한국건설관리학회논문집 (Korean Journal of Construction Engineering and Management)

  • 제24권6호
  • /
  • Pages.3-11
  • /
  • 2023
  • /
  • 2005-6095(pISSN)
  • /
  • 2465-9703(eISSN)
한국건설관리학회 (Korea Institute of Construction Engineering and Management)
권호 표지
DOI QR코드

DOI QR Code

가상현실 기반 건설안전교육에서 개인특성이 학습성과에 미치는 영향 - 머신러닝과 SHAP을 활용하여 -

Impact of personal characteristics on learning performance in virtual reality-based construction safety training - Using machine learning and SHAP -

  • 최다정 (인천대학교 일반대학원 건축학과 ) ;
  • 구충완 (인천대학교 도시건축학부 )
  • Choi, Dajeong (Department of Architectural Engineering, Graduate School, Incheon National University ) ;
  • Koo, Choongwan (Division of Architecture & Urban Design, Incheon National University)
  • 투고 : 2023.06.15
  • 심사 : 2023.09.18
  • 발행 : 2023.11.30
PDF 다운로드
⟨ 이전 논문 다음 논문 ⟩

초록

건설산업의 높은 재해율을 줄이고자, VR 기반 건설안전교육의 도입이 장려되고 있다. 그러나 학습자의 특성을 고려하지 않은 교육방식으로 인해, 학습자의 개인특성에 맞는 효과적인 교육을 수행하지 못하는 한계가 있다. 본 연구에서는, VR 기반 건설안전교육에서 학습성과에 영향을 미치는 개인특성을 분석하는 것으로 목표로 하였고, 이를 위해 머신러닝과 SHAP 기법을 활용하였다. SHAP 분석 결과, 연령이 학습성과에 가장 많은 영향을 미치는 것으로 나타났고, 경력이 가장 작은 영향을 미치는 것으로 나타났다. 또한, 연령은 학습성과와 음(-)의 상관관계를 보이고 있어, VR 기반 건설안전교육의 도입은 낮은 연령에게 더 효과적일 수 있는 것으로 나타났다. 반면, 학력, 자격, 경력은 양(+)의 상관관계를 보였다. 학력이 낮은 학습자에게 더욱 이해하기 쉬운 컨텐츠를 제공함으로써, 학습성과를 향상시킬 필요가 있다. 또한, 자격과 경력이 낮은 학습자의 특성은 학습성과에 영향을 거의 미치지 않으므로, 그 이외의 학습자 특성에 집중함으로써, 학습자 맞춤형 교육 컨텐츠를 제공할 수 있을 것으로 기대된다. 본 연구를 통해, 여러 개인특성이 학습성과에 서로 다른 영향을 미칠 수 있음을 확인했고, 이러한 결과를 활용함으로써, 건설근로자의 개인특성을 고려한 효과적인 안전교육의 기회를 제공할 수 있을 것으로 기대된다.

To address the high accident rate in the construction industry, there is a growing interest in implementing virtual reality (VR)-based construction safety training. However, existing training approaches often failed to consider learners' individual characteristics, resulting in inadequate training for some individuals. This study aimed to investigate the impact of personal characteristics on learning performance in VR-based construction safety training using machine learning and SHAP (SHAPley Additional exPlanations). This study revealed that age exerted the greatest influence on learning performance, while work experience had the least impact. Furthermore, age exhibited a negative relationship with learning performance, indicating that the introduction of VR-based construction safety training can be effective for younger individuals. On the other hand, academic degree, qualifications, and work experience exhibited a positive relationship. To enhance learning performance for individuals with lower academic degree, it is necessary to provide content that is easier to understand. The lower qualifications and work experience have minimal impact on learning performance, so it is important to consider other learners' characteristics so as to provide appropriate educational content. This study confirmed that personal characteristics can significantly affect learning performance in VR-based construction safety training, highlighting the potential for leveraging these findings to provide effective safety training for construction workers.

키워드

과제정보

본 연구는 과학기술정보통신부의 재원으로 한국연구재단의 지원을 받아 수행한 성과입니다(No. NRF-2020R1C1C1004147).

참고문헌

  1. Breiman, L. (2001). "Random forests." Machine learning, 45, pp. 5-32. https://doi.org/10.1023/A:1010933404324
  2. Bzdok, D., Krzywinski, M., and Altman, N. (2017). "Machine learning: a primer." Nature methods, 14(12), pp. 1119-1120. https://doi.org/10.1038/nmeth.4526
  3. Chen, T., and Guestrin, C. (2016). "Xgboost: A scalable tree boosting system." In Proceedings of the 22nd acm sigkdd international conference on knowledge discovery and data mining, pp. 785-794.
  4. Cortes, C., and Vapnik, V. (1995). "Support-vector networks." Machine learning, 20, pp. 273-297. https://doi.org/10.1007/BF00994018
  5. Dobrowolski, P., Skorko, M., Pochwatko, G., Mysliwiec, M., and Grabowski, A. (2021). "Immersive virtual reality and complex skill learning: transfer effects after training in younger and older adults." Frontiers in Virtual Reality, 1, 604008.
  6. Feng, Y., and Wu, P. (2015). "Risk compensation behaviours in construction workers' activities." International journal of injury control and safety promotion, 22(1), pp. 40-47. https://doi.org/10.1080/17457300.2013.844714
  7. Haslam, R.A., Hide, S.A., Gibb, A.G., Gyi, D.E., Pavitt, T., Atkinson, S., and Duff, A.R. (2005). "Contributing factors in construction accidents." Applied ergonomics, 36(4), pp. 401-415. https://doi.org/10.1016/j.apergo.2004.12.002
  8. Heinrich, H.W. (1941). "Industrial Accident Prevention. A Scientific Approach." Industrial Accident Prevention. A Scientific Approach., (2nd Edition).
  9. Hoerl, A.E., and Kennard, R.W. (1970). "Ridge regression: applications to nonorthogonal problems." Technometrics, 12(1), pp. 69-82. https://doi.org/10.1080/00401706.1970.10488635
  10. Korea Occupational Safety and Health Agency. (2022). "Occurrence of Industrial Accidents in 2022." Accessed: Jun. 10, 2023. [Online]. Available: https://www.kosha.or.kr/kosha/data/industrialAccidentStatus.do?mode=view&articleNo=438399&article.offset=0&articleLimit=10
  11. Lee, K.Y. (2020). "Enhancement of Safety and Health Education towards Improved Awareness of Construction workers." M.E. Dissertation, Hanyang University.
  12. Liu, H., Li, J., Li, H., Li, H., Mao, P., and Yuan, J. (2021). "Risk Perception and Coping Behavior of Construction Workers on Occupational Health Risks-A Case Study of Nanjing, China." International journal of environmental research and public health, 18(13), 7040.
  13. Loosemore, M., and Malouf, N. (2019). "Safety training and positive safety attitude formation in the Australian construction industry." Safety science, 113, pp. 233-243. https://doi.org/10.1016/j.ssci.2018.11.029
  14. Lundberg, S.M., and Lee, S.I. (2017). "A unified approach to interpreting model predictions." Advances in neural information processing systems, 30.
  15. McCabe, B., Loughlin, C., Munteanu, R., Tucker, S., and Lam, A. (2008). "Individual safety and health outcomes in the construction industry." Canadian Journal of Civil Engineering, 35(12), pp. 1455-1467. https://doi.org/10.1139/L08-091
  16. Meng, X., and Chan, A. H. (2020). "Demographic influences on safety consciousness and safety citizenship behavior of construction workers." Safety science, 129, 104835.
  17. Ministry of Employment and Labor. (2021). "Occupational Safety Accident Status." Accessed: Jun. 11, 2023. [Online]. Available: https://kosis.kr/statHtml/statHtml.do?orgId=118&tblId=DT_11806_N000&conn_path=I2
  18. Murtagh, F. (1991). "Multilayer perceptrons for classification and regression." Neurocomputing, 2(5-6), pp. 183-197. https://doi.org/10.1016/0925-2312(91)90023-5
  19. Park, H., and Koo, C. (2022). "Effect of virtual reality-based construction safety education on the learning performance of construction workers - Using CAMIL theory -" Korean Journal of Construction Engineering and Management, KICEM, 23(3), pp. 104-115.
  20. Park, S.W. (2017). "Suggestions on Remedies for Basic Safety and Health Education and New Hire Education in the Construction Industry." M.E. Dissertation, Kyung Hee University.
  21. Segal, M.R. (2004). "Machine learning benchmarks and random forest regression." UCSF: Center for Bioinformatics and Molecular Biostatistics, pp. 1-14.
  22. Shapley, Lloyd S. (1953). A value for n-person games, pp. 307-317.
  23. Shin, K.N., Joo, S.U., and Yang, S.H. (2015). "A Study on the Status and Improvement of the Basic Occupational Safety and Health Training for the Construction Industry : focused on the Educational Methods and Contents." Journal of the Korea Academia-Industrial Cooperation Society, 16(5), pp. 3484-3490. https://doi.org/10.5762/KAIS.2015.16.5.3484
  24. Smola, A.J., and Scholkopf, B. (2004). "A tutorial on support vector regression." Statistics and computing, 14, pp. 199-222. https://doi.org/10.1023/B:STCO.0000035301.49549.88
  25. Thevaraja, M., Rahman, A., and Gabirial M. (2019). "Recent developments in data science: Comparing linear, ridge and lasso regressions techniques using wine data." Proceedings of the International Conference on Digital Image & Signal Processing, Oxford United Kingdom, 1, pp. 1-6.
  26. Yu, W.D., Wang, K.C., and Wu, H.T. (2022). "Empirical Comparison of Learning Effectiveness of Immersive Virtual Reality-Based Safety Training for Novice and Experienced Construction Workers." Journal of Construction Engineering and Management, 148(9), 04022078.