• Title/Summary/Keyword: Discriminant analysis

Search Result 1,590, Processing Time 0.029 seconds

A Study on the Face Recognition Using PCA Algorithm

  • Lee, John-Tark;Kueh, Lee-Hui
    • Journal of the Korean Institute of Intelligent Systems
    • /
    • v.17 no.2
    • /
    • pp.252-258
    • /
    • 2007
  • In this paper, a face recognition algorithm system using Principal Component Analysis (PCA) is proposed. The algorithm recognized a person by comparing characteristics (features) of the face to those of known individuals of Intelligent Control Laboratory (ICONL) face database. Simulations are carried out to investigate the algorithm recognition performance, which classified the face as a face or non-face and then classified it as known or unknown one. Particularly, a Principal Components of Linear Discriminant Analysis (PCA + LDA) face recognition algorithm is also proposed in order to confirm the recognition performances and the adaptability of a proposed PCA for a certain specific system.

Financial Distress Prediction Models for Wind Energy SMEs

  • Oh, Nak-Kyo
    • International Journal of Contents
    • /
    • v.10 no.4
    • /
    • pp.75-82
    • /
    • 2014
  • The purpose of this paper was to identify suitable variables for financial distress prediction models and to compare the accuracy of MDA and LA for early warning signals for wind energy companies in Korea. The research methods, discriminant analysis and logit analysis have been widely used. The data set consisted of 15 wind energy SMEs in KOSDAQ with financial statements in 2012 from KIS-Value. We found that five financial ratio variables were statistically significant and the accuracy of MDA was 86%, while that of LA is 100%. The importance of this study is that it demonstrates empirically that financial distress prediction models are applicable to the wind energy industry in Korea as an early warning signs of impending bankruptcy.

Development of Daily Hassles Scale for Children in Korea (한국아동의 일상적 스트레스 척도의 개발)

  • 한미현
    • Journal of the Korean Home Economics Association
    • /
    • v.33 no.4
    • /
    • pp.49-64
    • /
    • 1995
  • The purpose of this study was to develop the Daily Hassles Scale for children in Korea. The subject were 444 children of 184 fourth graders and 260 sixth graders selected form five elementary schools in Seoul(217 male and 227 female). A questionnaire consisting of 90-item daily hassles scale, demographic questions, and some additional questions was used as a methodological instrument. statistics used for data analysis were X2, cramer's V, factor analysis, multi-regression, Pearson's r, Cronbach's α. The major findings of this study were as follows. 1) 87 items of the 90-item scale were acceptible through item discriminant method. The discriminant coefficients of the items(Cramer's V) ranged form .28 to .73. 2) 6 factors(parents, home environment, friends, studies, teachers & school, the surroundings) were extracted from factor analysis. Multi-regression analysis conducted to reduce the length of scale have drawed 42 items for 'the Daily Hassles Scale for Children in Korea'. The correlation between this scale and the Quality of Life Scale(Olson & Barnes, 1982) was conducted to test the criterion-related validity, and the coefficient was significant(r=-.52, p<.001).3) Finally, reliability coefficients(Cronbach'α) of this scale was. 85.

  • PDF

Bankruptcy predictions for Korea medium-sized firms using neural networks and case based reasoning

  • Han, Ingoo;Park, Cheolsoo;Kim, Chulhong
    • Proceedings of the Korean Operations and Management Science Society Conference
    • /
    • 1996.10a
    • /
    • pp.203-206
    • /
    • 1996
  • Prediction of firm bankruptcy have been extensively studied in accounting, as all stockholders in a firm have a vested interest in monitoring its financial performance. The objective of this paper is to develop the hybrid models for bankruptcy prediction. The proposed hybrid models are two phase. Phase one are (a) DA-assisted neural network, (b) Logit-assisted neural network, and (c) Genetic-assisted neural network. And, phase two are (a) DA-assisted Case based reasoning, and (b) Genetic-assisted Case based reasoning. In the variables selection, We are focusing on three alternative methods - linear discriminant analysis, logit analysis and genetic algorithms - that can be used empirically select predictors for hybrid model in bankruptcy prediction. Empirical results using Korean medium-sized firms data show that hybrid models are very promising neural network models and case based reasoning for bankruptcy prediction in terms of predictive accuracy and adaptability.

  • PDF

Development of Behavior Problem Scale for Children and Adolescence (아동 및 청소년의 행동문제 척도 개발)

  • 김경연
    • Journal of Families and Better Life
    • /
    • v.16 no.4
    • /
    • pp.155-166
    • /
    • 1998
  • The purpose of this study was to develop ' the Behavior Problem Scale for Children and Adolescence' The 518 subjects were selected from 5th and 6th grades of elementary schools and first and second grades of middle schools in Pusan. Statistics used for data analysis were χ2 cramer's V, factor analysis multi-regression Pearson's r, Cronbach's a. The major finding of this study were as follows 1) 80 items of the 159 item scale were acceptable through item discriminant method The discriminant coefficients of the items(Cramer's V) ranged from .48 to .81. 2) 6 factors(shyness aggression hyperactivity withdrawal anxious immature) extracted from factor analysis,. Multi-regression analysis conducted to reduce the length of scale have drawn 42 items for 'the Behavior Problem Scale Children and Adolescence' 3) Reliability coefficients(Cronbach's a) of this scale was 94.

  • PDF

A Study on the Visual Evaluation about Combination of Contrary Clothing Image (상반되는 의복이미지의 조합에 따른 시각적 평가에 관한 연구)

  • 김유진;이경희
    • Journal of the Korean Society of Clothing and Textiles
    • /
    • v.21 no.8
    • /
    • pp.1297-1306
    • /
    • 1997
  • The purpose of this study was to investigate the difference of visual evaluation about combination of contrary clothing image, Elegance-Casual, Ethnic-Modern. The data were collected using 23 semantic differential hi-polar scale questionnaires from 50 female students majoring in clothing and textile and analyzed by Factor analysis, ANOVA, Discriminant analysis and MDS. The results obtained were summarized as follows; 1. As a result of factor analysis, 4 factors -Attractiveness, Casualness, Moderateness, Modernness-were found out as constructing factors of contrary clothing image. 2. For the visual evaluation of contrary clothing image combined with top and bottom, there were significant differences in all factors. 3. As a result of discriminant analysis, discrimination among images was more closely related to renovated image by combination of contrary clothing image. 4. As a result of MDS, evaluative dimensions of contrary clothing image were identified, and relationship between clothing images and special qualities of design was shown on positioning map.

  • PDF

How Consumers Differently Perceive about Green Market Environments: Across Different Consumer Groups in Green Attitude-behaviour Dimension

  • Kim, So-Yun;Rha, Jong-Youn
    • International Journal of Human Ecology
    • /
    • v.15 no.2
    • /
    • pp.43-57
    • /
    • 2014
  • Consumers differ with respect to the level of green attitudes and green purchase behavious and different consumer would have different perceptions on green market environment. This study attempted to explain how consumers perceive green market environment differently across different consumer groups in attitude-behaviour dimension in green consumption. After identifying the four consumer groups based on their attitude toward green purchase and green purchase behaviours, a multinomial logistic analysis and a stepwise discriminant analysis were conducted. This study found that reliability in green market was the most critical factor that contributes to enlarge positive green consumers. Also, the role of reference persons and adequate price of green products were also found to be important to stimulate green buying. By understanding the different role of those factors in each group of consumers, this study provided group-specific implications to expand green consumers.

Customer Classification Method for Household Appliances Industries with a Large Number of Incomplete Data (다수의 결측치가 존재하는 가전업 고객 데이터 활용을 위한 고객분류기법의 개발)

  • Chang, Young-Soon;Seo, Jong-Hyen
    • IE interfaces
    • /
    • v.19 no.1
    • /
    • pp.86-96
    • /
    • 2006
  • Some customer data of manufacturing industries have a large number of incomplete data set due to the customer's infrequent purchasing behavior and the limitation of customer profile data gathered from sales representatives. So that, most sophisticated data analysis methods may not be applied directly. This paper proposes a heuristic data analysis method to classify customers in household appliances industries. The proposed PD (percent of difference) method can be used for the discriminant analysis of incomplete customer data with simple mathematical calculations. The method is composed of variable distribution estimation step, PD measure and cluster score evaluation steps, variable impact construction step, and segment assignment step. A real example is also presented.

Characterization of Korean Porcelainsherds by Neutron Activation Analysis

  • Lee, Chul;Kang, Hyung-Tae;Kim, Seung-Won
    • Bulletin of the Korean Chemical Society
    • /
    • v.9 no.4
    • /
    • pp.223-231
    • /
    • 1988
  • Some pattern recognition methods have been used to characterize Korean ancient porcelainsherds using their elemental composition as analyzed by instrumental neutron activation analysis. A combination of analytical data by means of statistical linear discriminant analysis(SLDA) has resulted in removal of redundant variables, optimal linear combination of meaningful variables and formulation of classification rules. The plot in the first-to-second discriminant scores has shown that the three distinct territorial regions exist among porcelainsherds of Kyungki, Chunbuk-Chungnam, and Chunnam, with respective efficiencies of 20/30, 22/27 and 14/15. Similar regions have been found to exist among punchong porcelain and ceradonsherds of Kyungki, Chungnam and Chunbuk, with respective efficiencies of 7/9, 15/16 and 6/6. Classification has been further attempted by statistical isolinear multiple component analysis(SIMCA), using the sample set selected appropriately through SLDA as training set. For this purpose, all analytical data have been used. An agreement has generally been found between two methods, i.e., SLDA and SIMCA.

The Design of Pattern Classification based on Fuzzy Combined Polynomial Neural Network (퍼지 결합 다항식 뉴럴 네트워크 기반 패턴 분류기 설계)

  • Rho, Seok-Beom;Jang, Kyung-Won;Ahn, Tae-Chon
    • The Transactions of The Korean Institute of Electrical Engineers
    • /
    • v.63 no.4
    • /
    • pp.534-540
    • /
    • 2014
  • In this paper, we propose a fuzzy combined Polynomial Neural Network(PNN) for pattern classification. The fuzzy combined PNN comes from the generic TSK fuzzy model with several linear polynomial as the consequent part and is the expanded version of the fuzzy model. The proposed pattern classifier has the polynomial neural networks as the consequent part, instead of the general linear polynomial. PNNs are implemented by stacking the simple polynomials dynamically. To implement one layer of PNNs, the various types of simple polynomials are used so that PNNs have flexibility and versatility. Although the structural complexity of the implemented PNNs is high, the PNNs become a high order-multi input polynomial finally. To estimate the coefficients of a polynomial neuron, The weighted linear discriminant analysis. The output of fuzzy rule system with PNNs as the consequent part is the linear combination of the output of several PNNs. To evaluate the classification ability of the proposed pattern classifier, we make some experiments with several machine learning data sets.