• The Transactions of the Korea Information Processing Society
• /
• v.3 no.6
• /
• pp.1468-1472
• /
• 1996

In this study, the performance of the CART(Classification and Regression Tree) is compared with that of discriminant analysis method. In most experiments using bank data, discriminant analysis shows better performance in terms of the total cost. In contrast, most experiments using insurance data show that the CART is better than discriminant analysis in terms of the total cost. The contradictory result are analysed by using the characteristics of the data sets. The performances of both the Classification and Regression Tree and discriminant analysis depend on the parameters:failure prior probability, data used, type I error, type II error cost, and validation method.

• Proceedings of the Acoustical Society of Korea Conference
• /
• 1998.06d
• /
• pp.40-45
• /
• 1998

본 논문은 한국산 박새(Parus major)의 소리(song)를 이용해서 태백산맥을 경계로 동서간의 지리적 변이에 관한 논문이다. 박새 소리의 지리적인 변이를 알아보기 위하여 지역간 음절의 시간과 주파수 요인을 비교하고, factor의 군집화의 지역간의 변이정도를 알아보기 위하여 Cluster Analysis와 discriminant Analysis를 실시하였다. 그 결과 태백산맥을 경계로 동쪽지역여과 서쪽지역은 영덕군과 청송군, 삼척시와 태백시를 중심으로 해서 지리적인 변이를 나타냈다.

• Journal of the Korean Institute of Intelligent Systems
• /
• v.22 no.1
• /
• pp.81-86
• /
• 2012

In this paper, we proposed a new design methodology of a pattern classification rule based on the local linear discriminant analysis expanded from the generic linear discriminant analysis which is used in the local area divided from the whole input space. There are two ways such as k-Means clustering method and the differential evolutionary algorithm to partition the whole input space into the several local areas. K-Means clustering method is the one of the unsupervised clustering methods and the differential evolutionary algorithm is the one of the optimization algorithms. In addition, the experimental application covers a comparative analysis including several previously commonly encountered methods.

• Proceedings of the IEEK Conference
• /
• 2006.06a
• /
• pp.689-690
• /
• 2006

Relational discriminant analysis is a way of representing an object based on the dissimilarity measures among the prototypes extracted from feature vectors instead of the vectors themselves. Thus, by appropriately selecting a few number of representatives and by defining the dissimilarity measure, in this paper we propose a method of reducing the dimensionality and getting to achieve a better classification performance in both speed and accuracy. Our experimental results demonstrate that the proposed mechanism increases the performance as compared with the conventional approaches for samples involving artificial data sets.

• The Korean Journal of Zoology
• /
• v.28 no.1
• /
• pp.9-20
• /
• 1985

Univariate and multivariate analyses of morphometric characters were performed with samples of striped field mice, Apodemus agrarius coreae Thomas, collected from Mt. Taebaek area, Mt. Wolak area, Mt. Palgong area, and Chongju area. It was confirmed that the samples of A. agrarius coreae were similar with one another to be grouped into a single subspecies. Moreover, clinal variation related with the altitude of localities where samples were collected was revealed in the first axis resulted from discriminant analysis and in the length of tail vertebrae.

• Annual Conference of KIPS
• /
• 2004.05a
• /
• pp.761-764
• /
• 2004

얼굴 데이터를 사용하는 인식 시스템에서 특징 벡터의 차원은 일반적으로 매우 크다. 패턴인식에서 차원 축소는 중요한 문제로서, 효과적인 얼굴 인식을 위한 특징 벡터의 차원 축소는 필수적이라 할 수 있다. 본 논문에서는 획득된 얼굴 데이터로부터 저 차원의 강건한 특징을 얻기 위하여 웨이블릿을 사용하고, 식별력 있는 특징을 얻기 위하여 direct linear discriminant analysis를 사용하였다. Direct linear discriminant analysis 방법을 사용하기 이전에 웨이블릿을 사용함으로써 계산 복잡도를 줄여줄 뿐만 아니라 식별력을 높여주고 효과적으로 얼굴 데이터의 차원을 축소할 수 있음을 보여 준다. 얼굴의 패턴정합을 위해서는 최근접 평균 분류기(Nearest Mean Classifier)를 사용하였으며, 최근접 평균 분류기를 사용함으로써 분류를 위한 시간을 최소화하였다. 본 논문에서 인간의 얼굴인식을 위해 제시한 방법이 얼굴패턴을 표현하는 효과적인 방법이며, 시간 및 공간의 절약이라는 측면에서 유리하다는 것을 보여준다.

• Korean Journal of Community Nutrition
• /
• v.13 no.5
• /
• pp.723-732
• /
• 2008

The purpose of this study was to identify the influence of diet related factors, such as diet behaviors, food intake, and nutrient intakes, on self-rated health (SRH). Also, in order to determine fitness of classification for SRH reflecting diet related factors, this study surveyed older adults in Gyeongnam province. A total of 101 responses were collected using the interview survey method. The self- rated health of rural older adults was poor as reported by 49.5%. The level of self-rated health was found to be related to the frequencies of coffee and snack, use of sugar and vegetable in diet, the amount of total food intake, and cholesterol intake. The result of discriminant analysis, which was conducted to assess the adequacy of SRH classification and to determine the class of observation, showed frequency of coffee and use of vegetable in diet among 47 variables as predictive variables for explaining SRH. The fitness of self-rated health function was high to 47.7%. Therefore, diet-related factors were ascertained to be important variables to predict SRH.

• Journal of Korean Academy of Nursing
• /
• v.29 no.3
• /
• pp.585-595
• /
• 1999

The purpose of this study was to examine the predictors of burnout among informal caregivers of older adults. One hundred thirty seven caregivers who had provided care to older adults over 60 years of age for more than one month were included in the study. Most of the caregivers were white (91%) and female (78%). Mean ages of the caregivers were 64 years and 78% of them were married. Seventy percent of the older adults suffered from Alzheimer and related disease. In this study, caregivers reported that they experienced burnout once a month. The scores of emotional exhaustion and reduced personal accomplishment of the caregivers were in the moderate burnout range. To examine the predictors of burnout, discriminant analysis was used. Caregivers were divided by two groups based on the sum of scores (cutpoint＝6) on three dimensions of burnout after each dimension was categorized into high(3), moderate(2), and low(1). Nine predictors were included in the analysis : Caregiver's age, employment status, Instrumental Activities of Daily Living (IADL) of the older adult, presence of dementia of the older adult, caregiver's empathy toward the older adult (emotional and cognitive), and 3 coping strategies (negative, problem-focused, cognitive reconstructioning). Caregivers who reported high burnout showed higher cognitive empathy toward the older adults than those who showed low burnout. Caregivers who experienced high burnout used negative coping more often, and cognitive reconstructioning coping and problem focused coping less often than their counterparts. Wilks' Lambda was .78 indicating that differences between the two groups were significant. Cognitive empathy and cognitive reconstructioning coping showed high standardized canonical discriminat function coefficients over .40. Discriminant function with 9 predictors correctly classified 71% of the sample. In conclusion, informal caregivers also experienced certain level of burnout. Cognitive empathy and coping strategies predicted burnout experience of the caregivers. Based on this study, nursing intervention to the informal caregivers to improve their cognitive empathy toward the older adults and to modify their coping strategies in a way to reduce burnout experience can be applied. Further research to develop effective nursing interventions for the purpose of reducing burnout experience by modifying predictors was suggested.

• Animal Systematics, Evolution and Diversity
• /
• v.2 no.2
• /
• pp.1-12
• /
• 1986

Genetic and morphological variation among seven populations of two species of the genus Liobagrus that had been collected from six separate river systems in Korea were analyzed by means of starch electrophoreiss and discriminant function analysis . The degree of genic variation among three population of L.andersoni was P=21.3%, H=0.068 , and that of four population of L.mediadiposalis was P=16.3%, H=0.560. Rogers' gentic similarity coefficient (S) of L.andersoni and L.mediadiposalis were S=0.592 , S=0.675 respectively. In morphometric characters of L. andersoni, the population from Kum River was distinctly different from other conspecific populations.

• Journal of the Korean Institute of Intelligent Systems
• /
• v.24 no.2
• /
• pp.161-165
• /
• 2014

In this paper, we proposed the fuzzy prototype pattern classifier. In the proposed classifier, each prototype is defined to describe the related sub-space and the weight value is assigned to the prototype. The weight value assigned to the prototype leads to the change of the boundary surface. In order to define the prototypes, we use Fuzzy C-Means Clustering which is the one of fuzzy clustering methods. In order to optimize the weight values assigned to the prototypes, we use the Differential Evolutionary Algorithm. We use Linear Discriminant Analysis to estimate the coefficients of the polynomial which is the structure of the consequent part of a fuzzy rule. Finally, in order to evaluate the classification ability of the proposed pattern classifier, the machine learning data sets are used.