• The Korean Journal of Applied Statistics
• /
• v.34 no.2
• /
• pp.127-139
• /
• 2021

Independent Component Analysis is a popular statistical method to separate independent signals from the mixed data, and Group Independent Component Analysis is an its multi-subject extension of Independent Component Analysis. It has been applied Functional Magnetic Resonance Imaging data and provides promising results. However, classical Group Independent Component Analysis works poorly when outliers exist on data which is frequently occurred in Magnetic Resonance Imaging scanning. In this study, we propose a robust version of the Group Independent Component Analysis based on ROBPCA. Through the numerical studies, we compare proposed method to the conventional method, and verify the robustness of the proposed method.

• The Korean Journal of Applied Statistics
• /
• v.30 no.6
• /
• pp.889-899
• /
• 2017

Independent component analysis is a multivariate approach to separate mixed signals into original signals. It is the most widely used method of blind source separation technique. ICA uses linear transformations such as principal component analysis and factor analysis, but differs in that ICA requires statistical independence and non-Gaussian assumptions of original signals. PCA have a natural ordering based on cumulative proportion of explained variance; howerver, ICA algorithms cannot identify the unique optimal ordering of the components. It is meaningful to set order because major components can be used for further analysis such as clustering and low-dimensional graphs. In this paper, we compare the performance of several criteria to determine the order of the components. Kurtosis, absolute value of kurtosis, negentropy, Kolmogorov-Smirnov statistic and sum of squared coefficients are considered. The criteria are evaluated by their ability to classify known groups. Two types of data are analyzed for illustration.

• Proceedings of the Korean Institute of Intelligent Systems Conference
• /
• 2006.05a
• /
• pp.401-404
• /
• 2006

본 논문에서는 영상의 중심이동과 독립성분분석에 의한 효율적인 표정 인식방법을 제안하였다. 여기서 중심이동은 얼굴영상의 1차 모멘트에 의한 전처리 과정으로 불필요한 배경을 배제시켜 계산시간의 감소 및 인식률을 개선하기 위함이다. 또한 독립성분분석은 얼굴표정의 특징으로 기저영상을 추출하는 것으로 고차의 통계성을 고려한 중복신호의 제거로 인식성능을 개선하기 위함이다. 제안된 방법을 320*243 픽셀의 48개(4명*6장*2그룹) 표정을 대상으로 Euclidean 분류척도를 이용하여 실험한 결과, 전처리를 수행치 않는 기존방법에 비해 우수한 인식성능이 있음을 확인하였다.

• Korean Journal of Food Science and Technology
• /
• v.28 no.6
• /
• pp.1171-1176
• /
• 1996

The changes in volatiles of the model system were analyzed by GC and GC-MS before and after retorting. The GC data were analyzed statistically by applying the analysis of variance, and 42 peaks were selected at 5% significance level. Multivariate statistical analysis was performed with these 42 peaks as independent variables. Through the stepwise discriminant analysis, 8 peaks, which corresponded to the compounds such as 2-heptanone, cis-3-hexenal, 2-pentyl-furan, 1-methyl-trans-1,2-cyclohexanediol, 2-hexanone, 3-octanone, trans, trans-nona-2,4-dienal and 1-octen-3-ol, were obtained in sequence to distinguish the samples with and without retorting. The principal component analysis of a set of 8 independent variables resulted in 3 principal components which accounted for 96.1% of the variance, while the first principal component (PC 1) explained 76.5% of the total variance. In addition, through the factor analysis of the principal components, the peaks 11, 20 and 21 could be grouped togather in accordance with the direction and the size while the peaks 9, 33 and 39 constituted the second group in the direction.

• KIPS Transactions on Software and Data Engineering
• /
• v.11 no.1
• /
• pp.41-50
• /
• 2022

In this paper, a method to directly calculate the major elements of skin color such as melanin and hemoglobin from the RGB signal of the camera is proposed. The main elements of skin color typically measure spectral reflectance using specific equipment, and reconfigure the values at some wavelengths of the measured light. The values calculated by this method include such things as melanin index and erythema index, and require special equipment such as a spectral reflectance measuring device or a multi-spectral camera. It is difficult to find a direct calculation method for such component elements from a general digital camera, and a method of indirectly calculating the concentration of melanin and hemoglobin using independent component analysis has been proposed. This method targets a region of a certain RGB image, extracts characteristic vectors of melanin and hemoglobin, and calculates the concentration in a manner similar to that of Principal Component Analysis. The disadvantage of this method is that it is difficult to directly calculate the pixel unit because a group of pixels in a certain area is used as an input, and since the extracted feature vector is implemented by an optimization method, it tends to be calculated with a different value each time it is executed. The final calculation is determined in the form of an image representing the components of melanin and hemoglobin by converting it back to the RGB coordinate system without using the feature vector itself. In order to improve the disadvantages of this method, the proposed method is to calculate the component values of melanin and hemoglobin in a feature space rather than an RGB coordinate system using a feature vector, and calculate the spectral reflectance corresponding to the skin color using a general digital camera. Methods and methods of calculating detailed components constituting skin pigments such as melanin, oxidized hemoglobin, deoxidized hemoglobin, and carotenoid using spectral reflectance. The proposed method does not require special equipment such as a spectral reflectance measuring device or a multi-spectral camera, and unlike the existing method, direct calculation of the pixel unit is possible, and the same characteristics can be obtained even in repeated execution. The standard diviation of density for melanin and hemoglobin of proposed method was 15% compared to conventional and therefore gives 6 times stable.

• Economic and Environmental Geology
• /
• v.35 no.2
• /
• pp.137-147
• /
• 2002

Natural geological and environmental processes reflect to element abundances in geological materials on the surface. This study aims to elucidate a possibility of geostatistical application to differentiate geochemical anomalies affected by anthropogenic and geogenic factors. A regional geochemical map was produced using 'inverse distance weight interpolation' method for analytical results of stream sediments «150 11m) which were collected from 2,290 first- to second-order streams over the whole Gyeonggi Province. The Jurassic granitic batholith in the southeastern province was selected as a target for the geostatistical examination. Factor analysis was conducted using 22 elements for stream sediments from 445 drainage basins over the granitic body. Co, Cr, Sc, MgO, Fe$_{2}$O$_{3}$, V, and Ni were grouped with high correlation coefficients and the depletion of the components may reflect the whole-rock chemistry of the granite. Regression analysis was done using Co, Cr, and Sc as dependent variables and other six components as independent variables, and the results were drawn as maps. The maps acquired generally show quite similar distribution patterns with those of concentrations of each variable. The similarity in the spatial patterns between the two maps indicates that the application of regression statistics can be valid for the interpretation of regional geochemical data. However, some components show local discrepancies which may be influenced by secondary factors regardless of the basement lithology. The regression analysis may be effective in extracting local geochemical anomalies which may reflect rather anthropogenic pollutions than geogenic influences.

• Journal of the Korean Society of Food Science and Nutrition
• /
• v.43 no.6
• /
• pp.916-925
• /
• 2014

The purpose of this study was to compare dietary and lifestyle habits in middle-aged women based on their self-perceived health-related physical fitness (SPF) level as well as investigate the effects of dietary and lifestyle habits on SPF. The study subjects were divided into two groups, 'High' group (${\geq}3.2$, n=64) and 'Low' group (<3.2, n=69), based on average SPF value (3.2). Women in the 'High' group showed a greater lean mass (P<0.05), whereas women in the 'Low' group had higher triglycerides (P<0.05). In analyzing characteristics of lifestyle habits, it was found that the 'High' group showed significantly higher scores for 'vitality level (P<0.001)', 'self-rated health status (P<0.001)', 'regular medical checkups (P<0.05)', and 'regular exercise (P<0.05)'. The average score for dietary habits was significantly high in the 'High' group (P<0.05). Furthermore, ordinary dietary habits showed a significant positive correlation (P<0.001) with SPF in the regression analysis after adjusting for disturbance factors. From these results, ordinary desirable dietary habits were shown to be an important factors having positive effects SPF. Therefore, healthy dietary and lifestyle habits should be practiced to improve the SPF of middle-aged women. For this purpose, related educational programs should be developed for the middle-aged women to take interest in their dietary habits.