• The Korean Journal of Financial Management
• /
• v.12 no.2
• /
• pp.1-23
• /
• 1995

본 연구의 목적은 특정 금융기관의 주거래기업들에 대한 부실예측을 위해 주거래기업들을 잠식, 도산, 그리고 건전기업과 같이 세집단으로 구분하여 예측하고자 하며, 기업부실 예측력에 영향을 미치는 세 가지 요인으로서 표본구성, 투입 변수, 분석 기법의 관점에서 다음을 살펴보는 것이다. 첫째, 기업부실예측에서 전통적인 delta learning rule과 sigmoid함수를 사용한 역전파학습(신경망 I)과 이들의 변형형태인 normalized cumulative delta learning rule과 hyperbolic tangent함수를 사용한 역전파 학습(신경망 II)과의 예측력의 차이를 살펴보고 또한 이러한 두가지 신경망기법의 예측력을 MDA(다변량판별분석) 결과와 비교하여 신경망기법에 대한 예측력의 유용성을 살펴보고자 한다. 둘째, 세집단분류문제에서는 잠식, 도산, 건전기업의 구성비율이 위의 세가지 예측기법의 결과에 어떠한 영향을 미치는지를 살펴보고자 한다. 세째, 투입 변수선정은 기존연구 또는 이론을 바탕으로 연구자의 판단에 의해 선택하는 방법과 다수의 변수를 가지고 통계적기법에 의해 좋은 판별변수의 집합을 찾는 것이다. 본 연구에서는 이러한 방법들에 의해 선정된 투입변수들이 세가지 예측기법의 결과에 어떠한 영향을 미치는지를 살펴보고자 한다. 이러한 관점에서 본 연구의 실증분석 결과를 요약하면 다음과 같다. 1) 신경망기법이 두집단에서와 같이 세집단 분류문제에서도 MDA보다는 더 높은 예측력을 보였다. 2) 잠식과 도산기업의 수는 비슷하게 그리고 건전기업의 수는 잠식과 도산기업을 합한 수와 비슷하게 표본을 구성하는 것이 예측력을 향상하는데 도움이 된다고 할 수 있다. 3) 속성별로 고르게 투입변수로 선정한 경우가 그렇지 않은 경우보다 더 높은 예측력을 보였다. 4) 전통적인 delta learning rule과 sigmoid함수를 사용한 역전파학습 보다는 normalized cumulative delta learning rule과 hyperbolic tangent함수를 사용한 역전파 학습이 더 높은 예측력을 보였다. 이러한 현상은 두집단문제에서 보다 세집단문제에서 더 큰 차이를 나타내고 있다.

• Journal of the Korean Wood Science and Technology
• /
• v.43 no.6
• /
• pp.701-713
• /
• 2015

A model was designed to identify wood species between Pinus densiflora for. erecta Uyeki and Pinus densiflora Sieb. et Zucc. using the near-infrared (NIR) spectroscopy in combination with principal component analysis (PCA) and partial least square discriminant analysis (PLS-DA). In the PCA using all of the spectra, Pinus densiflora for. erecta Uyeki and Pinus densiflora Sieb. et Zucc. could not be classified. In the PCA using the spectrum that has been measured in sapwood, however, Pinus densiflora for. erecta Uyeki and Pinus densiflora Sieb. et Zucc. could be identified. In particular, it was clearly classified by sapwood in radial section. And more, these two species could be perfectly identified using PLS-DA prediction model. The best performance in species identification was obtained when the second derivative spectra was used; the prediction accuracy was 100%. For prediction model, the $R_p{^2}$ value was 0.86 and the RMSEP was 0.38 in second derivative spectra. It was verified that the model designed by NIR spectroscopy with PLS-DA is suitable for species identification between Pinus densiflora for. erecta Uyeki and Pinus densiflora Sieb. et Zucc.

• Conservation Science in Museum
• /
• v.1
• /
• pp.61-74
• /
• 1999

Elemental analysis of 40 glass samples from the Northern Tomb and the Southern Tomb of Hwangnam-daech'ong No. 98 was performed. Fourteen compositions of each sample were analyzed quantitatively by SEM-EDS and glass samples were classified by multivariate analysis such as PCA. All of 40 samples were confirmed to be Na₂O-CaO-SiO₂ system with about 20% of Na₂O. Samples were classified into two groups by doing PCA on concentrations of 5 major elements(SiO₂, Al₂O₃, Na₂O, CaO and K₂O). Samples included in group I showed the concentration of Al₂O₃ is about 9.7% and that of CaO, about 2.2%. In group II, concentration of Al₂O₃ is about 3.2% and that of CaO, about 4.9%. Especially yellow grains embedded in sample No. 12 were shown to be PbSnO₃ by micro XRD, which was the first coloring material ever found in Korea. Lead isotope ratios of samples No. 12 and No. 17 which contained lead were measured by TIMS. The origin of lead was traced by means of multivariate analysis such as SLDA. The result showed that lead from southern China and southern Korea had been used for making glass.

• Journal of Digital Convergence
• /
• v.11 no.5
• /
• pp.429-436
• /
• 2013

Context aware environment u-health service is to provide health service with recognition of a computer. The computer recognizes that a patient can contact real life in many context. Context aware environment service for recommend have to definition of context data and service recommendations related to factors shall be identified. In this paper, Context aware environment of u-health service will be provide context data related to identifies recommendations factors using multivariate analysis method and recommendations factors creation to decision tree, association rule based decision model. health service recommend for significantly context data can be distinguish through recommendation factors of identify. Also, context data of patient can know preference factors through preference decision model.

• 한국해양학회지
• /
• v.26 no.4
• /
• pp.295-303
• /
• 1991

Multi-spectral analyses of excitation and emission fluorescence was applied to spilled crude oils in characterization of their specific fluorescence patterns which is called oil fingerprints. In the present study, oil fingerprints of 33 crude, 4 fuel and 2 other oils were analyzed to establish data base library search system. Cluster analysis showed that crude oils could be classified into two large groups according to their fluorescence characteristics. In simulated experiments, all the spilled sources was identifiable by the present library search system. In the natural environment this system could identify the exact source of weathered crude oil slicks upton 10 days. The present study shows that the fluorescence fingerprinting method with the library search system is reliable and superior to toutine GC/HPLC analyses in identification of the source of weathered spilled oils in the marine environment.

• Journal of Plant Biotechnology
• /
• v.38 no.1
• /
• pp.9-14
• /
• 2011

To determine whether pattern recognition based on metabolite fingerprinting for whole cell extracts can be used to discriminate cultivars metabolically, leaves of nine commercial Orostachys plants were subjected to Fourier transform infrared spectroscopy (FT-IR). FT-IR spectral data from leaves were analyzed by principal component analysis (PCA) and Partial least square discriminant analysis (PLS-DA). The dendrogram based on hierarchical clustering analysis of these PLS-DA data separated the nine Orostachys species into five major groups. The first group consisted of O. iwarenge 'Yimge', 'Jeju', 'Jeongsun' and O. margaritifolius 'Jinju' whereas in the second group, 'Sacheon' was clustered with 'Busan,' both of which belong to O. malacophylla species. However, 'Samchuk', belong to O. malacophylla was not clustered with the other O. malacophylla species. In addition, O. minuta and O. japonica were separated to the other Orostachys plants. Thus we suggested that the hierarchical dendrogram based on PLS-DA of FT-IR spectral data from leaves represented the most probable chemotaxonomical relationship between commercial Orostachys plants. Furthermore these metabolic discrimination systems could be applied for reestablishment of precise taxonomic classification of commercial Orostachys plants.

• Journal of Intelligence and Information Systems
• /
• v.9 no.1
• /
• pp.227-249
• /
• 2003

Prediction of corporate failure using past financial data is a well-documented topic. Early studies of bankruptcy prediction used statistical techniques such as multiple discriminant analysis, logit and probit. Recently, however, numerous studies have demonstrated that artificial intelligence such as neural networks can be an alternative methodology for classification problems to which traditional statistical methods have long been applied. In building neural network model, the selection of independent and dependent variables should be approached with great care and should be treated as model construction process. Irrespective of the efficiency of a teaming procedure in terms of convergence, generalization and stability, the ultimate performance of the estimator will depend on the relevance of the selected input variables and the quality of the data used. Approaches developed in statistical methods such as correlation analysis and stepwise selection method are often very useful. These methods, however, may not be the optimal ones for the development of neural network model. In this paper, we propose a genetic algorithms approach to find an optimal or near optimal input variables fur neural network modeling. The proposed approach is demonstrated by applications to bankruptcy prediction modeling. Our experimental results show that this approach increases overall classification accuracy rate significantly.

• Journal of Applied Biological Chemistry
• /
• v.64 no.3
• /
• pp.245-251
• /
• 2021

Codonopsis lanceolata (Deoduk) was grown in East Asia, including Korea, China, Japan, and Russia, and the roots of C. lanceolata have been used as functional foods and traditional medicine to treat symptoms of cough, bronchitis, asthma, tuberculosis, and dyspepsia. The phytochemicals of C. lanceolata have been reported such as phenylpropanoids, polyacetylenes, saponins, and flavonoids that are involved in pharmacological effects such as anti-obesity, anti-inflammation, anti-tumor, anti-oxidant, and anti-microbial activities. Selecting marker substances of the main producing area by MS-based metabolomics analysis is important to ensure the beneficial effect of C. lanceolata without side-effects because differences in cultivated areas of plants were related not only to the safety of medicinal plants but also to changes in chemical composition and biological efficacy. In our present study, ultra-performance liquid chromatography quadrupole time-of-flight mass spectrometry combined with multivariate statistical analysis was applied to recognize the main producing area of C. lanceolata in South Korea. As a result of Principal Component Analysis and loading plot analysis of three groups, Inje (Kangwon-do), Hoengseong (Kangwon-do), and Muju (Jeonlabuk-do), several secondary metabolites of C. lanceolata including tangshenoside I, lancemaside A, and lancemaside G, were suggested as potential marker substances to distinguish the place of main producing area of C. lanceolata.

• Journal of Korean Society of Forest Science
• /
• v.104 no.3
• /
• pp.375-382
• /
• 2015

We classified the forest type and figured out the ecological characteristics for each of the types in order to provide the basic informations for being induced ecologically efficient forest practice plan by vegetation units in the natural forest of Songnisan. We established the 250 sample points and collected the vegetation data of vertical distribution for each sample. A variety of multivariate statistical methods were applied to classify the forest types. The species diversity index were analyzed to estimate the stability and maturity for forest vegetation in each the type. The types were divided from two to ten clusters by cluster analysis. The appropriate number of clusters was estimated five clusters by indicator species analysis. It was verified through the multiple discriminant analysis that the estimated number of clusters had been suitable. Based on the species composition for each the type, this study site was classified into five forest types: 1) Quercus serrata and 2) mixed mesophytic forest in the valley area, 3) Q. mongolica forest in the main ridge, 4) Pinus densiflora forest in the sub-ridge extending from the main, and 5) Q. variabilis-P. densiflora forest between the sub-ridge and valley. The species diversity index of the pine forest that had been a simple species composition was the lowest while that of the mixed mesophytic forest of which the composition had been diverse was the highest. As the forest vegetation was more varied, the index showed a tendency to increase.

• Journal of Internet Computing and Services
• /
• v.7 no.1
• /
• pp.75-89
• /
• 2006

This paper is concerned with analysing the bankruptcy prediction power of three models: Multivariate Discriminant Analysis(MDA), Logit Analysis, Neural Network. The research targeted the bankrupted companies after the foreign exchange crisis in 1997 to differentiate from previous research efforts, and all participating companies were randomly selected from the KSE listed companies belonging to manufacturing industry 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 networks 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.