• Communications for Statistical Applications and Methods
• /
• v.8 no.3
• /
• pp.625-632
• /
• 2001

Principal component analysis(PCA) is a multivariate technique falling under the general title of factor analysis. The purpose of PCA is to Identify the dependence structure behind a multivariate stochastic observation In order to obtain a compact description of it. In engineering field PCA is utilized mainly (or data compression and restoration. In this paper we propose a new robust Hebbian algorithm for robust PCA. This algorithm is based on a hyperbolic tangent function due to Hampel ef al.(1989) which is known to be robust in Statistics. We do two experiments to investigate the performance of the new robust Hebbian learning algorithm for robust PCA.

• International Journal of Fuzzy Logic and Intelligent Systems
• /
• v.12 no.1
• /
• pp.1-5
• /
• 2012

Data reduction has been used widely in data mining for convenient analysis. Principal component analysis (PCA) and factor analysis (FA) methods are popular techniques. The PCA and FA reduce the number of variables to avoid the curse of dimensionality. The curse of dimensionality is to increase the computing time exponentially in proportion to the number of variables. So, many methods have been published for dimension reduction. Also, data augmentation is another approach to analyze data efficiently. Support vector machine (SVM) algorithm is a representative technique for dimension augmentation. The SVM maps original data to a feature space with high dimension to get the optimal decision plane. Both data reduction and augmentation have been used to solve diverse problems in data analysis. In this paper, we compare the strengths and weaknesses of dimension reduction and augmentation for classification and propose a classification method using data reduction for classification. We will carry out experiments for comparative studies to verify the performance of this research.

• Proceedings of the Korean Society of Broadcast Engineers Conference
• /
• 2016.11a
• /
• pp.82-84
• /
• 2016

We propose a new reliable SVD-based watermarking scheme having high fidelity and strong robustness with no false-positive problem. Each column of the principal component of a watermark image is embedded into singular values of LL, LH, HL and HH sub-bands of cover image with different scale factors. Each scale factor is optimized by trading-off fidelity and robustness using Differential Evolution (DE) algorithm. The proposed scheme improves fidelity and robustness of existing reliable SVD based watermarking schemes without any false-positive problem. Index Terms - watermarking, reliable SVD, DWT, principal component, Differential Evolution.

• Korea Trade Review
• /
• v.47 no.4
• /
• pp.1-14
• /
• 2022

This study examines the impact of trade facilitation on China's trade for the period 2010-2017 using a gravity model with a measurement of APEC trade facilitation through principal component analysis. The empirical results confirmed that trade facilitation was a key factor to have a positive effect on Chinese exports and that the higher the level of trade facilitation in APEC countries, the more positive the increase in exports and quantities with China. Further, the size of the economy, the total population, and the border between the trading partner had a positive effect on Chinese trade volume. To promote economic growth through increase in trade volume, countries should actively improve trade facilitation and participate in global trade facilitation reform through continuous cooperation with trading partners.

• Journal of the Institute of Electronics Engineers of Korea SP
• /
• v.43 no.2 s.308
• /
• pp.82-86
• /
• 2006

The design of a pattern recognition system generally involves the three aspects: preprocessing, feature extraction, and decision making. Among them, a feature extraction method determines an appropriate subspace of dimensionality in the original feature space of dimensionality so that it can reduce the complexity of the system and help to improve successful recognition rates. Linear transforms, such as principal component analysis, factor analysis, and linear discriminant analysis have been widely used in pattern recognition for feature extraction. This paper shows that singular value decomposition (SVD) can be applied usefully in feature extraction stage of pattern recognition. As an application, a remote sensing problem is applied to verify the usefulness of SVD. The experimental result indicates that the feature extraction using SVD can improve the recognition rate about 25% compared with that of PCA.

• The Journal of Korean Physical Therapy
• /
• v.1 no.1
• /
• pp.63-72
• /
• 1989

The present study was designed to investigate the general characteristics of pain patients and to analyze the properties of Korean pain expression terms as a preliminary step in the development of a pain questionnaire. Questionnaires were administered to 73 adult patients (53 males, 20 females) with knee, ankle, neck, low back, and shoulder pain. The mean duration of pain was 16.2 months (SE=3.3). The results were as fellows : 1. The data show that there are over 30 words in the Korean language to describe the varieties of pain experience even within this small sample. 2, There was low significant relationship between present pain intensity using visual analogue scale and the selected numbers of pain words from the pain questionnaire (p<.01). 3. In order to separate basic factors, a principal component analysis with varimax rotation was performed. The principal component analysis produced 8 factors. The proportion of variance explained by these factors was $71.0\%$. The first factor accounting $26.8\%$ of the variance was labeled 'cruelty and fear related pain' ; second 'pain produced from deep tissue' : third 'skin-punctuating related pain' ; and fourth 'miscellaneous and complicated pain'. Results of this study might be utilitzed in developing a pain questionnaire for pain patients.

• Journal of Korean Society of Water and Wastewater
• /
• v.29 no.6
• /
• pp.625-632
• /
• 2015

The study of water environment system using a multivariate analysis in Changnyeong-Haman weir section has been conducted. The purpose of this study is to establish better understanding related water qualities in the Changnyeong-Haman weir section which can provide useful information. The data were consisted of water quality data and algae data including WT(water temperature), pH, DO, EC, COD, SS, T-N, $NH_3-N$, T-P, $PO_4-P$, Chl-a, TOC, d-silica, t-silica, Cyanobacteria, Diatoms, and Green algae. Statistical analyses used in this study were correlation analysis, principal components, and factor analysis. According to correlation analysis on COD and TOC, it revealed that the each value of correlation coefficient was 0.843. On the other result, a negative correlation was observed between diatoms and d-silica. Furthermore, the results of principal component analysis to the overall water quality were classified into four main factors with contribution rate 81.071%.

• Korean Journal of Microbiology
• /
• v.27 no.4
• /
• pp.391-397
• /
• 1989

Population of Aeromonas and environmental parameters were investigated at three sites from August 1986, to December, 1986 in Naktong Estuary. The variation range of Aeromonas was $4.3\times10^{2}-4.6\times 10^{4}$ MPN/100ml. The result of ANOVA indicates significant differences among the populations of Aeromonas in each site. The highest population of Aeromonas occurred at site 2, and the lowest at site 3-B. To scrutinize the effects of environmental parameters on the distribution of Aeromonas spp, principal component analysis and multiple stepwise regression were used. The results showed that distribution of Aeromonas spp. was mainly influenced by outflow of freshwater and inflow of inorganic nutrients and correlated with heterotrophic bacteria, available nitrogen, fecal coliform bacteria, and temperature.

• Journal of Korean Society for Atmospheric Environment
• /
• v.10 no.E
• /
• pp.343-356
• /
• 1994

In this study, a statistical investigation was carried out for the evaluation of any relationship between polycyclic aromatic hydrocarbons (PAHss) associated with ambient aerosols and other air quality parameters under varying meteorological conditions. Daily measurements for PAHs and air quality/meteorological parameters were selected from a data-base constructed by a comprehensive air monitoring in London during 1985-1987. Correlation coefficients were calculated to examine any significant relationship between the PAHs and other individual variables. Statistical analysis was further Performed for the air quality/meteorological data set using a principal component analysis to derive important factors inherent in the interactions among the variables. A total of six components were identified, representing vehicle emission, photochemical activity/volatilization, space heating, atmospheric humidity, atmospheric stability, and wet deposition. It was found from a stepwise multiple regression analysis that the vehicle emission component is overall the most important factor contributing to the variability of PAHs concentrations at the monitoring site. The photochemical activity/volatilzation component appeared to be also an important factor particularly for the lower molecular weight PAHs. In general, the space heating component was found to be next important factor, while the contributions of other three components to the variance of each PAHs did not appear to be as much important as the first three components in most cases. However, a consistency for these components in their negative correlations with PAHs data was found, indicating their roles in the depletion of PAHs concentrations in the urban atmosphere.

• Journal of Distribution Science
• /
• v.13 no.9
• /
• pp.103-112
• /
• 2015

Purpose - This paper aims to provide a step-by-step approach to factor analytic procedures, such as principal component analysis (PCA) and exploratory factor analysis (EFA), and to offer a guideline for factor analysis. Authors have argued that the results of PCA and EFA are substantially similar. Additionally, they assert that PCA is a more appropriate technique for factor analysis because PCA produces easily interpreted results that are likely to be the basis of better decisions. For these reasons, many researchers have used PCA as a technique instead of EFA. However, these techniques are clearly different. PCA should be used for data reduction. On the other hand, EFA has been tailored to identify any underlying factor structure, a set of measured variables that cause the manifest variables to covary. Thus, it is needed for a guideline and for procedures to use in factor analysis. To date, however, these two techniques have been indiscriminately misused. Research design, data, and methodology - This research conducted a literature review. For this, we summarized the meaningful and consistent arguments and drew up guidelines and suggested procedures for rigorous EFA. Results - PCA can be used instead of common factor analysis when all measured variables have high communality. However, common factor analysis is recommended for EFA. First, researchers should evaluate the sample size and check for sampling adequacy before conducting factor analysis. If these conditions are not satisfied, then the next steps cannot be followed. Sample size must be at least 100 with communality above 0.5 and a minimum subject to item ratio of at least 5:1, with a minimum of five items in EFA. Next, Bartlett's sphericity test and the Kaiser-Mayer-Olkin (KMO) measure should be assessed for sampling adequacy. The chi-square value for Bartlett's test should be significant. In addition, a KMO of more than 0.8 is recommended. The next step is to conduct a factor analysis. The analysis is composed of three stages. The first stage determines a rotation technique. Generally, ML or PAF will suggest to researchers the best results. Selection of one of the two techniques heavily hinges on data normality. ML requires normally distributed data; on the other hand, PAF does not. The second step is associated with determining the number of factors to retain in the EFA. The best way to determine the number of factors to retain is to apply three methods including eigenvalues greater than 1.0, the scree plot test, and the variance extracted. The last step is to select one of two rotation methods: orthogonal or oblique. If the research suggests some variables that are correlated to each other, then the oblique method should be selected for factor rotation because the method assumes all factors are correlated in the research. If not, the orthogonal method is possible for factor rotation. Conclusions - Recommendations are offered for the best factor analytic practice for empirical research.