• Journal of Advanced Marine Engineering and Technology
• /
• 제40권8호
• /
• pp.726-732
• /
• 2016

Clustering analysis is widely used in data mining to classify data into categories on the basis of their similarity. Through the decades, many clustering techniques have been developed, including hierarchical and non-hierarchical algorithms. In gene profiling problems, because of the large number of genes and the complexity of biological networks, dimensionality reduction techniques are critical exploratory tools for clustering analysis of gene expression data. Recently, clustering analysis of applying dimensionality reduction techniques was also proposed. PCA (principal component analysis) is a popular methd of dimensionality reduction techniques for clustering problems. However, previous studies analyzed the performance of PCA for only full data sets. In this paper, to specifically and robustly evaluate the performance of PCA for clustering analysis, we exploit an improved FCBF (fast correlation-based filter) of feature selection methods for supervised clustering data sets, and employ two well-known clustering algorithms: k-means and k-medoids. Computational results from supervised data sets show that the performance of PCA is very poor for large-scale features.

• Genomics & Informatics
• /
• 제5권3호
• /
• pp.95-101
• /
• 2007

In this paper, we consider the variable selection methods in the Cox model when a large number of gene expression levels are involved with survival time. Deciding which genes are associated with survival time has been a challenging problem because of the large number of genes and relatively small sample size (n<

• Bulletin of the Korean Chemical Society
• /
• 제30권10호
• /
• pp.2287-2293
• /
• 2009

Gas Chromatography-Mass Spectrometry (GC-MS) fingerprint analysis, Principle Components Analysis (PCA), and Hierarchical Cluster Analysis (HCA) were introduced for quality assessment of Curcuma longa L. (C. longa). The GC-MS fingerprint method was developed and validated by analyzing 33 batches of samples of C. longa from different geographic locations. 18 chromatographic peaks were selected as characteristic peaks and their relative peak areas (RPA) were calculated for quantitative expression. Two principal components (PCs) were extracted by PCA. C. longa collected from Guizhou and Fujian were separated from other samples by PC1, capturing 71.83% of variance. While, PC2 contributed for their further separation, capturing 11.13% of variance. HCA confirmed the result of PCA analysis. Therefore, GC-MS fingerprint study with chemometric techniques provides a very flexible and reliable method for quality assessment of C. longa.

• International Journal of Internet, Broadcasting and Communication
• /
• 제14권4호
• /
• pp.181-188
• /
• 2022

The purpose of this study is to identify selection attributes, functional benefits, psychological benefits, and values according to crossover shopping patterns (showrooming and webrooming). To achieve objectives of this study, a survey was designed based on the means-end chain theory, using the in-depth laddering technique and APT laddering technique which understanding the linkage of A(attributes)-FB(functional benefits)-PB(psychological benefit)-V(value). These two laddering techniques were used to construct a hierarchical value map (HVM) by linking selection attributes, functional benefits, psychological benefits, and value levels. The selection attribute items that showrooming shoppers consider important are 'price conformity', 'product information', 'product variety', and 'delivery service'. Functional benefit items were 'free purchase', 'economic benefit', 'communication', 'safety', and 'accurate Information', and psychological benefit items were 'convenience', 'relaxation', 'pleasure', 'rational consumption', and 'stability'. Finally, the value items were 'self-satisfaction', 'abundant life', 'achievement', 'happiness', and 'reasonable life'. Next, the selection attribute items that webrooming shoppers consider important are 'price conformity', 'product information', 'product variety', 'AS', 'shopping atmosphere', and 'seller service'. Functional benefit items were 'free purchase', 'economic profit', 'expression opinion', 'safety', and 'accurate information', and psychological benefit items were 'convenience', 'relaxation', 'rational consumption', and 'stability'. Finally, the value items were 'self-satisfaction', 'abundant life', 'happiness', and 'reasonable life'.

• 한국환경과학회지
• /
• 제24권5호
• /
• pp.623-631
• /
• 2015

Microarray technology provides a unique tool for the determination of gene expression at the level of messenger RNA (mRNA). This study, the mRNA expression profiles provide insight into the mechanism of action of cadmium in Fleshy shrimp (Fenneropenaeus chinensis). The ability of genomic technologies was contributed decisively to development of new molecular biomarkers and to the determination of new possible gene targets. Also, it can be approach for monitoring of trace metal using oligo-chip microarray-based in potential model marine user level organisms. 15K oligo-chip for F. chinensis that include mostly unique sets of genes from cDNA sequences was developed. A total of 13,971 spots (1,181 mRNAs up- regulated and 996 down regulated) were identified to be significantly expressed on microarray by hierarchical clustering of genes after exposure to cadmium for different conditions (Cd24-5000 and Cd48-1000). Most of the changes of mRNA expression were observed at the long time and low concentration exposure of Cd48-1000. But, gene ontology analysis (GO annotation) were no significant different between experiments groups. It was observed that mRNA expression of main genes involved in metabolism, cell component, molecular binding and catalytic function. It was suggested that cadmium inhibited metabolism and growth of F. chinensis.

• 한국의류산업학회지
• /
• 제19권6호
• /
• pp.701-711
• /
• 2017

This research aimed to understand selfie behavior in social networking sites (SNSs). The research was conducted on the basis of the functional theories of attitude, verified self-presentation attitude, and self-expression attitude that affect selfie behaviors (i.e., taking selfies, posting selfies, and taking selfies for fashion product exposure). The moderating effect of satisfaction toward one's appearance was identified. The participants of the study were SNS users aged 20-30 years who had posted selfies in the past month. A survey was performed using an online panel of an international survey firm. The data were analyzed using hierarchical regression analysis on SPSS 22.0. Results corroborated that self-expression attitude affected the number of selfies taken but not the number of selfies posted and those uploaded for fashion product exposure. Self-presentation attitude exerted a significant effect on the number of selfies posted and those uploaded for fashion product exposure. When satisfaction toward one's appearance was high, self-presentation attitude increased the influence of the behaviors of posting selfies and uploading selfies for fashion product exposure. Self-expression attitude also significantly influenced the number of selfies taken due to the moderating effect of satisfaction toward one's appearance. This research was made meaningful by its quantitative analysis of selfie behavior in SNSs. The results confirmed the different functions of attitudes affecting selfie behavior. With the improved understanding of selfie behavior obtained from this research, Social Media marketing may be carried out in various industrial fields in the future.

• 동의생리병리학회지
• /
• 제19권4호
• /
• pp.913-921
• /
• 2005

In this study, we investigated gene expression patterns induced by Ailanthus altissima extract and compared it with Gleevec, a well-known anti-leukemia drug, in K562 chromic leukemia cells. Ailanthus altissima extract(100 ug/ml) and Gleevec(50 ug/ml) were treated to cells for 1h, 2h, 4h, and 16h and total RNA was extracted. Gene expressions were evaluated using cDMA microarray, in which 24,000 genes were spotted. Hierarchical clustering analysis showed that expression of genes included in two clusters were increased or decreased time dependently by both Ailanthus altissima extract and Gleevec. Genes included in another cluster were induced by Ailanthus altissima extract but not by Gleevec. In biological process analysis, expression of genes involved in apoptosis, growth arrest and DNA-damage were increased, but genes stimulating cell cycle were decreased. This study provides comprehensive comparison of the patterns of gene expression changes induced by Ailanthus altissima extract and Gleevec in K-562 leukemia cells.

• 동의생리병리학회지
• /
• 제20권4호
• /
• pp.853-860
• /
• 2006

This study was performed to investigate genes which are differently expressed in human blood by administrating of OLT-2. OLT-2 was medical precipitation composed of three medicinal herbs, Ginseng Radix, Astragali Radix, Glycyrrhizae Radix, and anti-leukemia effect of it was evaluated from Byung Hun Jeon of Wonkwang University this study was approved by Institutional Review Board of Korea Institute of Oriental Medicine (Taejeon, Korea) and four male subjects participated in this study. Gene expressions were evaluated by cDNA chip, in which 24,000 genes were spotted. Hierarchical cluster and biological process against the genes, which expression changes were more than 1.6 fold, were constructed by cluster 3.0 providing Stanford University and EASE(http://apps1 .maid.nih.gov/DAVID). Five groups were clustered according to their expression patterns. Group A contained gene decreased by OLT-2 and increased genes by OLT-2 were involved in Group B, C, D. In biological process, expression of genes involved in cytokine or cell calcium signaling, such as interleukin 18 and G-protein beta 4 were increased, but protein tyrosine phosphatase receptor type c, which function is cell adhesion between antigen-presenting cell and T or B-cell, was decreased by OLT-2. This study provides the most comprehensive available survey of gene expression changes in response to anti-leukemia effect of OLT-2 in human blood.

• 한국정보과학회논문지:데이타베이스
• /
• 제35권3호
• /
• pp.243-256
• /
• 2008

최근 인터넷의 급속한 발달로 인해 웹 상의 정보 양이 엄청나게 증가하고 있다. 하지만 현재 웹 상의 정보들은 사람이 읽고 해석하기에만 편리하게 설계되어 원하는 정보에 대한 정확한 검색이 어려워지고 있다. 이러한 문제점을 해결하기 위해 시맨틱 웹이 제안되었으며, 이를 구축하기 위해서는 데이타에 의미를 부여하는 온톨로지 언어를 사용해야 한다. 대표적인 은톨로지 언어는 RDF, RDF-S, OWL 등이 있다. 이러한 언어들 중 OWL은 W3C에서 권고안으로 채택한 언어로써 다른 온톨로지 언어에 비해 풍부한 표현력과 형식적인 의미론을 지닌다. 또한 OWL 데이타는 클래스/프로퍼티들 간의 계층 구조 정보를 포함한다. 따라서, 시맨틱 웹 상에서 데이타의 효율적인 검색을 위해서는 계층적 구조를 고려한 효율적인 OWL 저장 모델이 필요하다. 이 논문에서는 OWL 데이타의 클래스/프로퍼티들 간 계층 정보를 XPath 형태로 포함하며, 직관적이고 효율적인 질의 처리가 가능한 저장 모델(XPOS Model) 및 시스템을 제안한다. 또한, 제안 모델, Sesame, XML 저장소 기반 저장 시스템을 질의 처리 측면에서 성능에 대한 비교 평가 결과를 보인다.

• 한국의류학회지
• /
• 제35권5호
• /
• pp.561-574
• /
• 2011

This study investigates the ultimate factor structure of consumer dissatisfaction with the off-line purchase and usage of clothing. It identifies the determinant dimensions of consumer dissatisfaction on clothing purchase and usage and investigates the hierarchical structure of consumer dissatisfaction by assessing and comparing the effectiveness of five alternative factor structure models. A total of 300 women were online-surveyed to assess the level of dissatisfaction based on their dissatisfying experience with clothing purchases and usage in terms of product quality, price, salesperson's attitude, and store environment. The exploratory factor analysis identified the underlying dimensions of dissatisfaction: Handling, Aesthetics, Salesperson, Size, Price, Product Quality, Service, and Environment. By employing a first-order confirmatory factor analysis and higher-order confirmatory factor analysis, consumer dissatisfaction was confirmed to have a hierarchical structure with three second-order constructs Intrinsic instrument is manifested by handling, quality, and size, Intrinsic expression consists of service, salesperson, and environment, and Extrinsic circumstance contains aesthetics and price. On empirically demonstrating the multi-dimensional constructs of consumer dissatisfaction by identifying its hierarchical structure, the study provides the theoretical and practical insights to comprehend consumer purchase and post-purchase behavior. Specifically, it affords an empirical platform to extend the scope of research with condensed concepts of dissatisfaction to researchers. In addition, it also enables marketers to take a broader view of consumer dissatisfaction by providing cues about potential problems and identifying the source of those problems.