• 한국해양공학회지
• /
• 제24권1호
• /
• pp.161-165
• /
• 2010

In the present study, process optimization for thermal-sprayed STS316 coating has been performed using $L_9(3^4)$ orthogonal array and analysis of variance (ANOVA). STS316 coatings were fabricated by flame spray process on steel substrate, and the hardness test and microstructure observation of the coatings were studied. The results of hardness test were analyzed by ANOVA. The ANOVA results showed that the spray distance had the greatest effect on hardness of the coating, on the other hands, the effects of oxygen gas flow and spray distance were ignorable. From these results, the optimal combination of the flame spray parameters could be derived, and confirmation experiment was carried out to verify these derived results. The calculated hardness of the coatings by ANOVA was found to approximately close to that of confirmation experimental result. Thus, it was considered that design of experiments using orthogonal array and ANOVA was effective for process optimization of thermal-sprayed STS316 coating.

• 동력기계공학회지
• /
• 제13권5호
• /
• pp.89-94
• /
• 2009

In this work, the optimal process has been designed by $L_9(3^4)$ orthogonal array and analysis of variance(ANOVA) for thermal-sprayed Ni-based hard coating. Ni-based hard coatings were fabricated by flame spray process on steel substrate. Then, the hardness test and observation of microstructure of the coatings were performed. The results of hardness test were analyzed by ANOVA. The ANOVA results demonstrated that the acetylene gas flow had the greatest effect on hardness of the coatings. The oxygen gas flow was found to have a neglecting effect. From these results, the optimal combination of the flame spray parameters could be predicted. The calculated hardness of the coatings by ANOVA was found to lie close to that of confirmation experimental result. Thus, it was considered that design of experiments design using orthogonal array and ANOVA was useful to determine optimal process of thermal-sprayed Ni-based hard coating.

• 한국기계가공학회지
• /
• 제8권3호
• /
• pp.46-53
• /
• 2009

To find the working condition is one of the important factors in precision machining. In this study, we analyzed maximum working temperature by infra-red camera and surface roughness in side wall end milling using design of experiment (DOE): RSM(response surface methodology), ANOM(analysis of means) and ANOVA(analysis of variance) by table of orthogonal array. ANOM and ANOVA are well adapted to select sensitivity of design variables for maximum working temperature and surface roughness. The effective design variables and their levels should be determined using ANOM, ANOVA. RSM is presented 2nd order approximation polynomial of maximum working temperature and surface roughness is composed with design variables. Therefore, it is expected that the proposed procedure using design of experiment : table of orthogonal array, ANOM, ANOVA and RSM can be easily utilized to solve the problem of working condition.

• 한국콘텐츠학회논문지
• /
• 제9권10호
• /
• pp.398-406
• /
• 2009

본 연구의 목적은 관광행동에 따른 여행상품속성의 차이를 살펴봄으로써 여행업계가 더 주력해야 할 여행상품을 판매하기 위한 마케팅 전략을 제시하는 것에 도움을 주고자 하는 것이다. 본 연구를 위해 군집분석과 ANOVA분석이 이용되었는데, 군집분석 결과 4개의 군집으로 나타났다. '합리적 관광형', '약한 과시적 관광형', '가치적 관광형'과 '과시적 가치적 관광형'으로 분류되었다. ANOVA분석 결과 여행서비스와 오락을 제외한 교통 숙박시설, 관광매력물, 쇼핑, 식사에서는 관광행동에 있어 군집들이 차이를 보이는 것으로 나타났다.

• 대한인간공학회지
• /
• 제33권6호
• /
• pp.515-532
• /
• 2014

Objective: The purpose of this study is to define consumers' affection on the interior design of commercial cars in terms of its design factors: color, embossing and gloss as independent factors. Background: Existing affective studies related to interior of vehicle focus on just sedans. However, there is no affective study about the interior of commercial cars. In addition, it is hard to change levels to which manufactures want. Method: Representative design factors were drawn using ANOVA and SNK analysis and definitive affective vocabularies were drawn using factor analysis. Furthermore, the results of 3D experiment were analyzed using ANOVA and LSD analysis. 3D images for the experiment were made using 3D max program. The experiment revealed that consumers discerned the differences in levels of each design factor and affective vocabulary. Results: The ANOVA revealed that beige color "A" type and non-gloss were the most preferred design in terms of the affective vocabularies and total preference. Conclusion: The result of the experiment may help manufactures to design the interior of commercial cars in the near future. Furthermore, the ANOVA result of affective vocabularies evaluation is expected to suggest a meaningful guideline. Application: The study results may be utilized as a guideline for interior design of commercial cars.

• 한국환경과학회지
• /
• 제16권11호
• /
• pp.1209-1218
• /
• 2007

Advertisement signboards on the buildings have functionally a visual value as factor of urban and building design. But it is not easy to find any reasonable principles and regulations, how well the signboards deliver the information of stores to the customers, and how they contribute the visual amenity from the sight of urban landscape. Under this context, this study tries to analyze the information delivery power of signboards in relation to the visual cognition. The analysis method is the Two-Way ANOVA (Analysis of Variance) evaluation with factors, such as scale, amount and arrangement of signboards. The scale of letters or figures at Signboards is specified in 3 different sizes such as big, medium and small. The amount is classified into 5 grades from 100% to 20% installation. And the arrangement is divided into orderly and disorderly installation. As the results of the Two-Way ANOVA, the identical scale of signboards is much better for the awareness. And the orderly arrangement shows also the same result. Above all, including these two results, the 80% of installation showed the biggest different result of awareness.

• 한국생물정보학회:학술대회논문집
• /
• 한국생물정보시스템생물학회 2001년도 제2회 생물정보 워크샵 (DNA Chip Bioinformatics)
• /
• pp.97-115
• /
• 2001

cDNA microarray technology allows the monitoring of expression levels for thousands of genes simultaneously. Many statistical analysis tools become widely applicable to the analysis of cDNA microarray data. In this talk, we consider a two-way ANOVA model to differentiate genes that have high variability and ones that do not. Using this model, we detect genes that have different gene expression profiles among experimental groups. The two-way ANOVA model is illustrated using cDNA microarrays of 3,800 genes obtained in an experiment to search for changes in gene expression profiles during neuronal differentiation of cortical stem cells.

• 동력기계공학회지
• /
• 제15권5호
• /
• pp.72-76
• /
• 2011

In this work, the parameter optimization for thermal-sprayed Al/SiC composites have been designed by $L_9(3^4)$ orthogonal array and analysis of variance(ANOVA). Al/SiC composites were fabricated by flame spray process on steel substrate. The hardness of composites were measured using micro-vickers hardness tester, and these results were analyzed by ANOVA. The ANOVA results showed that the oxygen gas flow, powder feed rate and spray distance affect on the hardness of the Al/SiC composites. From the ANOVA results, the optimal combination of the flame spray parameters could be extracted. It was considered that experimental design using orthogonal array and ANOVA was efficient to determine optimal parameter of thermal-sprayed Al/SiC composites.

• 한국정보통신학회논문지
• /
• 제22권6호
• /
• pp.835-841
• /
• 2018

본 연구에서 공개 의료 빅데이터 분석을 지역사회건강조사 2012~2014년 자료를 이용해 개인의 건강관련 삶의 질 차이와 삶의 질에 영향을 미치는 요인을 분석하였다. 제안논문에서는 공개의료 빅데이터 분석을 위해 Hadoop 기반의 Spack을 이용해 병렬처리 지원을 위한 클라우드 메니저를 구성하고 개인의 삶의 질에 영향을 미치는 요인을 하드웨어의 제약없이 빠르게 분석하였다. 건강관련 삶의 질에 미치는 영향을 개인적 특성과 지역사회 특성으로 구분하여 단계별 다수준 회귀분석(ANOVA, t-test)을 실시하였다. 연구결과 개인별 삶의 질에 영향을 미치는 요인으로는 남자 평균 73.8점, 여자 평균 70.0점으로 남자가 여자보다 건강관련 삶의 질이 높은 것으로 나타났다.

• Communications for Statistical Applications and Methods
• /
• 제8권3호
• /
• pp.667-675
• /
• 2001

The usefulness of analysis of variance(ANOVA) estimates of variance components is impaired by the frequent occurrence of negative values. The probability of such an occurrence is therefore of interest. In this paper, we investigate a variety of reasons for negative estimates under one way random effects model. It can be shown, through simulation, that this probability increases when the number of treatments is too small for fixed total observations, unbalancedness of data is severe, ratio of variance components is too small, and data may contain many outliers.