• Journal of Korean Society of Forest Science
• /
• v.4 no.1
• /
• pp.39-41
• /
• 1965

(1) The durability of fifteen species of hard woods grown in Kangwon-do in relation to Polystictus Versecolor L. Fr. and Irpex consors Berk was studied. (2) The least affected hard wood species by Polystutus Versecolor L. Fr. were Q. serrata, C. crenata, M. amurensis, F. rhynchophylla and J. mandschrica; the moderatly affected species were Q. Variabilis, U. Davidiana var japonica, B. latiforia, C. controversa, P. padus and A. mono; and the most highly affected species were P. serrulata var. spondanea, S. obassia, T. amurensis and B. schmidtii. The least affected hard wood species by Irpex consors Berk, were U. Davidiana var japonica, C. crenata, M. amurensis, F. rhynchophylla, and J. mandshurica; the moderatly affected species were Q. Valiabilis, Q. serrata, P. serrulata var. spondanea, C. controversa, and A. mono; and the most highly affected species were B. latiforia, P. padus, S. obassia, T. amurensis, and J-mandshurica. (3) No difference was obscured on the durabilities on effected by kind of fungus. (4) Correlationship between specific gravity and durability of the woods was not significant.

• KOREAN JOURNAL OF CROP SCIENCE
• /
• v.8 no.1
• /
• pp.31-36
• /
• 1970

This experiment was designed to get some information on the parts in which necrosis occurs first in the embryo of rice, and on the phenomenon of necrosis that develops into other parts. Norin No.6 harvested in 1967 was used for this experiment and necrosis appearance was investigated by the T.T.C. method. The results obtained are summarized as follows; 1) Necrosis of the embryo in rice occurred in the plumule initially. 2) It was observed that the necrosis developed from the plumule to the radicle. 3) Finally, it was shown that necrosis developed from the surface tissue of the embryo to the inside tissue.

• Journal of the Korean Operations Research and Management Science Society
• /
• v.18 no.2
• /
• pp.57-81
• /
• 1993

This paper is concerned with analyzing the bankruptcy prediction power of three methods : Multivariate Discriminant Analysis (MDA), Inductive Learning, Neural Network, MDA has been famous for its effectiveness for predicting bankrupcy in accounting fields. However, it requires rigorous statistical assumptions, so that violating one of the assumptions may result in biased outputs. In this respect, we alternatively propose the use of two AI models for bankrupcy prediction-inductive learning and neural network. To compare the performance of those two AI models with that of MDA, we have performed massive experiments with a number of Korean bankrupt-cases. Experimental results show that AI models proposed in this study can yield more robust and generalizing bankrupcy prediction than the conventional MDA can do.

• Proceedings of the Korean Society for Quality Management Conference
• /
• 2004.04a
• /
• pp.655-673
• /
• 2004

This paper is concerned with analysing the bankruptcy prediction power of three models: Multivariate Discriminant Analysis(MDA ), Logit Analysis, Neural Network. The after-crisis bankrupted companies were limited to the research data and the listed companies belonging to manufacturing industry was limited to the research data so as to improve prediction accuracy and validity of the model. In order to assure meaningful bankruptcy prediction, training data and testing data were not extracted within the corresponding period. The result is that prediction accuracy of neural network model is more excellent than that of logit analysis and MDA model when considering that execution of testing data was followed by execution of training data.

• Asia pacific journal of information systems
• /
• v.5 no.1
• /
• pp.36-51
• /
• 1995

본 논문에서는 비구조적인 의사결정문제를 효과적으로 해결하기 위하여 감독학습 인공신경망 모형과 비감독학습 인공신경망 모형을 결합한 하이브리드 인공신경망 모형인 HYNEN(HYbrid NEural Network) 모형을 제안한다. HYNEN모형은 주어진 자료를 클러스터화 하는 CNN(Clustering Neural Network)과 최종적인 출력을 제공하는 ONN(Output Neural Network)의 2단계로 구성되어 있다. 먼저 CNN에서는 주어진 자료로부터 적정한 퍼지규칙을 찾기 위하여 클러스터를 구성한다. 그리고 이러한 클러스터를 지식베이스로하여 ONN에서 최종적인 의사결정을 한다. CNN에서는 SOFM(Self Organizing Feature Map)과 LVQ(Learning Vector Quantization)를 클러스터를 만든 후 역전파학습 인공신경망 모형으로 이를 학습한다. ONN에서는 역전파학습 인공신경망 모형을 이용하여 각 클러스터의 내용을 학습한다. 제안된 HYNEN 모형을 우리나라 기업의 도산자료에 적용하여 그 결과를 다변량 판별분석법(MDA:Multivariate Discriminant Analysis)과 ACLS(Analog Concept Learning System) 퍼지 ARTMAP 그리고 기존의 역전파학습 인공신경망에 의한 실험결과와 비교하였다.

• The Korean Journal of Mycology
• /
• v.15 no.3
• /
• pp.131-134
• /
• 1987

About 350 samples of mushrooms were collected in Mt. Halla of Cheju Island from March to December of 1986. 45 species of Aphyllophorales were identified and included in 7 families and 26 genera. Among them, Inonotus nodulosus and Daedaleopsis purpurea were recognized as unrecorded species in Korea. Characteristics of these two species were described and Korean names were designated.

• Health Policy and Management
• /
• v.12 no.3
• /
• pp.54-76
• /
• 2002

This study investigated how much EVA which evaluate firm's value can explain hospital bankruptcy prediction as a explanatory variable including financial indicators in Korea. In this study, artificial neural network and logit regression which are traditional statistical were used as the model for bankruptcy prediction. Data used in this study were financial and economic value added indicators of 34 bankrupt and -:4 non-bankrupt hospitals from the Database of Korean Health Industry Development Institute. The main results of this study were as follows: First, there was a significant difference between the financial variable model including EVA and the financial variable model excluding EVA in pre-bankruptcy analysis. Second, EVA could forecast bankruptcy hospitals up to 83% by the logistic analysis. Third, the EVA model outperformed the financial model in terms of the predictive power of hospital bankruptcy. Fourth, The predictive power of neural network model of hospital bankruptcy was more powerful than the legit model. After all the result of this study will be useful to future study on EVA to evaluate bankruptcy hospitals forecast.

• The Science & Technology
• /
• v.10 no.9 s.100
• /
• pp.144-147
• /
• 1977

한국과학기술정보센터(KORSTIC)와 전경련의 공동주최로 강등차랑 일본과학기술정보센터(JICST) 이사장 초청 강연회가 9월 7일 3.1 빌딩 32층에서 개최되었다. 「일본산업계의 기술정보 이용」이라는 주제로 강연에서 강리사장은 「연구개발력이 약한 기업은 미래가 없으며 불황이라도 닥치는 날이면 도산하는 예도 있다」고 말하면서 「그러므로 산업발전을 위해서는 기술개발이 절대로 필요하며 그 전제로서 비용이 적게드는 과학기술정보를 잘 활용할 것」을 기업간부들에게 권하였다. 현재 세계에는 연간 400만건의 과학기술정보가 홍수처럼 쏟아지고 있으므로 이를 자국의 필요에 맞게 제품화하는 것이 정보센터의 큰 임무인 동시에 제품화된 정보가 수요자의 필요에 맞게 그리고 수요자가 쉽게 구할 수 있도록 서어비스를 다양화하는 것도 중요하다고 강조하면서 일본에서는 500억대 단말기로 전국적으로 Network를 확대할 계획이라고 말하였다. 다음은 이날 강리사장이 행한 강연전문이다.

• Journal of Plant Biology
• /
• v.25 no.1
• /
• pp.9-19
• /
• 1982

A thin-layer chromatographic study was made of the chloroform-soluble and flavonoid fractions from the fruit peels of 16 species, 2 varieties and 5 formas of the Citrus plants cultivated in Je Ju Island for their interspecific relatinships. In addition, 3 hybrids and 9 native plants were also studied for their taxonomic position. Three phenograms were developed from these chromatographic data after cluster analysis via the unweighted paired group method using rithmatic average by Sneath and Sokal. These plants were grouped into 5 alliences based on the phenogram obtained from the chloroform-soluble fracitons, which were nearly identical to the subgenus rank by Tanaka, and rutinoside and neohesperidoside groups by Horowitz. Those from the flavonoid and methanol-soluble fractions were not able to evaluate the morphological classification except for a few cases.

• The Korean Journal of Zoology
• /
• v.29 no.4
• /
• pp.272-282
• /
• 1986

Univariate and multivariate analyses of morphometric characters were performed with samples of three subspecies of striped field mice (Apodemus agrarius coreae, A. agrarius pallescens, and A. agrarius chejuensis). It was found that the samples of A. agrarius chejuensis from Jeju-Do were distintc from those of the other two subspecies from the Korean peninsular, whereas subspecies coreae was similar to subspecies pallescens: it is concluded that A. agrarius pallescens is a synonym of A. agrarius coreae. Further analyses will be needed to clearify the subspecific status of A. agrarius chejuensis.