논문 상세보기

건설업의 산업재해 특성분석을 위한 의사결정나무 기법의 상용 최적 알고리즘 선정 KCI 등재

Selection of an Optimal Algorithm among Decision Tree Techniques for Feature Analysis of Industrial Accidents in Construction Industries

  • 언어KOR
  • URLhttps://db.koreascholar.com/Article/Detail/245288
구독 기관 인증 시 무료 이용이 가능합니다. 4,000원
대한안전경영과학회지 (Journal of Korea Safety Management & Science)
대한안전경영과학회 (Korea Safety Management & Science)
초록

The consequences of rapid industrial advancement, diversified types of business and unexpected industrial accidents have caused a lot of damage to many unspecified persons both in a human way and a material way Although various previous studies have been analyzed to prevent industrial accidents, these studies only provide managerial and educational policies using frequency analysis and comparative analysis based on data from past industrial accidents. The main objective of this study is to find an optimal algorithm for data analysis of industrial accidents and this paper provides a comparative analysis of 4 kinds of algorithms including CHAID, CART, C4.5, and QUEST. Decision tree algorithm is utilized to predict results using objective and quantified data as a typical technique of data mining. Enterprise Miner of SAS and AnswerTree of SPSS will be used to evaluate the validity of the results of the four algorithms. The sample for this work chosen from 19,574 data related to construction industries during three years (2002~2004) in Korea.

저자
  • 임영문 | Leem, Young-Moon
  • 최요한 | Choi, Yo-Han