Earticle

초록

영어

This paper presents a novel non-parametric methodology – rough set theory – for accident occurrence exploration. The rough set theory allows researchers to analyze accidents in multiple dimensions and to model accident occurrence as factor chains. Factor chains are composed of Seaman characteristic, ship’s characteristics, navigational behavior and environment factors that imply typical accident occurrence. Rose2 software tool is used. The purpose of this application is to find out the critical attributes to reduce the number of the fatality in maritime accidents. This paper explains the application on the accident reports of Accident Data database, containing data records for all categories of maritime accidents between the years of 2003 and 2009. Variable precision rough set is used to reduce the attributes of data set. The categorization tools and decision trees are used to find the relations and rules about the accidents resulted in fatality. Some rules about the fatality are obtained and also the attributes that affect the fatality in the incident have determined.

목차

Abstract
 1. Introduction
 2. Rough Set Theory
 3. Rule Identification Algorithms
  3.1 Data Preprocessing
  3.2 Reduction of Attributes
  3.3 Rule Identification Algorithm
  3.4 The Rule-validation Procedure
 4. Empirical Study for Exploring Accident Occurrence and Losses
  4.1 Identification Route Segment Prone to Accident
  4.2 Identification of Injury Severity&Death and Economic Losses
 5. Discussion and Conclusion
  5.1 Discussion
  5.2 Conclusion
 ACKNOWLEDGEMENTS
 References

키워드

저자

• Hao ZHANG [ Shanghai Maritime University, Shanghai 201305, China ]
• Ying-jie XIAO [ Shanghai Maritime University, Shanghai 201305, China ]
• Liang CHEN [ Shanghai Maritime University, Shanghai 201305, China ]

참고문헌

발행기관

간행물

표지보기 관심저널 등록

• 간행물명

  International Journal of u- and e- Service, Science and Technology

• 간기

  격월간

• pISSN

  2005-4246

• 수록기간

  2008~2016

• 십진분류

  KDC 505 DDC 605