• Journal of Physiology & Pathology in Korean Medicine
• /
• v.23 no.6
• /
• pp.1460-1464
• /
• 2009

In spite of many studies on statistical model for pattern identifications (PIs), little attention has been paid to the complexity of pattern diagnosis processed by oriental physicians. The aim of this study is to develop a statistical diagnostic model which discriminates four PIs using multiple indicators in stroke. Clinical data were collected from 981 stroke patients and 516 data of which PIs were agreed by two independent physicians were included. Discriminant analysis was carried out using clinical indicators such as symptoms and signs which referred to pattern diagnosis, and applied to validation samples which contained all symptoms and signs manifested. Four Fischer's linear discriminant models were derived and their accuracy and prediction rates were 93.2% and 80.43%, respectively. It is important to consider the pattern diagnosis processed by oriental physicians in developing statistical model for PIs. The discriminant model developed in this study using multiple indicators is valid, and can be used in the clinical fields.

• Journal of KIISE:Software and Applications
• /
• v.32 no.8
• /
• pp.789-794
• /
• 2005

LDA (Linear Discriminant Analysis) provides the projection that discriminates the data well, and shows a very good performance for face recognition. However, since LDA provides only one transformation matrix over whole data, it is not sufficient to discriminate the complex data consisting of many classes like honan faces. To overcome this weakness, we propose a new face recognition method, called LDA mixture model, that the set of alf classes are partitioned into several clusters and we get a transformation matrix for each cluster. This detailed representation will improve the classification performance greatly. In the simulation of face recognition, LDA mixture model outperforms PCA, LDA, and PCA mixture model in terms of classification performance.

• The Korean Journal of Applied Statistics
• /
• v.22 no.4
• /
• pp.771-780
• /
• 2009

Cataract is the main cause of blindness and visual impairment, especially, age-related cataract accounts for about half of the 32 million cases of blindness worldwide. As the life expectancy and the expansion of the elderly population are increasing, the cases of cataract increase as well, which causes a serious economic and social problem throughout the country. However, the incidence of cataract can be reduced dramatically through early diagnosis and prevention. In this study, we developed a prediction model of cataracts for early diagnosis using hospital data of 3,237 subjects who received the screening test first and then later visited medical center for cataract check-ups cataract between 1994 and 2005. To develop the prediction model, we used random forests and compared the predictive performance of this model with other common discriminant models such as logistic regression, discriminant model, decision tree, naive Bayes, and two popular ensemble model, bagging and arcing. The accuracy of random forests was 67.16%, sensitivity was 72.28%, and main factors included in this model were age, diabetes, WBC, platelet, triglyceride, BMI and so on. The results showed that it could predict about 70% of cataract existence by screening test without any information from direct eye examination by ophthalmologist. We expect that our model may contribute to diagnose cataract and help preventing cataract in early stages.

• 한국지형공간정보학회:학술대회논문집
• /
• 1993.10a
• /
• pp.101-106
• /
• 1993

본 연구의 목적은 토지자원의 유효한 개발과 관리를 위해 원격탐사 자료 및 지상자료를 이용하여 토지 이용의 예측 모형을 정립하고 실제로 제주도 지역에 적용하여 그 실증을 거치는 것이었다. 본 토형은 계절분석(multi-date processing) 및 다중분석 (multi-file processing)기법을 채택하고 Markov의 확률 이전 계산법 및 판별 함수 (discriminant function) 계산법으로부터 합성 출현된 공간적/시간적 토지이용 투영방법을 채택하였다. 판별 함수 계산법은 토지이용 변화상의 최다 경향치를 산출하기 위해 제주도 경관 평면(landscape plane) 전지역의 각 화소(pixel)에 적용되고, 확률 이전 계산법은 특정 미래 시간 간극상에서 상이한 토지이용으로 변화하는 이들 화소의 수량을 결정한다. 본 합성 모형은 이렇게 토지이용 변화성(정성적)과 그 화소의 수량(정량적)을 결합하여 경관 평면상에서 미래의 토지이용 예측을 가능케하는 것이다.

• Journal of Korean Society on Water Environment
• /
• v.23 no.2
• /
• pp.260-265
• /
• 2007

This study was carried out to complement water quality standards and to establish new concept for water quality standards reflecting current state of water quality in small streams. By this purpose, discriminant analysis was performed and Water Quality Level Model (WQLM) was developed using the data such as EC, BOD, $COD_{Mn}$, SS, T-N, T-P, $NH_3-N$ in 224 agricultural streams. To give water quality level for water quality parameters, it divided into 20% respectively in the order of excellent water quality. On the basis of the lowest water quality level, water quality level of small streams is granted. As a result of it, number of stream corresponding to Level I was no, Level II was 2 streams, Level III was 22 streams, Level IV was 70 streams, and Level V was 130 streams. Average of water quality in each level was the highest in Level V. EC, SS, and T-N of 7 parameters were selected in variance concerned water quality level. By standardized canonical discriminant function coefficient, EC of three variances was the highest in 0.625 at the discriminant power. The next was T-N (0.509), SS (0.414). By discriminant function for water quality level, Level II was equal to $-2.973+19.376{\times}(EC)+0.647{\times}(T-N)+0.009{\times}(SS)$, Level III was equal to $-3.288+19.190{\times}(EC)+0.733{\times}(T-N)+0.041{\times}(SS)$, Level IV was equal to $-4.462+27.097{\times}(EC)+0.792{\times}(T-N)+0.053{\times}(SS)$, and Level V was equal to $-9.117+40.040{\times}(EC)+1.305{\times}(T-N)+0.111{\times}(SS)$. As a result of test at real agricultural watershed of Jeongan and Euidang in Gongju city, the fitness of WQLM was high to 88.78%. But, to get accomplished water quality assessment more exactly in agricultural streams, we had to concentrate and get vast data, and WQLM was modified and complemented continually.

• Information Systems Review
• /
• v.16 no.3
• /
• pp.113-134
• /
• 2014

Since a movie is an experience goods, purchase can be decided upon preliminary information and evaluation. There are ongoing researches on what impact online reviews might have on movie revenues. Whereas research in the past was focused on the effect of online reviews. The influence of online reviews appears to be significant in products like a movie because it is difficult to evaluate the feature prior to "consuming" the product. Since an online review is regarded to be objective, consumers find it more trustworthy. Contrary to prior research focused on movie review ratings and volume, we focus moves on movie features related specific reviews. This research proposes a predictive model for movie revenue generation. We decided 15 criteria to classify movie features collected from online reviews through the online review mining and made up feature keyword list each criterion. In addition, we performed data preprocessing and dimensional reduction for data mining through factor analysis. We suggest the movie revenue predictive model is tested using discriminant analysis. Following the discriminant analysis, we found that online review factors can be used to predict movie popularity and revenue stream. We also expect using this predictive model, marketers and strategic decision makers can allocate their resources in more parsimonious fashion.

• Journal of Digital Convergence
• /
• v.15 no.2
• /
• pp.121-133
• /
• 2017

The propose of study is to examine the characteristics of companies with high possibility to form an internal control weakness using forecasting model. This study use the actual listed/unlisted companies' data from K_financial institution. The first conclusion is that discriminant model is more valid than logit model to predict internal control weak companies. A discriminant model for predicting the vulnerability of internal control has high classification accuracy and has low the Type II error that is incorrectly classifying vulnerable companies to normal companies. The second conclusion is that the characteristic of weak internal control companies have a low credit rating, low asset soundness assessment, high delinquency rates, lower operating cash flow, high debt ratios, and minus operating profit to the net sales ratio. As not only a case of listed companies but unlisted companies which did not occur in previous studies are extended in this study, research results including the forecasting model can be used as a predictive tool of financial institutions predicting companies with high potential internal control weakness to prevent asset losses.

• Health Policy and Management
• /
• v.10 no.2
• /
• pp.1-21
• /
• 2000

This study reviewde various parametic and nonparametic method for forexasting hospital closures in Korea. We compared multivariate discriminant analysis, multivartiate logistic regression, classfication and regression tree, and neural network method based on hit ratio of each model for forecasting hospital closure. Like other studies in the literture, neural metwork analysis showed highest average hit ratio. For policy and business purposes, we combined the four analytical method and constructed a foreasting model that can be easily used to predict the probabolity of hospital closure given financial information of a hospital.

• Journal of Digital Convergence
• /
• v.13 no.12
• /
• pp.117-124
• /
• 2015

As the acceptance of statistical analysis has been increased because of Big Data, the needs for an advanced second generation of statistical analysis method like Structural Equation Model are also increasing. This study suggests how R-Program, as open software, can be utilized when Partial Least Square Model, one of the SEMs, is applied to statistical analysis. R is a free software as a part of GNU projects as well as a powerful and useful tool for statistical analysis including Big Data. The study utilized R and SmartPLS, a representative statistical package of PLS-SEM, and analyzed internal consistency reliability, convergent validity, and discriminant validity of the measurement model. The study also analyzed path coefficients and moderator effects of the structural model and compared the results, respectively. The results indicated that R showed the same results with SmartPLS on the measurement model and the structural model. Therefore, the study confirmed that R could be a powerful tool that is alternative to a commercial statistical package in the future.

• Journal of Internet Computing and Services
• /
• v.7 no.1
• /
• pp.75-89
• /
• 2006

This paper is concerned with analysing the bankruptcy prediction power of three models: Multivariate Discriminant Analysis(MDA), Logit Analysis, Neural Network. The research targeted the bankrupted companies after the foreign exchange crisis in 1997 to differentiate from previous research efforts, and all participating companies were randomly selected from the KSE listed companies belonging to manufacturing industry to improve prediction accuracy and validity of the model. In order to assure meaningful bankruptcy prediction, training data and testing data were not extracted within the corresponding period. The result is that prediction accuracy of neural networks is more excellent than that of logit analysis and MDA model when considering that execution of testing data was followed by execution of training data.