• The Bulletin of The Korean Astronomical Society
• /
• v.27 no.2
• /
• pp.26-26
• /
• 2002

• Proceedings of the Korean Institute of Landscape Architecture Conference
• /
• 2009.03a
• /
• pp.15-18
• /
• 2009

• Magazine of the Korea Concrete Institute
• /
• v.28 no.4
• /
• pp.40-45
• /
• 2016

• The Bulletin of The Korean Astronomical Society
• /
• v.28 no.2
• /
• pp.52-52
• /
• 2003

• Proceedings of the Korean Society of Crop Science Conference
• /
• 2020.11a
• /
• pp.59-59
• /
• 2020

• Horticultural Science & Technology
• /
• v.35 no.4
• /
• pp.480-489
• /
• 2017

We investigated a suitable method for in vitro germination of spores, propagation of prothalli, and the formation of sporophytes in the fern Dryopteris nipponensis Koidz. Spore germination rate was relatively high regardless of culture medium. Prothallus development was faster in Knop medium than in Murashige and Skoog (MS) media. Prothalli used in all experiments were obtained from germinated spores, and were cultivated in different concentrations of media components. The active formation of sexual organs such as antheridium made 1MS medium suitable for prothallus propagation, although there was a lower propagation ratio compared to Knop medium. Growth and morphogenesis of prothalli were most effective on 1MS medium containing 2% sucrose, and 60 mM of total nitrogen source with 20:40 mM ratio of $NH_4{^+}:NO_3{^-}$. To select a suitable soil composition for sporophyte formation, ground prothalli were cultivated on single and mixed soils using bed soil, peat moss, perlite, and decomposed granite for 14 weeks. Bed soil promoted sporophyte formation and growth regardless of single or mixed use. In particular, a mixture of bed soil and decomposed granite in a 2:1 ratio (v:v) led to accelerated sporophyte formation ($0.83/cm^2$).

• The Bulletin of The Korean Astronomical Society
• /
• v.32 no.1
• /
• pp.28.2-28.2
• /
• 2007

• Proceedings of KOSOMES biannual meeting
• /
• 2017.04a
• /
• pp.269-269
• /
• 2017

• Proceedings of the Korean Radioactive Waste Society Conference
• /
• 2016.10a
• /
• pp.325-326
• /
• 2016

• Proceedings of the Korean Information Science Society Conference
• /
• 1999.10b
• /
• pp.57-59
• /
• 1999

본 논문에서는 최대 엔트로피 원리에 기반한 문서 분류기의 학습을 제안한다. 최대 엔트로피 기법은 자연언어 처리에서 언어 모델링(Language Modeling), 품사 태깅 (Part-of-Speech Tagging) 등에 널리 사용되는 방법중의 하나이다. 최대 엔트로피 모델의 효율성을 위해서는 자질 선정이 중요한데, 본 논문에서는 자질 집합의 선택을 위한 기준으로 chi-square test, log-likelihood ratio, information gain, mutual information 등의 방법을 이용하여 실험하고, 전체 후보 자질에 대한 실험 결과와 비교해 보았다. 데이터 집합으로는 Reuters-21578을 사용하였으며, 각 클래스에 대한 이진 분류 실험을 수행하였다.