novel Industrial Application of CNN Approach: Real Time Fabric Inspection and Defect Classification on Circular Knitting Machine. Textile and Apparel, 32(4), 344-352. doi: https://doi.org/10.32710/tekstilvekonfeksiyon.1017016
34. G.M. Weiss. (2004). Mining with rarity: a unifying framework. ACM SIGKDD Explorations Newsletter, 6 (1), 7-19. doi: https://doi.org/10.1145/1007730.1007734
35. Fernández A., López V., Galar M., Del Jesus M. J. & Herrera F. (2013). Analyzing the classification of imbalanced data-sets with multiple classes: Binarization techniques and ad-hoc approaches. Knowledge-based systems, 42, 97-110. doi: https://doi.org/10.1016/j.knosys.2013.01.018
36. Pir M. Ş. (2022). Dengesiz Veri Setlerinde Sınıflandırma Problemlerinin Çözümünde Melez Yöntem Uygulaması. (Publication No. 720846) [Doctoral dissertation, Bursa Uludağ University]
37. Ranjan G. S. K., Kumar Verma A. and Radhika S. (2019). K-Nearest Neighbors and Grid Search CV Based Real Time Fault Monitoring System for Industries. In 2019 IEEE 5th International Conference for Convergence in Technology (I2CT). Pune, India.