• Horticulture, Environment, and Biotechnology : HEB
• /
• v.59 no.6
• /
• pp.919-927
• /
• 2018

To compare the antioxidant properties and flavonols in various parts; dry skin (DS) and edible portion (EP), of 8 red onions (Allium cepa L, ROs), total content of phenolics (TPC), flavonoids (TFC), and anthocyanins (TAC) and DPPH radical scavenging properties were estimated and the content of six flavonols were quantified by HPLC-PDA analysis. The major component of DS and EP of RO was quercetin and quercetin-4'-glucoside, respectively. Score plots of the PCA and PLS-DA were segregated by flavonols content and antioxidant properties according to the EP and DS of ROs. Loading plot of the PCA showed that the quercetin and sum of flavonol content were highly correlated with antioxidant activity of ROs. Therefore, flavonol content and antioxidant activity can be used as markers for distinct parts of ROs.

• Journal of the Korean Society of Manufacturing Process Engineers
• /
• v.19 no.9
• /
• pp.47-52
• /
• 2020

With the 4th industrial revolution, condition monitoring using machine learning techniques has become popular among researchers. An overload due to complex operations causes several irregularities in MOSFETs. This study investigated the acquired voltage to analyze the overcurrent effects on MOSFETs using a failure mode effect analysis (FMEA). The results indicated that the voltage pattern changes greatly when the current is beyond the threshold value. Several features were extracted from the collected voltage signals that indicate the health state of a switched-mode power supply (SMPS). Then, the data were reduced to a smaller sample space by using a principal component analysis (PCA). A robust machine learning algorithm, the support vector machine (SVM), was used to classify different health states of an SMPS, and the classification results are presented for different parameters. An SVM approach assisted by a PCA algorithm provides a strong fault diagnosis framework for an SMPS.

• The Journal of the Acoustical Society of Korea
• /
• v.30 no.6
• /
• pp.330-336
• /
• 2011

In this paper, we propose a new method to improve the performance of supervector linear kernel SVM (Support Vector Machine) for speaker identification. This method is based on splitting one training datum into several pieces of utterances. We use four different databases for evaluating performance and use PCA (Principal Component Analysis), GKPCA (Greedy Kernel PCA) and KMDA (Kernel Multimodal Discriminant Analysis) for feature enhancement. As a result, the proposed method shows improved performance for speaker identification using supervector linear kernel SVM.

• Smart Media Journal
• /
• v.12 no.3
• /
• pp.30-37
• /
• 2023

Alzheimer's disease (AD) symptoms are being treated by early diagnosis, where we can only slow the symptoms and research is still undergoing. In consideration, using T1-weighted images several classification models are proposed in Machine learning to identify AD. In this paper, we consider the improvised feature selection, to reduce the complexity by using wrapping techniques and Restricted Boltzmann Machine (RBM). This present work used the subcortical and cortical features of 278 subjects from the ADNI dataset to identify AD and sMRI. Multi-class classification is used for the experiment i.e., AD, EMCI, LMCI, HC. The proposed feature selection consists of Forward feature selection, Backward feature selection, and Combined PCA & RBM. Forward and backward feature selection methods use an iterative method starting being no features in the forward feature selection and backward feature selection with all features included in the technique. PCA is used to reduce the dimensions and RBM is used to select the best feature without interpreting the features. We have compared the three models with PCA to analysis. The following experiment shows that combined PCA &RBM, and backward feature selection give the best accuracy with respective classification model RF i.e., 88.65, 88.56% respectively.

• Journal of Korean Society for Atmospheric Environment
• /
• v.22 no.E2
• /
• pp.57-68
• /
• 2006

Four intensive seasonal sampling campaigns between October 1998 and October 1999 were undertaken at an urban site of Chongju, in which polyurethane foam (PUF) sampler was used to collect particulate- and vapor-phase polycyclic aromatic hydrocarbons (PAHs). The contribution to total (particulate+vapor) PAH concentration by the vapor phase component exceeded the particulate phase contribution by factor of ${\sim}2.6$. Summed concentrations of phenanthrene (30.9%), pyrene (16.6%), naphthalene (11.3%) and fluoranthene (11.0%) account for significant amounts of the vapor-phase, while chrysene (12.5%), benzo[b]fluoranthene (11.6%), indeno[123-cd]pyrene (9.9%), benzo[ghi]perylene (9.5%), benzo[k]fluoranthene (9.4%), pyrene (8.9%), and benzo[a]pyrene (8.3%) are found to be the most common PAH compounds in the particulate phase. The results from application of principal component analysis to particulate-phase PAH data demonstrate that a combination of PAH and $PM_{2.5}$ inorganic data is a more powerful tracer of emission sources than PAH species data alone. Particulate-phase PAH species were found to be associated predominantly with emissions from diesel engine vehicles and incineration.

• Journal of Environmental Health Sciences
• /
• v.42 no.5
• /
• pp.302-313
• /
• 2016

Objectives: This study was conducted to assess environmental health status on a local scale using environmental health-related indicators. It demonstrated the possibility of using a structural equation model, a methodological approach to provide synthesized information. Methods: Eighteen indicators were selected from official statistical data published by local governments. Each environmental health-related indicator was classified according to the PSR (pressure-state-response) model. Aggregation methods were performed using principal component analysis and fuzzy sets. Results: The five principal components were classified through principal component analysis (PCA) and obtained eigenvalues >1.0 from the initial 18 indicators. The aggregated index was obtained by condensing the original information into two broad and simple categories through fuzzy sets. Conclusion: This could be useful in that the aggregation procedure may provide a basis for establishing environmental health policies and a decision-making process. However, the availability and quality of indicators, assessment of aggregation method bias, choice of weighted scores for indicators, and other factors should be examined in future studies.

• Journal of Korea Multimedia Society
• /
• v.9 no.4
• /
• pp.414-420
• /
• 2006

Online character recognition techniques have been applied in many new fields of PDA, Tablet PC etc. But the recognition techniques can not use such high technologies naturally yet. Hidden Markov Model (HMM) that is much used recently requires high memory space and complex computational tasks because of comparing the input data with entire standard patterns. In this paper we propose a method to recognize the online characters more efficiently. At first we create chain-codes of learning data and recognition data in preprocessing phase, and then we compress dimensions of data using Principal Component Analysis (PCA) and recognize a character compressed data in recognition phrase. Validity of proposed method .is verified. by experiment results.

• Journal of Pharmaceutical Investigation
• /
• v.39 no.1
• /
• pp.43-49
• /
• 2009

Aspirin or acetylsalicylic acid, a member of the salicylate family, is frequently used as an analgesic, antipyretic, anti-inflammatory and antiplatelet drug. Because aspirin is chemically unstable in water and heat for tablet formulation, additives including lubricants are used in preparing aspirin tablets, using a dry-granulation process. Aspirin tablets are produced by a number of manufacturers which usually use their own unique combination of additives during the manufacturing process. In this study, we employed an NMR based metabolomics technique to identify the manufacturers of various aspirin tablets. Aspirin tablets from six different companies were analyzed by 1H 400 MHz NMR. The acquired data was then integrated and processed by principal component analysis (PCA). Based on the NMR data, we were able to identify peaks corresponding to acetylsalicylic acid in all of the six samples, whereas different NMR patterns were found in the aromatic and aliphatic regions depending on the unique additive used. These observations led to the conclusion that the differences in the NMR patterns among the different aspirin tablets were due to the presence of additives.

• Korean Journal of Medicinal Crop Science
• /
• v.20 no.6
• /
• pp.466-471
• /
• 2012

'Usul' is a traditional medicinal herb, which has anti-inflammatory activities is distributed in India, Nepal, China, Korea, Japan. Korea pharmacopeia listed 'Usul' as either a species of Achyranthes japonica (Miq.) Nakai or A. bidentata Blume. Recent taxonomic studies in China and Japan delimited these taxa as two varieties, A. bidentata Blume var. bidentata and var. japonica Miq. A multivariate morphometric study of Achyranthes bidentata complex was undertaken to assess the entities of taxa that usefully could be recognized. Five quantitative characters were reviewed and analyzed with 293 specimens from Korea. The univariate analysis of inflorescence length, interval between florets, angle between floret and floral axis indicated that ranges among all taxa were continuous. However, quantitative characters of membrane size and the number of hairs within 4 were useful to identify two varieties. In PCA, the first three principal components accounted for 89.4% of the total variance. PCA revealed that var. bidentata showed distinctions in morphological attributes from var. japonica entity. Therefore, continued recognition at the infraspecifc level for these taxa is supported.

• The Journal of Asian Finance, Economics and Business
• /
• v.9 no.3
• /
• pp.105-112
• /
• 2022

The current study is at the forefront of examining the theory of principal-agent framework and financing constraints to explain the level of corporate innovation. To boost the firm's level of innovation, this study uses corporate governance and corporate performance as driving factors. The study's secondary goal is to give information on the parallel relationship between corporate governance and the level of corporate innovation. This study used a two-step least square (TSLS) regression analysis to examine such a simultaneous association using secondary data from Indonesian listed businesses from 2000 to 2021, which totaled around 1,910 observations. This study uses the Principal Component Analysis (PCA) tool to test cumulative variances of potential corporate governance indicators such as the total commissioner of the firm (TCOM), total independent commissioner of the firm (INDPCOM), the proportion of institutional ownership (INSOWN), total female commissioner (FEMCOM), CEO duality (CEODUAL), and type of the firm (SOE). As a result, PCA reveals that four of these variables, omitting CEODUAL and SOE, were a corporate governance construct. Furthermore, the study discovered that the amount of firm innovation and corporate governance are related.