• Proceedings of the Korea Water Resources Association Conference
• /
• 2008.05a
• /
• pp.694-698
• /
• 2008

In hydrology, it is a difficult task to deal with multivariate time series such as modeling streamflows of an entire complex river system. Normal distribution based model such as MARMA (Multivariate Autorgressive Moving average) has been a major approach for modeling the multivariate time series. There are some limitations for the normal based models. One of them might be the unfavorable data-transformation forcing that the data follow the normal distribution. Furthermore, the high dimension multivariate model requires the very large parameter matrix. As an alternative, one might be decomposing the multivariate data into independent components and modeling it individually. In 1985, Lins used Principal Component Analysis (PCA). The five scores, the decomposed data from the original data, were taken and were formulated individually. The one of the five scores were modeled with AR-2 while the others are modeled with AR-1 model. From the time series analysis using the scores of the five components, he noted "principal component time series might provide a relatively simple and meaningful alternative to conventional large MARMA models". This study is inspired from the researcher's quote to develop a multivariate simulation model. The multivariate simulation model is suggested here using Principal Component Analysis (PCA) and Independent Component Analysis (ICA). Three modeling step is applied for simulation. (1) PCA is used to decompose the correlated multivariate data into the uncorrelated data while ICA decomposes the data into independent components. Here, the autocorrelation structure of the decomposed data is still dominant, which is inherited from the data of the original domain. (2) Each component is resampled by block bootstrapping or K-nearest neighbor. (3) The resampled components bring back to original domain. From using the suggested approach one might expect that a) the simulated data are different with the historical data, b) no data transformation is required (in case of ICA), c) a complex system can be decomposed into independent component and modeled individually. The model with PCA and ICA are compared with the various statistics such as the basic statistics (mean, standard deviation, skewness, autocorrelation), and reservoir-related statistics, kernel density estimate.

• The Journal of the Korea institute of electronic communication sciences
• /
• v.8 no.9
• /
• pp.1299-1305
• /
• 2013

In this paper, we investigate a method of reducing the computational cost in speech recognition by dimensionality reduction of MFCC feature vectors. Eigendecomposition of the feature vectors renders linear transformation of the vectors in such a way that puts the vector components in order of variances. The first component has the largest variance and hence serves as the most important one in relevant pattern classification. Therefore, we might consider a method of reducing the computational cost and achieving no degradation of the recognition performance at the same time by dimensionality reduction through exclusion of the least-variance components. Experimental results show that the MFCC components might be reduced by about half without significant adverse effect on the recognition error rate.

• Journal of Ginseng Research
• /
• v.42 no.3
• /
• pp.277-287
• /
• 2018

Background: Temperature is an essential condition in red ginseng processing. The pharmacological activities of red ginseng under different steam temperatures are significantly different. Methods: In this study, an ultrahigh-performance liquid chromatography quadrupole time-of-flight tandem mass spectrometry was developed to distinguish the red ginseng products that were steamed at high and low temperatures. Multivariate statistical analyses such as principal component analysis and supervised orthogonal partial least squared discrimination analysis were used to determine the influential components of the different samples. Results: The results showed that different steamed red ginseng samples can be identified, and the characteristic components were 20-gluco-ginsenoside Rf, ginsenoside Re, ginsenoside Rg1, and malonyl-ginsenoside Rb1 in red ginseng steamed at low temperature. Meanwhile, the characteristic components in red ginseng steamed at high temperature were 20R-ginsenoside Rs3 and ginsenoside Rs4. Polar ginsenosides were abundant in red ginseng steamed at low temperature, whereas higher levels of less polar ginsenosides were detected in red ginseng steamed at high temperature. Conclusion: This study makes the first time that differences between red ginseng steamed under different temperatures and their ginsenosides transformation have been observed systematically at the chemistry level. The results suggested that the identified chemical markers can be used to illustrate the transformation of ginsenosides in red ginseng processing.

• Proceedings of the Korean Society of Broadcast Engineers Conference
• /
• 2009.01a
• /
• pp.703-708
• /
• 2009

The present paper describes the application of an improved impression transfer vector method (Sakurai et al., 2007) to transform the three basic dimensions (Evaluation, Activity, and Potency) of higher-order impression. First, a set of shapes and surface textures of faces was represented by multi-dimensional vectors. Second, the variation among faces was coded in reduced parameters derived by applying principal component analysis. Third, a facial attribute along a given impression dimension was analyzed to select discriminative parameters from among principal components with higher sensitivity to impressions, and obtain an impression transfer vector. Finally, the parametric coordinates were changed by adding or subtracting the impression transfer vector and the image was manipulated so that its facial appearance clearly exhibits the transformed impression. A psychological rating experiment confirmed that the impression transfer vector modulated three dimensions of higher-order impression. We discussed the versatility of the impression transfer vector method.

• Journal of Institute of Control, Robotics and Systems
• /
• v.12 no.6
• /
• pp.568-572
• /
• 2006

This paper presents the device of recognizing image of the studded paving blocks, transmitting, the information by vibration to a visually handicapped person. Usually the blind uses the walking stick to recognize the studded paving block. This research uses a PCA (Principal Component Analysis) based image processing approach for recognizing the paving blocks. We classify the studded paving blocks into 5 classes, that is, vertical line block, right-declined line block, left-declined line block, dotted block and flat block. The 8 images for each of 5 classes are captured for each block by 112*120 pixels, then the eigenvectors are obtained in magnitude order of eigenvectors by using principal component analysis. The principal components for images can be calculated using projection of transformation matrix composed of eigenvectors. The classification has been executed using Euclidean's distance, so the block having minimum distance with a image is chosen as matched one. The result of classification is transmitted to the blind by electric vibration signals with different magnitudes and frequencies.

• Spatial Information Research
• /
• v.10 no.3
• /
• pp.481-492
• /
• 2002

The severity and spatial Patterns of spring drought on the croplands arc investigated using satellite imagery(Landsat ETM+). It is necessary to analyze the area droughty conditions in order to decrease the damage and make the efficient policies. In this context, the information about soil moisture levels, which were fatal factors to the crop growth, was acquired from wetness calculated from Tasseled cap transformation. We confirmed that the wetness values have a strong correlation with NDVI and the principal components. The result showed that the intensity of vegetation covering the surface could be understood as the index of the impacts of drought on croplands and these relationships were effective to classify dry areas in satellite imagery.

• Proceedings of the Polymer Society of Korea Conference
• /
• 2006.10a
• /
• pp.355-355
• /
• 2006

In this study, we have applied principal component analysis-based 2D (PCA2D) correlation spectroscopy to the temperature-dependent IR spectra of biodegradable poly(hydroxyalkanoate). PCA2D analysis reveals clearly that there are two components in crystalline band of C=O stretching mode without being hampered by noise. To better understand the thermal behavior of biodegradable poly(hydroxyalkanoate), eigenvalue manipulating transformation (EMT) technique was also employed. By uniformly lowering the power of a set of eigenvalues associated with the original data, the subtle contributions from minor eigenvectors are highlighted. Details of thermal behavior of biodegradable poly(hydroxyalkanoate) studied by PCA2D correlation spectroscopy with EMT will be discussed.

• Proceedings of the Korean Information Science Society Conference
• /
• 2006.06a
• /
• pp.4-6
• /
• 2006

Tree-dependent component analysis (TCA) is a generalization of independent component analysis (ICA), the goal of which is to model the multivariate data by a linear transformation of latent variables, while latent variables fit by a tree-structured graphical model. In contrast to ICA, TCA allows dependent structure of latent variables and also consider non-spanning trees (forests). In this paper, we present a TCA-based method of clustering gene expression data. Empirical study with yeast cell cycle-related data, yeast metaboiic shift data, and yeast sporulation data, shows that TCA is more suitable for gene clustering, compared to principal component analysis (PCA) as well as ICA.

• Journal of Korean Society for Atmospheric Environment
• /
• v.16 no.1
• /
• pp.11-22
• /
• 2000

Polycyclic aromatic hydrocarbons(PAHs) have known as potentially hazardous air pollutants(HAPs0 to human health because of its carcinogenic and mutagenic behaviors. The purpose of this study was to determine the level of 6 PAHs(Fluoranthene, Pyrene, Benzo[a]anthracene, Chrysene, Benzo[b]fluoranthene, and Benzo[a]pyrene) as well as 10 inorganic elements(Cr, Na, K, Zn, Pb, Fe, Cu, Ti, Al and Cd) in the ambient PM-10. The total of 115 samples had been collected from February, 1996 to June, 1996 on quartz fiber by a PM-10 high volume air sampler near the Yong-Tong Apartment complexes. A statistical analysis was performed for the PAHs and inorganic elements data set using a principal component analysis in order to identify qualitatively the potential sources of PM-10. A total of 6 principal components were separated by intensive data pretrement and transformation processes, such as soil, refuse incineration, oil burning, coal burning, field burning, vehicle emission sources. The results showed that PAHs were associated with various burning activities like refuse and field burning, coal burning, and oil burning emissions in the study area. These derived sources were well matched with the previously known source profiles in terms of compositonal order and level of measured species. The combination data set consisted of both organic and inorganic species might provide more powerful source signature and might increase the number of potentially derived sources than PAHs or inorganic data alone.

• Parasites, Hosts and Diseases
• /
• v.53 no.5
• /
• pp.553-559
• /
• 2015

Research on micro-level assessment of the changes of socio-economic status following health interventions is very scarce. The use of household asset data to determine wealth indices is a common procedure for estimating socio-economic position in resource poor settings. In such settings information about income is usually lacking, and the collection of individual consumption or expenditure data would require in-depth interviews, posing a considerable risk of bias. In this study, we determined the socio-economic status of 213 households in a community population in an island in the north-western Tanzania before and 3 year after implementation of a participatory hygiene and sanitation transformation (PHAST) intervention to control schistosomiasis and intestinal worm infections. We constructed a household 'wealth index' based housing construction features (e.g., type of roof, walls, and floor) and durable assets ownership (e.g., bicycle, radio, etc.). We employed principal components analysis and classified households into wealth quintiles. The study revealed that asset variables with positive factor scores were associated with higher socio-economic status, whereas asset variables with negative factor scores were associated with lower socio-economic status. Overall, households which were rated as the poorest and very poor were on the decrease, whereas those rated as poor, less poor, and the least poor were on the increase after PHAST intervention. This decrease/increase was significant. The median shifted from -0.4376677 to 0.5001073, and the mean from -0.2605787 (SD; 2.005688) to 0.2605787 (SD; 1.831199). The difference in socio-economic status of the people between the 2 phases was highly statistically significant (P<0.001). We argue that finding of this study should be treated with caution as there were other interventions to control schistosomiasis and intestinal worm infections which were running concurrently on Kome Island apart from PHAST intervention.