• Proceedings of the IEEK Conference
• /
• 2003.07e
• /
• pp.1767-1770
• /
• 2003

This paper proposes an algorithm that can reduce the estimation error of surface spectral-reflectance(SR) when using a conventional 3-band RGB camera. In the proposed method, the estimation error is reduced by using adaptive principle components (PCs) for each color region. To build an adaptive set of PCs, n SR populations are organized for n PC sets using the Lloyd quantizer design algorithm. The Macbeth Color Checker is utilized for the initial representative SR values for 1485 Munsell color chips as the total color population, then the Munsell chips arc divided into subsets with a set of corresponding adaptive PCs organized for each subset.

• Proceedings of the KIEE Conference
• /
• 2002.07d
• /
• pp.2272-2275
• /
• 2002

PCA(Principle Component Analysis) has emerged as a useful tool for process monitoring and fault diagnosis. The general approach requires the user to identify the root cause by interpreting the residual or principle components. This could be tedious and often impossible for a large process. In this paper, PCA scheme is combined with the FCM-based fault diagnostic algorithm to enhance the diagnosistic results. The implementation of the PCA-FCM based fault diagnostic system is done and its application is illustrated on the two-tank system.

• Journal of Sensor Science and Technology
• /
• v.9 no.2
• /
• pp.127-133
• /
• 2000

We propose a novel monitoring system for a recycling piggery slurry treatment system through neural networks. Here we tried to model treatment process for each tank(influent, fermentation, aeration, first sedimentation and fourth sedimentation tanks) in the system based on population densities of heterotrophic and lactic acid bacteria. Principle component analysis(PCA) was first applied to identify a relation between input(microbial densities and parameters for the treatment) and output, and then multilayer neural networks were employed to model the treatment process for each tank. PCA filtration of input data as microbial densities was found to facilitate the modeling procedure for the system monitoring even with a relatively lower number of input. Neural networks independently trained for each treatment tank and their subsequent combinatorial data analysis allowed a successful prediction of the treatment system for at least two days.

• Journal of the Korean Statistical Society
• /
• v.29 no.2
• /
• pp.231-245
• /
• 2000

This paper considers a linear regression model with space and time data in where the disturbances follow spatially correlated error components. We provide the best linear unbiased predictor for the one way error components. We provide the best linear unbiased predictor for the one way error component model with spatial autocorrelation. Further, we derive two diagnostic test statistics for the assessment of model specification due to spatial dependence and random effects as an application of the Lagrange Multiplier principle.

• Proceedings of the Korean Society for Noise and Vibration Engineering Conference
• /
• 2014.10a
• /
• pp.481-482
• /
• 2014

• Bulletin of the Society of Naval Architects of Korea
• /
• v.19 no.4
• /
• pp.1-10
• /
• 1982

An experimental investigation on the energy absorption of two staged combined structures is presented, which deals with the plastic collapse test as a series of research on soft bow structure involved in a ship collision. The principle of arithmetic superposition of energy absorption is derived upon experimental analysis and based upon the characteristics of the energy absorptions of component structures. This relationship is related to the further approach toward the design of soft bow.

• Interdisciplinary Bio Central
• /
• v.6 no.4
• /
• pp.3.1-3.10
• /
• 2014

Amino acid substitution matrices are essential tools for protein sequence analysis, homology sequence search in protein databases and multiple sequence alignment. The PAM matrix was the first widely used amino acid substitution matrix. The BLOSUM series then succeeded the PAM matrix. Most substitution matrixes were developed by using the statistical frequency of substitution between each amino acid at blocks representing groups of protein families or related proteins. However, substitution of amino acids is based on the similarity of physiochemical properties of each amino acid. In this study, a new approach was used to obtain major physiochemical properties in multiple sequence alignment. Frequency of amino acid substitution in multiple sequence alignment database and selected attributes of amino acids in physiochemical properties database were merged. This merged data showed the major physiochemical properties through principle components analysis. Using factor analysis, these four principle components were interpreted as flexibility of electronic movement, polarity, negative charge and structural flexibility. Applying these four components, BAPS was constructed and validated for accuracy. When comparing receiver operated characteristic ($ROC_{50}$) values, BAPS scored slightly lower than BLOSUM and PAM. However, when evaluating for accuracy by comparing results from multiple sequence alignment with the structural alignment results of two test data sets with known three-dimensional structure in the homologous structure alignment database, the result of the test for BAPS was comparatively equivalent or better than results for prior matrices including PAM, Gonnet, Identity and Genetic code matrix.

• KOREAN JOURNAL OF CROP SCIENCE
• /
• v.57 no.1
• /
• pp.83-88
• /
• 2012

In order to get information on tocopherol content and composition in fifty-six soybean germplasms were evaluated by HPLC. From the principle component analysis, the first three components accounted for 71.6% of the total variance of tocopherol content in the germplasms. Principal component 1 showed significant correlations with all the morphological markers except 100-seed weight. Soybean germplasms were divided into three groups by the first two principal components. The highest content of ${\alpha}$-tocopherol was $38.6{\mu}g$ per g in Tanner, while that of ${\gamma}$-tocopherol was $195.6{\mu}g$ in PI 91073. In case of ${\delta}$-tocopherol, IT 105622 showed the highest value as $29.8{\mu}g$. The contents of tocopherol were gradually increased from the late August to late September, which was 10 days before maturity, in Alchankong and PI 96322. The tocopherol content was higher in seeds from the plants sown early than those sown late. Total tocopherol contents of PI 96188, Geomjeongkong 2, and Suwon 183 grown in Gimje were higher than those grown in Iksan, but the difference was not observed in PI 96322. These results suggest that the contents of tocopherol in soybean were affected not only by the genotypes but also by environment.

• International Journal of Contents
• /
• v.8 no.1
• /
• pp.23-29
• /
• 2012

Multiple expression levels of genes obtained using time series microarray experiments have been exploited effectively to enhance understanding of a wide range of biological phenomena. However, the unique nature of microarray data is usually in the form of large matrices of expression genes with high dimensions. Among the huge number of genes presented in microarrays, only a small number of genes are expected to be effective for performing a certain task. Hence, discounting the majority of unaffected genes is the crucial goal of gene selection to improve accuracy for disease diagnosis. In this paper, a non-Gaussian weight matrix obtained from an incremental model is proposed to extract useful features of multivariate time series microarrays. The proposed method can automatically identify a small number of significant features via discovering hidden variables from a huge number of features. An unsupervised hierarchical clustering representative is then taken to evaluate the effectiveness of the proposed methodology. The proposed method achieves promising results based on predictive accuracy of clustering compared to existing methods of analysis. Furthermore, the proposed method offers a robust approach with low memory and computation costs.

• Journal of the Korean Society for Precision Engineering
• /
• v.20 no.3
• /
• pp.149-156
• /
• 2003

The estimation of fatigue limit for the component with complicated shape is difficult than of standard fatigue specimen, due to complex test equipment. So, we substitute maximum principle stress from FEM results for fatigue limit diagram made by standard fatigue specimen. Then we can estimate endurance safety of component with high trust. The static stress analysis, the nonlinear contact stress analysis and the model analysis for turbine blade is performed by ANSYS ver. 5.6. the comparison of maximum static stress around hole with maximum contact stress between pun and hole can make the cause of fracture for turbine blade clear. The difference of fatigue limit between fatigue test by standard specimen and in-service mechanical components is due to surface roughness and machining condition etc. In in-service mechanical components, Goodman diagram has to consider surface roughness for failure analysis. To find fracture mechanism of torison-mounted blade in nuclear plant. This study performs the static stress, the nonlinear contact stress and the modal analysis on torison-mounted blade with finite element method and makes the estimation for safety of turbine blade.