• 한국연초학회지
• /
• 제29권2호
• /
• pp.74-79
• /
• 2007

This study was conducted to evaluate the prediction of sensory property of smoke from leaf chemical property and characterize leaf chemical components for the best tobacco taste's leaves in flue-cured tobacco. For analytical and sensory evaluations, one hundred and forty grades were used. The major leaf chemical components to predict the sensory property of smoke were nicotine for impact, irritation and off taste & odor, and total sugar/nicotine ratio for tobacco taste. Within ${\pm}20%$ range of difference, the predictable probabilities of sensory property of smoke form leaf chemical property were 80.0% for off taste & odor and $91.4{\sim}96.4%$ for impact, irritation and tobacco taste. As a result of K-means cluster analysis on the basis of tobacco taste, the desirable leaf chemical component contents were $2.77{\sim}3.55%$ in nicotine and $5.1{\sim}6.9$ in total sugar/nicotine ratio. This study suggest that the some regression equations may be useful to predict the sensory property of tobacco smoke from a few selected leaf chemical components in flue-cured tobacco and to select the flue-cured tobacco leaves for enhance the tobacco taste of cigarette.

• 한국가정과교육학회지
• /
• 제27권1호
• /
• pp.13-29
• /
• 2015

본 연구는 광주 전남지역 남녀 중 고등학생을 대상으로 성별, 연령(학교급)과 외모에 대한 사회문화적 태도의 유형에 따른 신체비교, 신체만족, 그리고 외모관리행동에 어떠한 차이가 있는지 살펴봄으로써 이 지역 청소년들의 외모에 대한 사회문화적 태도 및 외모관리행동과 관련된 자료를 제공하고자 하였다. 598명의 자료를 결과분석에 이용하였으며 자료 분석을 위해 SPSS/PC WIN 19.0프로그램을 이용하여 기술통계, 신뢰도(Cronbach's ${\alpha}$)분석, 요인분석, ${\chi}^2$검증, K-means군집분석 t-test, ANOVA(일원변량분석), Duncan's grouping을 실시하였다. 광주 전남지역 청소년들도 보통이상으로 외모에 대한 사회문화적 기준을 수용하여 인식하고 내면화하는 경향이 있었다. 또한 여학생의 경우 남학생보다, 그리고 고등학생이 중학생보다 이러한 경향이 더욱 강하게 나타났다. 외모에 대한 사회문화적 태도는 수용형, 내면화형, 인식형, 비수용형으로 분류되었으며 외모에 대한 사회문화적 가치관을 내면화하는 정도가 높은 내면화형과 적극적으로 수용하는 수용형의 경우 신체만족도가 더 낮고 신체비교를 자주하였다. 또한 외모관리행동에서도 성형과 기능성보정의복착용에 대해 적극적이고 수용적이었으며 다른 사람에게 보여주기 위한 체중감량을 위해 다이어트를 열심히 하고 피부관리와 청결관리를 적극적으로 하는 것으로 나타났다. 따라서 우리사회의 외모에 대한 현상을 객관적으로 볼 수 있고 자신의 신체상을 긍정적으로 볼 수 있는 시각을 길러주어야 할 것으로 보인다. 현실과 너무 떨어져 있는 현재의 사회문화적 외모기준으로부터 청소년의 자존감을 보호할 수 있는 바람직한 외모에 대한 태도와 행동을 기를 수 있는 교육내용이 가정교과 지도 시 강조되어야 할 필요가 있다고 하겠다.

• 한국대기환경학회지
• /
• 제23권1호
• /
• pp.14-28
• /
• 2007

This study presented the selection of ozone ($O_3$) potential factors and designed and assessed its potential prediction model using multiple-linear regression equations in Ulsan area during the springtime from April to June, $2000{\sim}2004$. $O_3$ potential factors were selected by analyzing the relationship between meterological parameters and surface $O_3$ concentrations. In addition, cluster analysis (e.g., average linkage and K-means clustering techniques) was performed to identify three major synoptic patterns (e.g., $P1{\sim}P3$) for an $O_3$ potential prediction model. P1 is characterized by a presence of a low-pressure system over northeastern Korea, the Ulsan was influenced by the northwesterly synoptic flow leading to a retarded sea breeze development. P2 is characterized by a weakening high-pressure system over Korea, and P3 is clearly associated with a migratory anticyclone. The stepwise linear regression was performed to develop models for prediction of the highest 1-h $O_3$ occurring in the Ulsan. The results of the models were rather satisfactory, and the high $O_3$ simulation accuracy for $P1{\sim}P3$ synoptic patterns was found to be 79, 85, and 95%, respectively ($2000{\sim}2004$). The $O_3$ potential prediction model for $P1{\sim}P3$ using the predicted meteorological data in 2005 showed good high $O_3$ prediction performance with 78, 75, and 70%, respectively. Therefore the regression models can be a useful tool for forecasting of local $O_3$ concentration.

• 한국의류학회지
• /
• 제26권2호
• /
• pp.303-314
• /
• 2002

The colors of apparel have become an important element to be used strategically in order to give differentiated character at the level of fiber and fabric production. The colors of apparel have a close relationship with the skin colors of consumers and their preference colors. This study was carried out to classify the skin colors of Korean elderly women into several similar skin colors and to analyse their preference colors. Sample size was 471 Korean elderly women. With color spectrometer, JX-777, we measured 4 points of the body; cheek with removing cosmetics off, forehead, rear neck and arm on the interior part near elbow. All subjects had been shown with 40 color chips and answered the preference colors of apparel and the preference colors. Data weirs analysed to classify skin colors using K-means Cluster Analysis and Duncan test. Independent variables for Cluster Analysis were 12 variables out of L value, a value and b value of 4 points. In doing so, we used SPSS WIN 10 statistical package. Findings were as follows: 1) The skin colors of the Korean elderly women were composed of skin colors of YR, R, and Y. 2) 355 subjects were classified into 4 kinds of skin color groups. 3) The average face color of type 1 was 6.7YR 5.1/4.3 and 56 observations out of 355 subjects were composed of Type 1 and of Type 2 was 6.1YR 6.1/4.5 and 166 observations out of 355 and of 3 Type 6. YR 4.8/4.2 and 75 observations out of 355 and of Type was 6.17 YR 5.7/4.7 and 58 observations out of 355. 4) The average skin color of Type 1 was 7.0YR 5.9/4.4 and of Type 2 was 7.2YR 6.3/4.2 and of Type 3 was 7.0YR 6.2/4.2 and of Type 4 was 7.6YR 5.4/4.2 respectively. 5) The mean values of 12 variables between the 4 classified face color and skin color groups showed significantly different except H value of skin color. 6) All 4 groups showed that the most preference color of apparel and the most preference color were 2.5R 5/14 respectively.

• 한국의류산업학회지
• /
• 제23권5호
• /
• pp.667-673
• /
• 2021

The purpose of this study was to obtain drape information and objective texture of fabrics easily and quickly by using a constructed fabric database. For the construction of the fabric database, 287 woven fabrics were examined by using the CLO fabric kit, KES-FB system, and drape test system. The k-means cluster analysis method was used to classify the fabrics into 7 grades. After correlation analysis of the fabric properties for each experiment, similar properties of the CLO fabric kit and KES-FB system were chosen, which were then designed to extract similar fabrics from the database. It was confirmed that inferring the drape information and objective hand feeling of fabrics was to some extent possible by extracting similar fabrics from the database. In this study, the primary hand and total hand value(THV) of KES-FB system, which was constructed by Kawabata and other experiments, were used to quantify the objective hand feeling, because they are the most widely used. However, these standards can be changed over time; in order to be applied within the clothing industry, these standards may have to be changed to some extent. Moreover, it is notable that although objective hand feeling cannot be expressed in the 3D virtual costume program, it can be easily derived from the constructed database. Additionally, it is expected that the existing 3D virtual costume program will express the costumes more realistically by improving these results.

• 한국의류산업학회지
• /
• 제25권5호
• /
• pp.603-614
• /
• 2023

Body shape is the most influential factor in determining the quality of clothing fit. Women's body shape begins to change significantly in their mid-30s; therefore, this study aimed to classify and analyze the torso shapes of women aged 35-54 years. This study selected 200 3D body scans of women from the 8th Size Korea Survey database (2021). Using the Grasshopper algorithm developed in a previous study, 17 landmarks were automatically detected and 57 measurement values were generated. Using principal component analysis, 11 components (overall body size, upper body length, back protrusion, upper body slope, neck position, neck inclination, hip length, bust prominence, abdominal prominence, shoulder slope, and buttock prominence) were extracted. Three torso types were identified using K-means cluster analysis. The three body types were significantly different on nine component scores. Among the three torso types, Type 1 (37.5%) has the longest upper body and the flattest back and hips. Type 2 (31.0%) has the most curved back and forward upper body. Its abdomen is the flattest, and its shoulders are the most sloped. Type 3 (31.5%) has the shortest upper body, the most protruding hips, and the largest overall body size. This paper proposes two discriminant functions for identifying a new person's torso type.

• 한국융합학회논문지
• /
• 제11권4호
• /
• pp.11-16
• /
• 2020

해양 오염사고를 대비한 계획으로, 최적화된 배치안들을 수집하여 분석하는 연구가 필수적이지만, 해양 오염사고 대응을 위한 최적을 배치안을 다양화하고 분석한 연구는 아직 선행되지 않았다. 이러한 필요성에 따라, 우리는 방제자원 배치 최적화를 위한 유전알고리즘을 고안하고 이를 통해 최적의 방제 자원 배치안을 10,000 개 도출하였다. k-평균 알고리즘으로 군집화한 결과, 예상 최대 유출지역인 여수, 대산, 울산에 대하여 두 개의 군집으로 확연히 구분되었다. 우리는 이러한 군집을 새몬 맵핑을 통해 이차원으로 사영하여 배치안의 분포도를 분석하였고, 군집에 포함되는 배치안들이 그렇지 않은 배치안보다 시뮬레이션의 결과가 우수함을 확인했다. 향후, 본 연구를 기반으로 성능이 우수한 근사모델을 구현하는 것이 가능할 것으로 보인다.

• 융합보안논문지
• /
• 제23권4호
• /
• pp.61-70
• /
• 2023

클러스터링은 데이터의 정답값(실제값)이 없는 데이터를 기반으로 데이터의 특징벡터의 거리 기반 등으로 군집화를 하는 비지도학습 방법이다. 이 방법은 이미지, 텍스트, 음성 등 다양한 데이터에 대해서 라벨링이 없이 적용할 수 있다는 장점이 있다. 기존 클러스터링을 하기 위해 차원축소 기법을 적용하거나 특정 특징만을 추출하여 군집화하는 방법이 적용되었다. 하지만 딥러닝 기반 모델이 발전하면서 입력 데이터를 잠재 벡터로 표현하는 오토인코더, 생성 적대적 네트워크 등을 통해서 딥 클러스터링의 기술이 연구가 되고 있다. 본 연구에서, 딥러닝 기반의 딥 클러스터링 기법을 제안하였다. 이 방법에서 오토인코더를 이용하여 입력 데이터를 잠재 벡터로 변환하고 이 잠재 벡터를 클러스터 구조에 맞게 벡터 공간을 구성 및 k-평균 클러스터링을 하였다. 실험 환경으로 pytorch 머신러닝 라이브러리를 이용하여 데이터셋으로 MNIST와 Fashion-MNIST을 적용하였다. 모델로는 컨볼루션 신경망 기반인 오토인코더 모델을 사용하였다. 실험결과로 k가 10일 때, MNIST에 대해서 89.42% 정확도를 가졌으며 Fashion-MNIST에 대해서 56.64% 정확도를 가진다.

• 한국정보통신학회논문지
• /
• 제13권1호
• /
• pp.177-185
• /
• 2009

클러스터링은 주어진 데이터 포인트들을 주어진 개수의 그룹으로 나누는 비지도 학습의 한 방법이다. 클러스터링의 방법 중 하나로 널리 알려진 퍼지 클러스터링은 하나의 포인트가 모든 클러스터에 서로 다른 정도로 소속될 수 있도록 함으로써 하나의 클러스터에만 속할 수 있도록 하는 K-means와 같은 방법에 비해 자연스러운 클러스터 형태의 유추가 가능하고, 잡음에 강한 장점이 있다. 이 논문에서는 기존의 퍼지 클러스터링 방법 중 소속도(membership)와 전형성(typicality)을 동시에 계산해 낼 수 있는 Possibilistic Fuzzy C-Means(PFCM) 방법에 Gath-Geva(CG)의 방법을 적용하여 PFCM을 개선한다. 제안한 방법은 PFCM 장점을 그대로 가지면서도, GG의 거리 척도에 의해 클러스터들 사이의 경계를 강조함으로써 분류 목적에 적합한 소속도를 계산할 수 있으며 전형성은 가우스 형태의 분포에서 생성된 포인트들의 분포 함수를 정확하게 모사함으로써 확률 밀도 추정의 방법으로도 사용될 수 있다. 또한 GG 방법은 Gustafson-Kessel 방법과 달리 클러스터에 포함된 포인트의 개수가 확연히 차이나는 경우에도 정확한 결과를 얻을 수 있다. 이러한 사실들은 실험 결과를 통해 확인할 수 있다.

• 한국과학교육학회지
• /
• 제16권4호
• /
• pp.477-485
• /
• 1996

The purpose of this study was to identify the preferable motivation types in science-learning and to find out the relationship between these types and scientific achievement of students in the secondary school. The subjects of the study were the second grade 581 students sampled by random cluster sampling method in three middle schools and three high schools. Three motivation types in science learning were analyzed, and they were named to task-orientation, ego-orientation and work-avoidance. From our results, secondary school students preferred task-orientation and work-avoidance to ego-orientation. In the case of task-orientation, high school students, especially in male group, had much preferable tendency than that of middle school students (p<0.001). It is interpreted that, as the level of scientific content of texts or the cognitive level of students were higher, a preference for the motivation type was focused to the task-orientation, especially in male group. In the case of ego-orientation, the female group showed much preferable tendency than that of male group in middle school (p<0.05). However, the female group in high school students was not different from the other groups in this motivation type. In the case of work-avoidance, there were not only a significant difference between males and females in the middle school (p<0.001), but also difference between middle and high school students in female group (p<0.05). It showed that female group had much preferable tendency than that of male group, and this tendency was decreased to the higher grade students in secondary school. From the analysis of correlation between motivation types and scientific achievement, task-orientation and work-avoidance were correlated to the scientific achievement. Its results were interpreted that the scientific achievement could be accomplished by the external motivation stimulus as well as the scientific content of texts. The task-orientation were comparatively correlated to the intelligence quality. It means that the students having high intelligence quality showed much preferable for the task-orientation.