• Journal of Intelligence and Information Systems
• /
• v.18 no.2
• /
• pp.29-45
• /
• 2012

Bond rating is regarded as an important event for measuring financial risk of companies and for determining the investment returns of investors. As a result, it has been a popular research topic for researchers to predict companies' credit ratings by applying statistical and machine learning techniques. The statistical techniques, including multiple regression, multiple discriminant analysis (MDA), logistic models (LOGIT), and probit analysis, have been traditionally used in bond rating. However, one major drawback is that it should be based on strict assumptions. Such strict assumptions include linearity, normality, independence among predictor variables and pre-existing functional forms relating the criterion variablesand the predictor variables. Those strict assumptions of traditional statistics have limited their application to the real world. Machine learning techniques also used in bond rating prediction models include decision trees (DT), neural networks (NN), and Support Vector Machine (SVM). Especially, SVM is recognized as a new and promising classification and regression analysis method. SVM learns a separating hyperplane that can maximize the margin between two categories. SVM is simple enough to be analyzed mathematical, and leads to high performance in practical applications. SVM implements the structuralrisk minimization principle and searches to minimize an upper bound of the generalization error. In addition, the solution of SVM may be a global optimum and thus, overfitting is unlikely to occur with SVM. In addition, SVM does not require too many data sample for training since it builds prediction models by only using some representative sample near the boundaries called support vectors. A number of experimental researches have indicated that SVM has been successfully applied in a variety of pattern recognition fields. However, there are three major drawbacks that can be potential causes for degrading SVM's performance. First, SVM is originally proposed for solving binary-class classification problems. Methods for combining SVMs for multi-class classification such as One-Against-One, One-Against-All have been proposed, but they do not improve the performance in multi-class classification problem as much as SVM for binary-class classification. Second, approximation algorithms (e.g. decomposition methods, sequential minimal optimization algorithm) could be used for effective multi-class computation to reduce computation time, but it could deteriorate classification performance. Third, the difficulty in multi-class prediction problems is in data imbalance problem that can occur when the number of instances in one class greatly outnumbers the number of instances in the other class. Such data sets often cause a default classifier to be built due to skewed boundary and thus the reduction in the classification accuracy of such a classifier. SVM ensemble learning is one of machine learning methods to cope with the above drawbacks. Ensemble learning is a method for improving the performance of classification and prediction algorithms. AdaBoost is one of the widely used ensemble learning techniques. It constructs a composite classifier by sequentially training classifiers while increasing weight on the misclassified observations through iterations. The observations that are incorrectly predicted by previous classifiers are chosen more often than examples that are correctly predicted. Thus Boosting attempts to produce new classifiers that are better able to predict examples for which the current ensemble's performance is poor. In this way, it can reinforce the training of the misclassified observations of the minority class. This paper proposes a multiclass Geometric Mean-based Boosting (MGM-Boost) to resolve multiclass prediction problem. Since MGM-Boost introduces the notion of geometric mean into AdaBoost, it can perform learning process considering the geometric mean-based accuracy and errors of multiclass. This study applies MGM-Boost to the real-world bond rating case for Korean companies to examine the feasibility of MGM-Boost. 10-fold cross validations for threetimes with different random seeds are performed in order to ensure that the comparison among three different classifiers does not happen by chance. For each of 10-fold cross validation, the entire data set is first partitioned into tenequal-sized sets, and then each set is in turn used as the test set while the classifier trains on the other nine sets. That is, cross-validated folds have been tested independently of each algorithm. Through these steps, we have obtained the results for classifiers on each of the 30 experiments. In the comparison of arithmetic mean-based prediction accuracy between individual classifiers, MGM-Boost (52.95%) shows higher prediction accuracy than both AdaBoost (51.69%) and SVM (49.47%). MGM-Boost (28.12%) also shows the higher prediction accuracy than AdaBoost (24.65%) and SVM (15.42%)in terms of geometric mean-based prediction accuracy. T-test is used to examine whether the performance of each classifiers for 30 folds is significantly different. The results indicate that performance of MGM-Boost is significantly different from AdaBoost and SVM classifiers at 1% level. These results mean that MGM-Boost can provide robust and stable solutions to multi-classproblems such as bond rating.

• Journal of Intelligence and Information Systems
• /
• v.24 no.4
• /
• pp.137-154
• /
• 2018

Animal infectious diseases, such as avian influenza and foot and mouth disease, occur almost every year and cause huge economic and social damage to the country. In order to prevent this, the anti-quarantine authorities have tried various human and material endeavors, but the infectious diseases have continued to occur. Avian influenza is known to be developed in 1878 and it rose as a national issue due to its high lethality. Food and mouth disease is considered as most critical animal infectious disease internationally. In a nation where this disease has not been spread, food and mouth disease is recognized as economic disease or political disease because it restricts international trade by making it complex to import processed and non-processed live stock, and also quarantine is costly. In a society where whole nation is connected by zone of life, there is no way to prevent the spread of infectious disease fully. Hence, there is a need to be aware of occurrence of the disease and to take action before it is distributed. Epidemiological investigation on definite diagnosis target is implemented and measures are taken to prevent the spread of disease according to the investigation results, simultaneously with the confirmation of both human infectious disease and animal infectious disease. The foundation of epidemiological investigation is figuring out to where one has been, and whom he or she has met. In a data perspective, this can be defined as an action taken to predict the cause of disease outbreak, outbreak location, and future infection, by collecting and analyzing geographic data and relation data. Recently, an attempt has been made to develop a prediction model of infectious disease by using Big Data and deep learning technology, but there is no active research on model building studies and case reports. KT and the Ministry of Science and ICT have been carrying out big data projects since 2014 as part of national R &D projects to analyze and predict the route of livestock related vehicles. To prevent animal infectious diseases, the researchers first developed a prediction model based on a regression analysis using vehicle movement data. After that, more accurate prediction model was constructed using machine learning algorithms such as Logistic Regression, Lasso, Support Vector Machine and Random Forest. In particular, the prediction model for 2017 added the risk of diffusion to the facilities, and the performance of the model was improved by considering the hyper-parameters of the modeling in various ways. Confusion Matrix and ROC Curve show that the model constructed in 2017 is superior to the machine learning model. The difference between the2016 model and the 2017 model is that visiting information on facilities such as feed factory and slaughter house, and information on bird livestock, which was limited to chicken and duck but now expanded to goose and quail, has been used for analysis in the later model. In addition, an explanation of the results was added to help the authorities in making decisions and to establish a basis for persuading stakeholders in 2017. This study reports an animal infectious disease prevention system which is constructed on the basis of hazardous vehicle movement, farm and environment Big Data. The significance of this study is that it describes the evolution process of the prediction model using Big Data which is used in the field and the model is expected to be more complete if the form of viruses is put into consideration. This will contribute to data utilization and analysis model development in related field. In addition, we expect that the system constructed in this study will provide more preventive and effective prevention.

• The Journal of Korean Academy of Prosthodontics
• /
• v.52 no.4
• /
• pp.287-297
• /
• 2014

Purpose: The purpose of this study is to examine the impacts of infection control education on dental hygienists' perceptions for hepatitis B and their behaviors. Materials and methods: Study participants were chosen by random selection among dental hygienists working in Seoul, Korea. A total of 150 questionnaires were sent out for the survey from April 2013 to May 2013, of which 140-excluding incomplete responses-were used for the study. Chi-square tests and t-tests were used (SPSS 19.0), and post-hoc analysis was performed as well. The maximum significance level was 0.05. Results: Average 1.53 times infection control education was taken, but dental hygienists' perceptions for hepatitis B and their behaviors did not show statistical differences whether the education was done or not. Practices to prevent infection showed differences depending on categories, especially disinfection and sterilization were well performed by educated group. The most common reasons for not taking the education and noncompliance with infection prevention guidelines are lack of time and opportunity due to busy schedule. Conclusion: 1. The more highly educated, the greater number of patients per day, and the greater size of hospitals, the better infection control education was conducted. 2. Although hepatitis B is one of the most common chronic liver diseases in Korea, no significant correlation between perceptions of hepatitis B and infection control education was found. 3. Dental hygienists who received infection control education performed more efficient practices for protection against infections than those who did not.

• Journal of Animal Science and Technology
• /
• v.54 no.2
• /
• pp.83-87
• /
• 2012

The purpose of this study was to estimate genetic parameters for productive traits in swine. Productive traits were considered on average daily gain (ADG), body height (BH) and body length (BL). Genetic analysis was consisted of 18,668 heads for productive traits which were based on on-farm performance tested from May, 2007 to Apr, 2011. For estimating genetic parameters on productive traits, single best model was fitted after finding source of variance on fixed and random effects and estimated with a multiple trait animal model by using DF-REML (Derivative-Free Restricted Maximum Likelihood). The estimated heritabilities of Duroc, Berkshire, Landrace and Yorkshire 0.22-0.58 for the average daily gain, 0.34-0.41 for the body height and 0.4-0.52 for the body length, respectively. Phenotypic correlations of average daily gain with body height and body length for the four breeds were 0.42-0.48, 0.53-0.58, 0.34-0.46 and 0.47-0.56, respectively. Phenotypic correlations of body height with body length were 0.41, 0.57, 0.52, 0.59, respectively. The estimated genetic correlation coefficients of average daily gain with body height and body length estimated for the four breeds were 0.34-0.47, 0.70-0.75, 0.17-0.38 and 0.50-0.53, respectively. The estimated genetic correlation coefficients of body height with body length were 0.57, 0.69, 0.61 and 0.71, respectively.

• Journal of Korean Society of Forest Science
• /
• v.90 no.4
• /
• pp.565-572
• /
• 2001

The spatial genetic structure of Needle fir(Abies holophylla Max.) seedlings on forest gap within a Needle fir forest at Mt. Odae in Korea was analyzed on the basis of ISSR(inter-simple sequence repeats) marker analysis. The gap size was $1,500m^2(50m{\times}30m)$, and we sampled 416 one- or two-year-old seedlings by 2m intervals. Some trees at the upper crown layer except Needle firs and all trees at the middle and lower crown layers were removed, and Needle firs at the upper crown layer showed very weak growth strength or to be withering to death. The results of spatial autocorrelation using 31 polymorphic ISSR markers revealed that it was genetically homogeneous within spatial distance of 15.6m and the randomness of genetic distribution was from 15.6m to 31.2m. The genetic patch size of seedlings in forest gap might be restricted by the density of mother trees, making allow for the average height of adult Needle firs, the seed dispersal area, and the average distance between adults. For the directionality of seedling distribution, we investigated the variography using 'genetic configuration' which was the value of configuration in Multidimensional Scaling by genetic distance. In directional variogram, the increment of spatial distance from East to West direction was inversely proportional to genetic homogeneity. We presumed that this anisotrophy of seedling distribution at this forest gap resulted from the directionality of seed dispersal rather than the difference of fecundity between mother trees or the microhabitat variation, taking the evenness of forest floor condition, a vast seed production and the random distribution of seedlings at the studied site into consideration.

• The Journal of Korean Society for Radiation Therapy
• /
• v.29 no.2
• /
• pp.53-64
• /
• 2017

Purpose: To evaluate the usefulness of the $HexaPOD^{TM}$ evo RT system(6DoF couch) and the tendency of dose difference according to size of rotational direction error for volumetric rotational modulated radiotherapy(V-MAT) in patients with long target lengths. Therefore, it is suggested to recommend the need for rotational error correction. Materials and Methods: Ten patients with Esophagus cancer or Breast cancer including SCL treated with HexaPOD 6DoF(Six-Degree of Freedom) couch were included in this study. 6DoF couch was used to measure the difference in dose according to the rotation error in the directions of Rx(pitch), Ry(roll), and Rz(yaw). Each rotation error was applied. Positioning variation on x, y and z axis was verified and random variations were made by 6DoF couch with positioning variation. Modified DQA is conducted and point dose and gamma value are analyzed and compared. In addition, after applying the rotation error every $1^{\circ}$ to treatment plans of each target with a diameter of 3 cm, 5, 10, 15, and 20 cm respectively, gamma passing rate is being monitored by its aspect of change according to types and sizes of the target length and rotation error. Results: Mean error of the point dose and Gamma passing rate when the position variation was applied were $2.50{\pm}1.11%$ and $84.1{\pm}7.39%$ in the Rx direction, $2.36{\pm}1.16%$, and $81.0{\pm}8.49%$ in the Ry, $2.35{\pm}1.10%$ and $84.4{\pm}6.99%$ in the Rz direction, respectively. As a result of analysis on gamma passing rate according to types and sizes of the target length and rotation error, the gamma passing rate tended to decrease with increasing rotation error in the Rx and Rz directions except Ry direction. In particular, the lowest gamma passing rate (74.2 %) was in the case of $2.5^{\circ}$ rotation error in Rz direction of the target of 10 cm. Conclusion: The correction of the rotational error is needed for volumetric modulated radiotherapy of the treatment area with a long target length, and the use of 6DoF couch will improve the reproducibility of the patient position and the quality of the treatment.

• Women's Health Nursing
• /
• v.7 no.1
• /
• pp.93-106
• /
• 2001

The purpose of this study is to provide the basic data in order to develop of some educational programs for increasing breast feeding by studying the female university student's knowledge and attitude on breast feeding, who will become a mother in future. The respondents of this research were selected at random for 462 female students at the university in Seoul and Kyongki area, and it was the period collected the data from Oct 28, 2000 to Nov 8, 2000. The method of study distributed the measuring tools of knowledge with 33 items and the tools of measurement with 20 items on the attitude of breast feeding to the respondents directly, and collected them. The data were analyzed to use SPSS program. Unpaired t-test, ANOVA, Pearson correlation coefficient and Multiple regression analysis were used for the calculation of difference between groups and the results were as follows ; 1. The breast feeding was 50.6% in the period of lactation for the respondents and the nuclear families were 81.7% in family constituent unit. In the future the wisher of breast feeding was 91.5%, the medical personnel was a major informer who enjoyed their best confidence, Besides the respond-ents responded that the proper period for education of the breast feeding was in a high school. 2. The level of Knowledge on breast feeding. The respondents's knowledge on breast feeding was average $16.40{\pm}4.59$ points on the basis of 33 points and On the merits and demerits ratio of breast feeding has shown highest but there was low in the field of such a concrete and practical plan as the estimate of breast feeding and the method and mindfulness for breast feeding. The higher grader, the college of the natural science showed significantly the higher points in the knowledge degree by respondents's characters and in such cases the persons of breast feeding or the informed of breast feeding by a medical personnel or the women of strong will for breast feeding action in the future. 3. The Attitude on breast feeding. There was relatively shown a positive attitude of the total average $60.50{\pm}7.59$ points and the average evaluation $3.04{\pm}.36$ points in the attitude on breast feeding. The attitude by each factors has the highest points in the practical action aspect but the lowest in the emotional aspect. The attitude on breast feeding by respondents's characters significantly showed a positive attitude in such cases the persons of breast feeding or the informed of breast feeding or the women of strong will for breast feeding action in the future. 4. Relation to knowledge and attitude on breast feeding. There was shown a correlation of definition in the relation to knowledge and attitude on breast feeding, 5.Factors which have an effect on knowledge and attitude on breast feeding. The factors which have an effect on knowledge of breast feeding were attitudes on breast feeding, graders, the college of natural science and the informed of breast feeding. Also the factors which have an effect on attitude on breast feeding were on will and knowledge on breast feeding, a large family, the informed of breast feeding. In conclusion, it will have to enforce a systematic education on the method of a practical breast feeding enlarged by a medical personnel and professional early enough as the information provision on breast feeding enables one to increase knowledge and attitude on it, besides it has relations with their practical will.

• Korean Journal of Occupational Health Nursing
• /
• v.6 no.2
• /
• pp.110-127
• /
• 1997

The aim of this study is to present the basic datum for the promotion of effectiveness and improvement of nursery tasks, by grasping the situation of operating room nurses tasks and the degree of their fatigue. For these researches, 70 nurses out of the operating rooms of 3 university-affiliated hospitals-two in Seoul and one in Pusan, were chosen at random by a non-probability sampling method. These researches were done from April 14 to April 26 in 1997 by questionairing method. The questionaire was composed of 30 items, which asks the examinees of their physical, mental, and neurosensory symptoms, with 10 items respectively. The reliability of the research instrument was turned out very high with Cronbach's ${\alpha}=.9376$. The datum were electronically processed using Statistics Program for Social Sciences(SPSS). The analysis of datum in this study has a general character, in which the demosociological character and the special ex-officio character was calculated by frequency and percentage. The situation of tasks in operating rooms was calculated by frequency and percentage. The fatigue of operating room nurses was calculated by average and standard deviation. To compare the fatigue with regard to the character of operating room nurse's tasks, t-test and F-test(ANOVA) were used after the character of variations, and the variations at the level of P<.05 which might have some meaning was verified after the fact with Duncan's Multiple Range(DMR). The results of this research are as follows : 1) The nurses working in operating rooms show their fatigue in three fields-in Group I physical symptoms 3.28, in Group III neurosensory symptoms 2.85, and in Group II mental symptoms 2.73, which shows I Dominant type (general type). 2) They complain, in Group I they are "feeling the heavy legs," 3.28 and in Group II they "occasionally forget soon what to do," 3.09. and in Group III, they "feel lumbago," 3.47, which is the highest rate of the three. The highest rate results from the character of their tasks, in which they have to move rapidly the heavy appliances and do their jobs standing many hours, especially wearing heavy radiation protector. 3) As to transportation, subway using group feel the greatest fatigue, 3.18(F=4.315, P=.008). 4) As to department, nurses in the orthopedic's surgery part feel the greatest fatigue, 3.26(F=2.040, P=.050). 5) As to the change of physical symptoms, the group answering that they found physical abnormality after working in operating rooms show the greatest fatigue, 3.12(t=-3.13, P=.003). 6) At to the general circumstances, the group answering that they receive insufficient consideration on their physical abnormality in their department, show the greatest fatigue, 3.10(F=3.200, P=0.47). 7) As to the relation with superior officers, the group answering that their superior officer has an impetuous temperament, show great fatigue, 3.11(F=4.855, P=.011). 8) As to the time of feeling fatigue, the fatigue reaches the highest point 1~2 hours after operations, 3.04(F=2.703, P=.046). 9) When they feel fatigue after scrub nurse duties, they feel the greatest fatigue 2 hours after the duties, 3.09( F=2.841, P=.038). 10) As to the operation instruments, when they use complex instruments borrowing from the outside in addition to the basic instruments, their fatigue becomes the greatest, 3.09(F=7.831, P=.000). 11) As to the kind of operation, when they participate in orthopedic's surgery operations, they feel the greatest fatigue, 3.18(F=4.362, P=.000). With the above results, it is proved that the degree of operating room nurses' fatigue is considerably high. So it may be concluded that the measure for lessening the fatigue should be find immediately, not on the level of personal matters but on the level of hospital nursing administration.

• Korea Journal of Hospital Management
• /
• v.9 no.1
• /
• pp.66-94
• /
• 2004

The objective of this study is to examine how to maximize the efficiency of hospital management by minimizing the unit cost of hospital operation. For this purpose, this paper proposes to develop a model of the profit maximization based on the cost minimization dictum using the statistical tools of arriving at the maximum likelihood values. The preliminary survey data are collected from the annual statistics and their analyses published by Korea Health Industry Development Institute and Korean Hospital Association. The maximum likelihood value statistical analyses are conducted from the information on the cost (function) of each of 36 hospitals selected by the random stratified sampling method according to the size and location (urban or rural) of hospitals. We believe that, although the size of sample is relatively small, because of the sampling method used and the high response rate, the power of estimation of the results of the statistical analyses of the sample hospitals is acceptable. The conceptual framework of analyses is adopted from the various models of the determinants of hospital costs used by the previous studies. According to this framework, the study postulates that the unit cost of hospital operation is determined by the size, scope of service, technology (production function) as measured by capacity utilization, labor capital ratio and labor input-mix variables, and by exogeneous variables. The variables to represent the above cost determinants are selected by using the step-wise regression so that only the statistically significant variables may be utilized in analyzing how these variables impact on the hospital unit cost. The results of the analyses show that the models of hospital cost determinants adopted are well chosen. The various models analyzed have the (goodness of fit) overall determination (R2) which all turned out to be significant, regardless of the variables put in to represent the cost determinants. Specifically, the size and scope of service, no matter how it is measured, i. e., number of admissions per bed, number of ambulatory visits per bed, adjusted inpatient days and adjusted outpatients, have overall effects of reducing the hospital unit costs as measured by the cost per admission, per inpatient day, or office visit implying the existence of the economy of scale in the hospital operation. Thirdly, the technology used in operating a hospital has turned out to have its ramifications on the hospital unit cost similar to those postulated in the static theory of the firm. For example, the capacity utilization as represented by the inpatient days per employee tuned out to have statistically significant negative impacts on the unit cost of hospital operation, while payroll expenses per inpatient cost has a positive effect. The input-mix of hospital operation, as represented by the ratio of the number of doctor, nurse or medical staff per general employee, supports the known thesis that the specialized manpower costs more than the general employees. The labor/capital ratio as represented by the employees per 100 beds is shown to have a positive effect on the cost as expected. As for the exogeneous variable's impacts on the cost, when this variable is represented by the percent of urban 100 population at the location where the hospital is located, the regression analysis shows that the hospitals located in the urban area have a higher cost than those in the rural area. Finally, the case study of the sample hospitals offers a specific information to hospital administrators about how they share in terms of the cost they are incurring in comparison to other hospitals. For example, if his/her hospital is of small size and located in a city, he/she can compare the various costs of his/her hospital operation with those of other similar hospitals. Therefore, he/she may be able to find the reasons why the cost of his/her hospital operation has a higher or lower cost than other similar hospitals in what factors of the hospital cost determinants.

• Research in Plant Disease
• /
• v.16 no.3
• /
• pp.238-246
• /
• 2010

In 2006 fall, a preliminary survey of viruses in two important medicinal plants, Cynanchum wilfordii and C. auriculatum, was conducted on the experimental fields at the Agricultural Research and Extension Services of Chungbuk province in Korea. On each experimental fields, percentage of virus infection was ranged from 20 to 80%, and especially an average of disease incidence propagated by roots was twice higher than that by seeds. The various symptoms were observed in Cynanchum spp. plants, such as mosaic, mottle, necrosis, yellowing, chlorotic spot and malformation etc. In electron microscopic examination of crude sap extracts, filamentous rod particles with 390-730 nm were observed in most samples. The virus particles were purified from the leaves of C. wilfordii with typical mosaic symptom, and the viral RNA was extracted from this sample containing 430-845 nm long filamentous rod. To identify the viruses, reverse transcription followed by PCR with random primers was carried out. The putative sequences of P3 and coat protein of potyvirus were obtained. From a BLAST of the two sequences, they showed 26-38% and 62-72% identities to potyviruses, respectively. In SDS-PAGE analysis, the subunit of coat protein was approximately 30.3 kDa, close to the coat protein of potyvirus. In bioassay with 21 species in 7 families, Chenopodium quinoa showed local lesion on inoculated leave and chlorotic spot on upper leave, but the others were not infected. RT-PCR detection using specific primer of C. wilfordii and C. auriculatum samples, all of 24 samples with virus symptom was positive, and five out of seven samples without virus symptom were also positive. On the basis of these data, the virus could be considered as a new member of potyvirus. We suggested that the name of the virus was Keunjorong mosaic virus (KjMV) after the common Korean name of C. wilfordii.