DC Field | Value | Language |
---|---|---|
dc.contributor.advisor | Lee, Tae-Eog | - |
dc.contributor.advisor | 이태억 | - |
dc.contributor.author | Seo, Jin-Kyu | - |
dc.contributor.author | 서진규 | - |
dc.date.accessioned | 2011-12-14T04:18:46Z | - |
dc.date.available | 2011-12-14T04:18:46Z | - |
dc.date.issued | 1995 | - |
dc.identifier.uri | http://library.kaist.ac.kr/search/detail/view.do?bibCtrlNo=98774&flag=dissertation | - |
dc.identifier.uri | http://hdl.handle.net/10203/41451 | - |
dc.description | 학위논문(석사) - 한국과학기술원 : 산업공학과, 1995.2, [ ii, 34 p. ] | - |
dc.description.abstract | We propose the use of the maximum entropy method for estimation of rare event probabilities. This method does not presume any distribution function form, but instead flexibly incorporates information from samples as constraints in the associated optimization problem that maximizes the entropy. While the moments information is usually used for MEM, to improve the accuracy of tail probability estimation, we also use tail information from the samples as constraints. We apply this method to several known distributions. We compare our method with the generalized extreme value theory method. | eng |
dc.language | eng | - |
dc.publisher | 한국과학기술원 | - |
dc.title | Estimation of rare event probabilities by maximum entropy method | - |
dc.title.alternative | 엔트로피 최대화방법을 이용한 극미부 확률의 추정 | - |
dc.type | Thesis(Master) | - |
dc.identifier.CNRN | 98774/325007 | - |
dc.description.department | 한국과학기술원 : 산업공학과, | - |
dc.identifier.uid | 000933245 | - |
dc.contributor.localauthor | Lee, Tae-Eog | - |
dc.contributor.localauthor | 이태억 | - |
Items in DSpace are protected by copyright, with all rights reserved, unless otherwise indicated.