[논문]건설현장의 공사사전정보를 활용한 사망재해 예측 모델 개발

최승주; 김진현; 정기효

doi:10.14346/jkosos.2021.36.3.31

건설현장의 공사사전정보를 활용한 사망재해 예측 모델 개발
Development of Prediction Models for Fatal Accidents using Proactive Information in Construction Sites 원문보기

한국안전학회지 = Journal of the Korean Society of Safety, v.36 no.3, 2021년, pp.31 - 39

최승주 (울산대학교 안전보건전문학과) , 김진현 (한국산업안전보건공단 산업안전보건연구원) , 정기효 (울산대학교 산업경영공학부)

Abstract ▼ AI-Helper

In Korea, more than half of work-related fatalities have occurred on construction sites. To reduce such occupational accidents, safety inspection by government agencies is essential in construction sites that present a high risk of serious accidents. To address this issue, this study developed risk prediction models of serious accidents in construction sites using five machine learning methods: support vector machine, random forest, XGBoost, LightGBM, and AutoML. To this end, 15 proactive information (e.g., number of stories and period of construction) that are usually available prior to construction were considered and two over-sampling techniques (SMOTE and ADASYN) were used to address the problem of class-imbalanced data. The results showed that all machine learning methods achieved 0.876~0.941 in the F1-score with the adoption of over-sampling techniques. LightGBM with ADASYN yielded the best prediction performance in both the F1-score (0.941) and the area under the ROC curve (0.941). The prediction models revealed four major features: number of stories, period of construction, excavation depth, and height. The prediction models developed in this study can be useful both for government agencies in prioritizing construction sites for safety inspection and for construction companies in establishing pre-construction preventive measures.

주제어

표/그림 (7)

그림 Fig. 1. Research process to develop prediction models for fatal accidents in construction sites.
표 Table 1. Definition of features and factors considered in this study
그림 Fig. 2. Data distribution by fatality.
표 Table 2. Example of confusion matrix
그림 Fig. 3. ROC curve for machine learning algorithms with ADASYN (the ROC curve for AutoML is not visualized since the visualization function is not implemented in the AutoML library yet).
표 Table 3. F1-score for machine learning algorithms with/ without over-sampling
표 Table 4. Feature importances of two major algorithms with ADASYN

참고문헌 (43)

S. D. Choi and K. Carlson, "Occupational Safety Issues in Residential Construction Surveyed in Wisconsin, United States", Industrial Health, Vol. 52, No. 6, pp. 541-547, 2014.

상세보기
C. W. Liao and Y. H, Perng, "Data mining for Occupational Injuries in the Taiwan Construction Industry", Safety Science, Vol. 46, No. 7, pp. 1091-1102, 2008.

상세보기
Y. H. Chiang, F. K. W. Wong and S. Liang, "Fatal Construction Accidents in Hong Kong", J. Constr. Eng. Manag., Vol. 144, No. 3, 04017121, 2018.

상세보기
Y. G. Choi and K. T. Cho, "A Cause Analysis of the Construction Incident Using Causal Loop Diagram : Safety Culture Perspective", J. Korean. Soc. Saf. Vol 35, No. 2, pp. 34-46, 2020.

원문보기 상세보기
Ministry of Employment and Labor (MOEL), "2019 Industrial Accident Statistics"
W. J. Lim, J. H. Kee, J. H. Seong and J. Y. Park, "Development of Accident Cause Analysis Model for Construction Site", J. Korean Soc. Saf., Vol. 34, No. 1, pp. 45-52, 2019.

원문보기 상세보기
W. Zhang, S. Zhu, X. Zhang and T. Zhao, "Identification of Critical Cause of Construction Accidents in China using Model based on System Thinking and Cause Analysis", Saf. Sci., Vol. 121, pp. 606-618, 2019.
J. J. Jeong and J. J. Jeong, "Development of Framework for Integrated Work-Risk Breakdown Structure based on Fatal incident Cases in Construction Industry", Korean Journal of Construction Engineering and Management, Vol. 21, No. 3 pp. 11-19, 2020.

원문보기 상세보기
S. S. Yang and S. W. Paik, "Risk Management for Preventing Workers' Deaths in Construction Machinery Work", J. Korean Soc. Saf., Vol. 35, No. 3, pp. 16-23, 2020.

원문보기 상세보기
H. P. Park and J. G. Han, "Development of Risk Assesment Index for Construction Safety Using Statistical Data", J. Korea Inst. Build. Constr. Vol. 19, No. 4, pp. 361-371, 2019.

원문보기 상세보기
Y. R. Jang and S. S. Go, "A Risk Assessment Counterplan for Reducing the Accident Rates in Medium and Small sized Construction Sites", Korean Journal of Construction Engineering and Management, Vol. 19, No. 5, pp. 90-100, 2018.

원문보기 상세보기
D. S. Kim and Y. S. Shin, "A Study on the Risk Factors according to the Frequency of Falling Accidents in Construction Sites", J. Korea Inst. Build. Constr., Vol. 19, No. 2, pp. 185-192, 2019.

원문보기 상세보기
D. Y. Kim, S. M. Yun, J. M. Kim, S. Y. Lee and K. Y. Son, "Improvement of Fall Prevention Method in Construction Site through Comparison with Advanced Countries' Cases", J. Korea Inst. Build. Constr., Vol. 20, No. 5, pp. 471-480, 2020.

원문보기 상세보기
G. H. Lee, C. S. Lee, C. W. Koo and T. W. Kim, "Identification of Combinatorial Factors Affecting Fatal Accidents in Small Construction Sites: Association Rule Analysis", Korean Journal of Construction Engineering and Management, Vol. 21, No. 4, pp. 90-99, 2020.

원문보기 상세보기
S. G. Ha, T. H. Kim, K. Y. Son and J. M. Kim, "Quantification Model Development of Human Accidents based on the Insurance Claim Payout on Construction Site", J. Korea Inst. Build. Constr., Vol. 18, No. 2, pp. 151-159, 2018.

원문보기 상세보기
H. S. Kim, S. C. Jang and J. G. Joo, "Preventive Priority Methods Based on the Analysis of Fire Accident Causes in Construction Site", J. Korea Institute of Construction Safety, Vol. 2, No. 2, pp. 50-55, 2019.

원문보기 상세보기
C. F. Chi, C. C. Yang and Z. L. Chen, "In-depth Accident Analysis of Electrical Fatalities in the Construction Industry", Int. J. Ind. Ergo., Vol. 39, No. 4, pp. 635-644, 2009.

상세보기
J. H. Andersen, P. Malmros, N. E. Ebbehoej and E. M. Flachs, E. Bengtsen and J. P. Bonde, "Systematic Literature Review on the Effects of Occupational Safety and Health (OSH) interventions at the workplace", Scand J. Work Environ. Health, Vol 45, No. 2, pp. 103-113, 2019.

상세보기
D. I. Levine, M. W. Toffel and M. S. Johnson, "Randomized Government Safety Inspections Reduce Worker Injuries with No Detectable Job Loss", Science, Vol. 336, No. 6083, pp. 907-911, 2012.

상세보기
S. Sarkar et al., "Predicting and Analyzing Injury Severity: A Machine Learning-based Approach using Classimbalanced Proactive and Reactive Data", Saf. Sci., Vol. 125, 2020.

상세보기
H. Li et al., "Proactive Behavior-based Safety Management for Construction Safety Improvement", Saf. Sci., Vol. 75, pp. 107-117, 2015.

상세보기
R. Zhu et al., "Application of Machine Learning Techniques for Predicting the Consequences of Construction Accidents in China", Process Saf. Environ. Prot. Vol. 145, pp. 293-302, 2021.

상세보기
M. Shanker, M. Y. Hu and M. S. Hung, "Effect of Data Standardization on Neural Network Training", Omega, Vol. 24, No. 4, pp. 385-397, 1996.

상세보기
H. Bhavsar and A. Ganatra, "A Comparative Study of Training Algorithms for Supervised Machine Learning", International Journal of Soft Computing and Engineering, Vol. 2, No. 4, pp. 2231-2307, 2012.
V. N. Vapnik, "The Nature of Statistical Learning Theory", Springer-Verlag, 1999.
L. Breiman, "Random Forests", Machine Learning, Vol. 45, pp. 5-32, 2001.
T. Chen and C. Guestrin, "XGBoost: A Scalable Tree Boosting System", KDD '16: Proc. of the 22nd ACM SIGKDD International Conference on Knowledge Discovery and Data Mining, pp. 785-794, 2016.
G. Ke, Q. Meng, T. Finley and T. Wang, W. Chen, "LightGBM: A Highly Efficient Gradient Boosting Decision Tree", Advances in Neural Information Processing Systems (NIPS 2017), Vol. 30, pp. 3146-3154, 2017.
Y. H. Moon, I. H. Shin, Y. J. Lee and O. G. Min, "Recent Research & Development Trends in Automated Machine Learning", Electronics and Telecommunications Trends, Vol. 34, No. 4, pp. 32-42, 2019.
M. Feurer, A. Klein, K. Eggensperger, J. Springenberg, M. Blum and F. Hutter, "Efficient and Robust Automated Machine Learning", Advances in Neural Information Processing Systems (NIPS 2015), Vol. 28, pp. 2962-2970, 2015.
M. Claesen and B. D. Moor, "Hyperparameter Search in Machine Learning", arXiv preprint arXiv:1502.02127, 2015.
T. Akiba, S. Sano, T. Yanase T. Ohta and M. Koyama, "Optuna: A Next-generation Hyperparameter Optimization Framework", KDD '19: Proc. of the 25th ACM SIGKDD International Conference on Knowledge Discoverty and Data Mining, pp. 2623-2631, 2019.
H. He and E. A. Garcia, "Learning from imbalanced data", IEEE Transactions on Knowledge and Data Engineering, Vol 21, No. 9, pp. 1263-1284, 2009.

상세보기
S. Ertekin, J. Huang, L. Bottou and L. Giles, "Learning on the border: Active Learning in Imbalanced Data Classification", CIKM '07: Proc. of 16th ACM conference on Conference on Information and Knowledge Management, pp. 127-136, 2007.
M. J. Son, S. W. Jung and E. J. Hwang, "A Deep Learning Based Over-Sampling Scheme for Imbalanced Data Classification", KIPS Trans. Softw. and Data Eng., Vol. 8, No. 7, pp. 311-316, 2019.

원문보기 상세보기
N. V. Chawla, L. O. Hall, K. W. Bowyer, L. O. Hall and W. P. Kegelmeyer, "SMOTE: Synthetic Minority Over-sampling Technique", Journal of Artificial Intelligence Research, Vol. 16, pp. 321-357, 2002.

상세보기
H. He, Y. Bai, E. A. Garcia and S. Li, "ADASYN: Adaptive Synthetic Sampling Approach for Imbalanced Learning", 2008 IEEE International Joint Conference on Neural Networks, pp. 1322-1328, 2008.
S. Arlot and A. Celisse, "A survey of Cross-validation Procedures for Model Selection", Statistics Surveys, Vol. 4, pp. 40-79, 2010.
Y. Fang, Y. Zhang and C. Huang, "Credit Card Fraud Detection Based on Machine Learning", Computers, Materials & Continua, Vol. 61, No. 1, pp. 185-195, 2019.
G. Haixiang, L. Yijing, J. Shang and G. Mingyun, H. Yuanyue and G. Bing, "Learning from Class-imbalanced Data: Review of Methods and Applications," Expert Systems with Applications, Vol. 73, pp. 220-239, 2017.

상세보기
J. H. Choi and H. G. Ryu, "Analysis of Occupational Injury and Feature Importance of Fall Accidents on the Construction Sites using Adaboost", J. Architectural Institute of Korea Structure & Construction, Vol. 35, No. 11, pp. 155-162, 2019.
S. Piramuthu, "Input Data for Decision Trees", Expert Systems with Applications, Vol. 34, pp. 1220-1226, 2008.

상세보기
S. I. Choi and H. Kim, "A Study on the Safety Climate and Worker's Safe Work Behavior in Construction Site", J. Korean Soc. Saf., Vol. 21, No. 5, pp. 60-71, 2006.

표제어: PCR

동의어: Packet Collision Rate

용어 설명 출처 목록 (6)

용어 설명: PCR은 세균 특이성이 있는 primer를 이용하여 적은 수의 세균이 있을지라도 쉽게 검출할 수 있는 유용한 방법이며, 이를 이용하여 구강 내 치면세균막이나 타액에서 직접 세균을 검출할 수 있게 되었다[8].

내보내기 구분	파일저장 인쇄 메일전송
구성항목	기본정보 상세정보 관리번호, 논문명, 저널/프로시딩명, 저자 , 발행년, 권, 호, 시작페이지, 끝페이지, 발행기관 관리번호, 논문명, 대등논문명, 저자 , 저널/프로시딩명, 발행기관, 발행년, 발행언어, 권, 호, 시작페이지, 끝페이지, ISBN, ISSN, 주제분야, 키워드, 초록(한글), 초록(영문), 저자(소속기관)
저장형식	Text(ASCII format) Excel format RefWorks Direct Export RIS format (for Reference Manager, ProCite, EndNote), Scholar's Aids, Mendeley
메일정보	받는사람 (필수) @ 보내는사람 (선택) @ 제목 내용 KISTI 검색결과 이메일 서비스
안내	총 건의 자료가 검색되었습니다. 다운받으실 자료의 인덱스를 입력하세요. (1-10,000) 검색결과의 순서대로 최대 10,000건 까지 다운로드가 가능합니다. 데이타가 많을 경우 속도가 느려질 수 있습니다.(최대 2~3분 소요) 다운로드 파일은 UTF-8 형태로 저장됩니다. 파일의 내용이 제대로 보이지 않을실 때는 웹브라우저 상단의 보기 -> 인코딩 -> 자동선택 여부를 확인하십시오. ~ Text(ASCII format) Excel format

연합인증