Journal of the Korean Society of Safety (한국안전학회지)

The Korean Society of Safety (한국안전학회)
권호 표지
DOI QR코드

DOI QR Code

Development of Accident Classification Model and Ontology for Effective Industrial Accident Analysis based on Textmining

효과적인 산업재해 분석을 위한 텍스트마이닝 기반의 사고 분류 모형과 온톨로지 개발

  • Ahn, Gilseung (Department of Industrial and Management Engineering, Hanyang University) ;
  • Seo, Minji (Department of Industrial and Management Engineering, Hanyang University) ;
  • Hur, Sun (Department of Industrial and Management Engineering, Hanyang University)
  • 안길승 (한양대학교 산업경영공학과) ;
  • 서민지 (한양대학교 산업경영공학과) ;
  • 허선 (한양대학교 산업경영공학과)
  • Received : 2017.08.09
  • Accepted : 2017.09.06
  • Published : 2017.10.31
Download PDF
⟨ Previous Next ⟩

Abstract

Accident analysis is an essential process to make basic data for accident prevention. Most researches depend on survey data and accident statistics to analyze accidents, but these kinds of data are not sufficient for systematic and detailed analysis. We, in this paper, propose an accident classification model that extracts task type, original cause materials, accident type, and the number of deaths from accident reports. The classification model is a support vector machine (SVM) with word occurrence features, and these features are selected based on mutual information. Experiment shows that the proposed model can extract task type, original cause materials, accident type, and the number of deaths with almost 100% accuracy. We also develop an accident ontology to express the information extracted by the classification model. Finally, we illustrate how the proposed classification model and ontology effectively works for the accident analysis. The classification model and ontology are expected to effectively analyze various accidents.

Keywords

References

  1. http://laborstat.molab.go.kr/
  2. T. Kontogiannis, V. Leopoulous and N. Marmaras, "A Comparison of Accident Analysis Techniques for Safetycritical Man-machine Systems", International Journal of Industrial Ergonomics, Vol. 25, No. 4, pp. 327-347, 2000. https://doi.org/10.1016/S0169-8141(99)00022-0
  3. J. Kim, J. B. Lee, and S. R. Chang, "A Study on the Accident Analysis of Architectural Work", Journal of the Korean Society of Safety, Vol. 31, No. 3, pp. 96-101, 2016. https://doi.org/10.14346/JKOSOS.2016.31.3.96
  4. O. N. Jeong, Y. S. Yun and O. H. Kwon, "Accident Prevention for the Elevator and Escalator by the Accident Type Analysis", Journal of the Korean Society of Safety, Vol. 31, No. 4, pp. 15-21, 2016. https://doi.org/10.14346/JKOSOS.2016.31.4.15
  5. Y. S. Yun and O. H. Kwon, "A Study on Industrial Injury Analysis for Manufacturing Industry", Journal of the Korean Society of Safety, Vol. 28, No. 8, pp. 13-18, 2013.
  6. M. Gruninger and J. Lee, "Ontology", Communications of the ACM, Vol. 45, No. 2, p. 39, 2002. https://doi.org/10.1145/585597.585599
  7. D. Yang, R. Miao, H. Wu and Y. Zhou, "Product Configuration Knowledge Modeling using Ontology Web Language", Expert Systems with Applications, Vol. 36, No. 3, pp. 4399-4411, 2009. https://doi.org/10.1016/j.eswa.2008.05.026
  8. F. J. Garcia-Penalvo, R. Colomo-Palacios, J. Garcia and R. Theron, "Towards an Ontology Modeling Tool, A Validation in Software Engineering Scenarios", Expert Systems with Applications, Vol. 39, No. 13, pp. 11468-11478, 2012. https://doi.org/10.1016/j.eswa.2012.04.009
  9. https://www.kosha.or.kr/board.do?menuId=541
  10. K. N. Junejo, A. Karim, M. T. Hassan and M. Jeon, "Term-based Discriminative Information Space for Robust Text Classification", Information Science, Vol. 372, pp. 518-538, 2016. https://doi.org/10.1016/j.ins.2016.08.073
  11. http://konlpy-ko.readthedocs.io/ko/v0.4.3/
  12. H. Drucker, D. Wu and V. N. Vapnik, "Support Vector Machines for Spam Catecorization", IEEE Transactions on Neural Networks, Vol. 10, No. 5, pp. 1048-1054, 1999. https://doi.org/10.1109/72.788645
  13. Y. Yang, "An Evaluation of Statistical Approaches to Text Categorization", Information Retrieval, Vol. 1, No. 1, pp. 69-90, 1999. https://doi.org/10.1023/A:1009982220290