Application of the Classification Tree Model in Predicting Workers’ Injured Body Part in Reinforced Concrete Construction

Ji Seon Lim; Sanghyeok Kang

doi:10.55785/JCAR.1.3.7

All Issue

2022 Vol.1, Issue 3 Preview Page Next Page

Application of the Classification Tree Model in Predicting Workers’ Injured Body Part in Reinforced Concrete Construction 철근콘크리트 공사 작업자의 부상 부위 예측을 위한 분류나무 모델의 적용

30 September 2022. pp. 7-13

PDF XML

Abstract

Compared to other industries, the construction industry has a high work risk, and the number of accidents is high. Much research and effort have been made to prevent these occupational accidents in the construction industry. However, few studies on the injured body part of workers have been conducted. This study proposed a model for predicting the injured part of workers in the construction industry using construction accident cases. The Chi-squared Automatic Interaction Detection (CHAID) algorithm of the classification tree model was employed in this study. This model is easy to interpret the result and shows excellent performance among machine learning algorithms. A total of 10 models with prediction variables of accident type, detailed work, type of facility, original cause materials, cause of the accident, and season were built using the 60:40 training and validation dataset with the SPSS statistics package. The outcome variable is workers' injured body parts: 1) head, 2) torso, 3) upper extremity, and 4) lower extremity. The classification accuracy of the validation data was found to be an average of 47.8%, which is greater than the posterior probability of 25.0% but not satisfactory. The model constructed in this study and the results were discussed. Construction managers can establish more detailed disaster prevention measures through the results of this study.

Keywords

Safety Management

Construction Accident

Workers’ Injured Body Part

Classification Tree Model

Data Mining

건설업은 다른 산업에 비해 작업 위험도가 높고 사고 발생률이 높다. 건설산업에서는 이러한 산업재해를 예방하기 위한 많은 연구와 노력이 있었다. 그러나 근로자의 부상 신체 부위에 대한 연구는 거의 수행되지 않았다. 본 연구에서는 2,273개의 건설사고 사례를 활용하여 건설업 종사자의 부상 부위를 예측하는 모델을 제안하였다. 이때 결과 해석이 용이하고 머신러닝 알고리즘 중 우수한 성능을 보여주는 분류나무 모델의 Chi-squared Automatic Interaction Detection (CHAID) 알고리즘을 사용하였다. 분석에 사용된 예측변수는 사고 유형, 세부 작업, 시설 유형, 원래 원인 자료, 사고 원인 및 계절이고, 결과변수는 작업자의 부상 신체 부위(1. 머리, 2. 몸통, 3. 상지, 4. 하지)이다. 검증 데이터로 평가한 정확도는 평균 47.8%로 사후 확률 25.0%보다 높은 것으로 나타났다. 본 논문은 구축된 모델과 그 결과에 대한 논의를 담고 있다. 건설관리자는 본 연구결과를 바탕으로 작업자의 안전을 위한 세부적인 방재대책을 수립할 수 있을 것이다.

키워드

안전관리

건설재해

작업자의 부상 부위

분류나무 모델

데이터 마이닝

References

건설공사 안전관리 종합정보망(Construction Safety Management Integrated Information, CSI), <http://www.csi.go.kr/ >

Amiri, M., Ardeshir, A., Fazel Zarandi, M.H., and Soltanaghaei, E. (2016). Pattern extraction for high-risk accidents in the construction industry: a data-mining approach. International Journal of Injury Control and Safety Promotion, 23(3), pp. 264-276, 10.1080/17457300.2015.103297925997167

Ayhan, B.U., and Tokdemir, O.B. (2020). Accident Analysis for Construction Safety Using Latent Class Clustering and Artificial Neural Networks. Journal of Construction Engineering and Management, 146(3). 10.1061/(ASCE)CO.1943-7862.0001762

Cho, Y., Kim, Y., and Shin, Y. (2017). Prediction Model of Construction Safety Accidents using Decision Tree Technique. Journal of the Korea Institute of Building Construction, 17(3), pp. 295-303. 10.5345/JKIBC.2017.17.3.295

Choi, J., Gu, B., Chin, S., and Lee, J. (2020). Machine learning predictive model based on national data for fatal accidents of construction workers. Automation in Construction, 110. 10.1016/j.autcon.2019.102974

Choi, S. (2015). Aging Workers and Trade-Related Injuries in the US Construction Industry. Safety and Health at Work, 6(2), pp. 151-155. 10.1016/j.shaw.2015.02.00226106517PMC4476198

Halvani, G.H., Jafarinodoushan, R., Mirmohammadi, S.J., and Mehrparvar, A.H. (2012). A survey on occupational accidents among construction industry workers in Yazd city: Applying Time Series 2006-2011. Journal of Occupational Health and Epidemiology, 1(1), pp. 1-8. 10.18869/acadpub.johe.1.1.1

Kang, K., Choi, J., and Ryu, H. (2021). Analysis of the Feature Importance of Occupational Accidents Occurring at Construction Sites on the Severity of Lost Workdays. Journal of Korea Institute of Building Construction, 21(2), pp. 165-174.

Kass, G. (1980). An exploratory technique for investigating large quantities of categorical data, Applies Statistics. 10.2307/2986296

Kim, K., Kim, K., Lee, Y., and Kim, J. (2008). A Study about Influence of Risk Factors in Relation to Construction Cost Increase and Schedule Delay on the Reinforced Concrete Construction. Architectural Institute of Korea, 24(5), pp. 165-172.

Lee, J., Yoon, Y., Oh, T., Park, S., and Ryu, S. (2020). A study on data pre-processing and accident prediction modelling for occupational accident analysis in the construction industry. Applied Sciences, 10(21), pp. 1-23. 10.3390/app10217949PMC7029300

Lee, Y., Kang, S., and Yu, H. (2019). A Study on Risk Factor Identification by Specialty Construction Industry Sector through Construction Accident Cases : Focused on the Insurance Data of Specialty Construction Worker. Journal of the Korea Industrial Information Systems Research, 24(1), pp. 45-63,

Leem, Y., and Hwang, Y. (2005). A Feature Analysis of Industrial Accidents Using CHAID Algorithm. Journal of Korea Safety Management & Science, pp. 59-67.

Ministry of Employment and Labor (2022). 2021 industrial accident status analysis.

Mistikoglu, G., Gerek, I.H., Erdis, E., Mumtaz Usmen, P.E., Cakan, H., and Kazan, E.E. (2015). Decision tree analysis of construction fall accidents involving roofers. 42(4), pp. 2256-2263. 10.1016/j.eswa.2014.10.009

Shim, U., Suh, H., and Ahn, Y. (2010). Highly Efficient Checklist for the Safety Management of Reinforced Concrete construction. Journal of the Korea Institute of Building Construction, 10(6), pp. 7-17. 10.5345/JKIC.2010.12.6.007

Song, Y., Cho, Y., Seo, Y., and Ahn, S. (2009). Development and its Application of Computer Program for Slope Hazards Prediction using Decision Tree Model. Korean Society of Civil Engineers, 29(2C), pp. 59-69.

Information

Publisher :Korean Society of Automation and Robotics in Construction
Publisher(Ko) :(사)한국건설자동화·로보틱스학회
Journal Title :Journal of Construction Automation and Robotics
Journal Title(Ko) :건설자동화·로보틱스 논문집
Volume : 1
No :3
Pages :7-13
Received Date : 2022-09-20
Revised Date : 2022-09-26
Accepted Date : 2022-09-26
DOI :https://doi.org/10.55785/JCAR.1.3.7

Journal of Construction Automation and Robotics ISSN:2800-0552(Print) 2951-116X(Online) 건설자동화·로보틱스 논문집

All Issue