한국가스학회지 (Journal of the Korean Institute of Gas)

  • 제25권3호
  • /
  • Pages.9-15
  • /
  • 2021
  • /
  • 1226-8402(pISSN)
  • /
  • 2713-6922(eISSN)
한국가스학회 (The Korean Institute of GAS)
권호 표지
DOI QR코드

DOI QR Code

지식베이스를 이용한 작업자 증상 기반 화학물질 추정 시스템 설계

Worker Symptom-based Chemical Substance Estimation System Design Using Knowledge Base

  • 주용택 (명지대학교 재난안전학과) ;
  • 이동훈 (명지대학교 재난안전학과) ;
  • 신은지 (명지대학교 재난안전학과) ;
  • 유상우 (명지대학교 재난안전학과) ;
  • 신동일 (명지대학교 재난안전학과)
  • Ju, Yongtaek (Dept. of Disaster and Safety, Myongji University) ;
  • Lee, Donghoon (Dept. of Disaster and Safety, Myongji University) ;
  • Shin, Eunji (Dept. of Disaster and Safety, Myongji University) ;
  • Yoo, Sangwoo (Dept. of Disaster and Safety, Myongji University) ;
  • Shin, Dongil (Dept. of Disaster and Safety, Myongji University)
  • 투고 : 2021.04.23
  • 심사 : 2021.06.19
  • 발행 : 2021.06.30
PDF 다운로드
⟨ 이전 논문 다음 논문 ⟩

초록

본 논문에서는 산업현장 화학물질 인체 접촉 증상 기반 지식베이스 구축 및 화학물질 추정 시스템 설계에 대한 연구이다. 미국NIH에서 제공하는 WISER 프로그램의 499개의 화학물질 접촉 증상 정보로 활용하였다. 지식베이스 구축을 위해 AllegroGraph 7.0.1 프로그램을 이용하였으며 입력된 Chemical structure로 Triple 값인 Cas No., Synonyms, Symptom, SMILES, InChl, Formula를 사용 하였다. 또한 작업자의 증상을 안내하는 방법은 AI 스피커를 활용한 방식이 가능하며 지식베이스 구축 결과 암모니아(CAS No: 7664-41-7)를 기준으로 39개의 증상이 WISER 프로그램과 동일함을 확인 하였다. 이를 통해 화학물질 추정 시스템의 증상 추출 과정에 지식베이스 구축이 가능하였다.

In this paper, a study on the construction of a knowledge base based on natural language processing and the design of a chemical substance estimation system for the development of a knowledge service for a real-time sensor information fusion detection system and symptoms of contact with chemical substances in industrial sites. The information on 499 chemical substances contact symptoms from the Wireless Information System for Emergency Responders(WISER) program provided by the National Institutes of Health(NIH) in the United States was used as a reference. AllegroGraph 7.0.1 was used, input triples are Cas No., Synonyms, Symptom, SMILES, InChl, and Formula. As a result of establishing the knowledge base, it was confirmed that 39 symptoms based on ammonia (CAS No: 7664-41-7) were the same as those of the WISER program. Through this, a method of establishing was proposed knowledge base for the symptom extraction process of the chemical substance estimation system.

키워드

과제정보

본 연구는 산업통상자원부 지식서비스산업 핵심기술개발사업(K_G012000926501)의 연구비지원에 의해 수행되었습니다. 이에 감사드립니다.

참고문헌

  1. KOSHA(Korea Occupational Safety & Health Agency), http://www.kosha.or.kr/
  2. Jeong-Min Cha, Seong-Ho Hyun, "A Study on the Analysis of Domestic Hazardous Material Accidents in Recent 10 Years", Korean Journal of Hazardous Materials , 7(1), 54-64, (2019) https://doi.org/10.31333/kihm.2019.7.1.54
  3. NIH (National Institutes of Health), https://wiser.nlm.nih.gov/
  4. Kim, J.R., Ro, K.H., "Construction of Knowledge Base Based on Graph Database for College Student Career Advice Using Public Data", Journal of The Institute of Electronics and Information Engineers, 56(10), 41-48, (2019) https://doi.org/10.5573/ieie.2019.56.10.41
  5. Hong, G.W., Myaeng, S.H., "Generation of open relation embeddings from natural language sentences using BERT and knowledge base relation embeddings", Journal of The Korean Institute of Information Scientists and Engineers, 533-535, ICC JEJU, Korea, (2019)
  6. Kim, J.H., Lee, M.J., "Knowledge Extraction Methodology and Framework from Wikipedia Articles for Construction of Knowledge-Base", Journal of Intelligence and Information Systems, 25(1), 43-61, (2019) https://doi.org/10.13088/JIIS.2019.25.1.043
  7. Jung, S.W., Choi, M.S., Kim, H.S., "Construction of Korean Knowledge Base Based on Machine Learning from Wikipedia", Journal of KIISE, 42(8), 1065-1070, (2015) https://doi.org/10.5626/JOK.2015.42.8.1065
  8. Kingma, D. and J. Ba, Adam: A method for stochastic optimization, Proceedings of the 3rd International Conference for Learning Representations, (2015)
  9. B. Saha and K. Goebel, Battery data set,"NASA AMES Prognostics Data Repository, (2007)
  10. A. Jain, K. Nandakumar and A. Ross, "Score normalization in multimodal biometric systems", Pattern Recognit., 38(12), 2270-2285, (2005) https://doi.org/10.1016/j.patcog.2005.01.012