• 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 Distribution Science
• /
• v.12 no.4
• /
• pp.31-39
• /
• 2014

Purpose - This study investigates the following two issues. First, we attempt to find the important determinants of housing investment and to identify their significance rank using survey panel data. Recently, the expansion of global uncertainty in the real estate market has directly and indirectly influenced the Korean housing market; households demonstrate a sensitive reaction to changes in that market. Therefore, this study aims to draw conclusions from understanding how the impact of financial strength of the household is related to house investment. Second, we attempt to verify the effectiveness of diverse indices of financial strength such as DTI, LTV, and PIR as measures to monitor the housing market. In the continuous housing market recession after the global crisis, the government places top priority on residence stability. However, the government still imposes forceful restraints on indices of financial strength. We believe this study verifies the utility of these regulations when used in the housing market. Research design, data, and methodology - The data source for this study is the "National Survey of Tax and Benefit" from 2007 (1st) to 2011 (5th) by the Korea Institute of Public Finance. Based on this survey data, we use panel data of 3,838 households that have been surveyed continuously for 5 years. We sort the base variables according to relevance of house investment criteria using the decision tree model (DTM), which is the standard decision-making model for data-mining techniques. The DTM method is known as a powerful methodology to identify contributory variables for predictive power. In addition, we analyze how important explanatory variables and the financial strength index of households affect housing investment with the binary logistic multi-regressive model. Based on the analyses, we conclude that the financial strength index has a significant role in house investment demand. Results - The results of this research are as follows: 1) The determinants of housing investment are age, consumption expenditures, income, total assets, rent deposit, housing price, habits satisfaction, housing scale, number of household members, and debt related to housing. 2) The impact power of these determinants has changed more or less annually due to economic situations and housing market conditions. The level of consumption expenditure and income are the main determinants before 2009; however, the determinants of housing investment changed to indices of the financial strength of households, i.e., DTI, LTV, and PIR, after 2009. 3) Most of all, since 2009, housing loans has been a more important variable than the level of consumption in making housing market decisions. Conclusions - The results of this research show that sound financing of households has a stronger effect on housing investment than reduced consumption expenditures. At the same time, the key indices that must be monitored by the government under economic emergency conditions differ from those requiring monitoring under normal market conditions; therefore, political indices to encourage and promote the housing market must be divided based on market conditions.

• Journal of the Korea Academia-Industrial cooperation Society
• /
• v.17 no.6
• /
• pp.379-388
• /
• 2016

High school and college students majoring in dance have different types of stress because of their different circumstances and goals. The purpose of this study was to investigate the relation between multidimensional perfectionism and eating disorder in high school and college students who are majoring in dance. Questionnaires for eating disorder (Eating Disorder Inventory-2(EDI-2) made by Garner (1990) and adapted by Lee (1998)) and multidimensional perfectionism (Multidimensional Perfectionism Scale(F-MPS) made by Frost (1990) and translated by Hyun (1992) were utilized after the sentences in the questionnaires were partially revised and (rendered more appropriate for?) the purpose of this study. The questionnaires were completed by all of the subjects (n=250), but 32 of them were excluded due to insincere answers. Thus, a total of 218 questionnaires were analyzed using SPSS version 21.0. The results showed that the students with a higher education level and who were more career oriented were more likely to suffer from multidimensional perfectionism and eating disorder. In addition, multidimensional perfectionism (concern about mistakes, constant personal and parental expectation) resulted in the development and maintenance of eating disorder for the students majoring in dance. In conclusion, higher education level and greater career orientation induce greater stress in dance major students and cause them to have an incorrect physical image. Thus, these factors may cause higher psychological pressure leading to multidimensional perfectionism and eating disorder. Therefore, these students need to know how to correctly manage their body weight and how to prevent eating disorder.

• Archives of design research
• /
• v.20 no.3 s.71
• /
• pp.141-150
• /
• 2007

This study began with the question: "what influence would the width of river surface have on visual preference, provided that the environment surrounding the river does not change?" to evaluate the visual preference factors of the river scenery which could vary according to the change of water level. To estimate the minimum flow needed for river sceneries, field survey of Youngsan river was carried out to collect the field data and evaluated the visual preference factors to obtain a most preferred W/B ratio. At Youngsan bridge location, the feeling of open space factors, physical characteristic factors and complexity factors appeared to have significant relations to visual preferences. At Imgok bridge location, complexity factors, aesthetic factors and physical characteristic factors have significance to visual preferences. As a result of multi regression modeling, it was found that physical factors affected visual preferences the most at urban river locations and complexity factors affected the most visual preferences at rural river locations. As a results of this study, the most preferred W/B ratio was estimated as which vary from 0.5 to 0.7 and this results can contribute to the field of river landscape design to maximize the users' satisfaction level.

• Quality Improvement in Health Care
• /
• v.9 no.2
• /
• pp.116-133
• /
• 2002

Background : It is very common in Korea to take care of non-acute patients in an acute setting, due to the lack of long-term facilities. Long term hospitalization increase medical expenses and decreases the bed utilization, which can affect the urgent and emergent admissions, and eventually jeopardize the hospital financially. In this study, strategies for effective transfers to the lower levels of care, and to decrease the length of stay were presented by surveying and analyzing the patient's knowledge of the transfer needs, and the willingness to transfer those whose hospital length of stay was more than 30days. Method : The survey is subject to a group of 251 patients who have been hospitalized over 30 days in a general hospital in Seoul. Excluding those that were in the Intensive Care Unit and psychiatric ward, 214 in-patients were used as participants. They were surveyed from April 9, 2002 to April 17, 2002. One hundred and thirty seven out of 214 were responded which made the response rate 64%. Data were analyzed by SAS and SPSS. Result : Multi-variable Logistic Regression Analysis showed a significant effect in medical expenses, knowledge of referral system and the information of the receiving hospital. The financial burden in medical expenses made the patient 10.7 times more willing to be transferred, knowledge of the referral system made them 5 times more willing to be transferred, and the information of receiving hospital makes 6.5 times more willing to be transferred. Reasons for willing to be transferred to a lower level of care were the phase of physical therapy, the distance from home, the attending physician's advice and being unable to be treated as an out patient. Reasons for refusing to be transferred were the following. The attending physician's competency, not being ready to be discharged, not trusting the receiving hospital's competency due to the lack of information, or never hearing about the referring system by the attending physician. Conclusion : Based on this, strategies for the effective transfer to the lower levels of care were suggested. It is desirable for the attending physician to be actively involved by making an effort to explain the transfer need, and referring to the Healthcare Coordinating Center, which can help the patient make the right decision. Nationwide networking for the referral system is the another key factor that may need to be suggested as an alternative to decrease the medical expenses. Collaborating with the Home Health Agency for the early discharge planning and the Social Service Department for financial aid are also needed. It is recommended that the hospital should expedite the transfer process by prioritizing the cost and the information as medical expenses, knowledge of referring system and the information of the receiving hospital, are the most important factors to the willingness to transfer to a lower level of care.

• Asia-Pacific Journal of Business Venturing and Entrepreneurship
• /
• v.9 no.3
• /
• pp.119-128
• /
• 2014

One of the theoretically and empirically grounded black boxes in HRD and firm performance link is employee' attitudes such as organizational commitment and job satisfaction. However, most studies were conducted with the regression analysis at the organizational level. This study used HLM(hierarchical linear modeling) analysis, which made it possible to estimate more accurate relationship between variables that were measured from two different levels. In addition, this study attempted to open an the black box(learning culture) in the relationship between HRD and employee attitudes. The result showed that the HRD have a positive effect on the organizational commitment and the job satisfaction. Also the HRD showed full mediation effect of organization commitment and the job satisfaction on the Learning culture. And the result showed that the HRD in 2007 have a positive effect on employee' attitudes in 2009. These findings concluded that systematic HRD like employee's education and training must be built and also the positive culture for employee's learning like support of management's learning organization must be improved in order to promote the organizational performance(organizational commitment, job satisfaction) in company.

• Journal of the Korean Institute of Landscape Architecture
• /
• v.32 no.2
• /
• pp.11-24
• /
• 2004

The purpose of this study is to present data on the human activities responding to the physical environment of ‘Ulsan’s Grand Parks by evaluating user behavior and activity, visiting motivations, and user satisfaction. This study was conducted using multi-methods such as interviews and questionnaires surveys. The main findings of this study can be summarized in six parts as follows: \circled1 Behavior patterns showed that the users visited the park left within 30 minutes and the frequency of visits was 1 or 2 times per week. They spent their time mostly on ‘walking’ and ‘picnicking’. The users visited regardless of the seasons or the day of the week. \circled2 The priorities for improvements were analyzed as follows: the users expressed their demands for ‘shadowing facilities’ like shelters and pergolas because they used these facilities frequently. Also, the users would like an ‘event program’, ‘sign system’ and ‘guide program’. \circled3 Analysis of the the user’s perception of the park showed that they perceive the park as ‘representative source of the landscape and open space in Ulsan and place for making contact with nature. \circled4 In examining the visiting motivations of the users of Ulsan Grand Park, it was revealed that people use the park for ‘time with family and friends’, ‘to escape from city life’, ‘to relieve fatigue. As a result of factor analysis, 4 factors were identified such as ‘physical motive(MF1)’, ‘exploratory motive(MF2)’, ‘social motive(MF3)’ and ‘emotional motive(MF4). \circled5 Park users’ evaluation for park facilities showed that people are satisfied with most of the facilities and especially, they have high level of satisfaction for ‘footpaths’, ‘squares’ and ‘picnicspace’. The evaluation of the park user’s of activity reveals that they are content with nearly all the variables. Especially, they have high level of satisfaction for the variables of ‘convenience for dynamic activities’, ‘making of a beautiful atmosphere, ‘accessibility from the outside’ and, ‘convenience in group activitie. Factor analysis of the park user’s of activity revealed 5 factors such as ‘convenience and interest factor (AF1)’, ‘park maintenance, management and use program(AF2)’, ‘visual beauty(AF3)’, ‘safety and accessibility(AF4)’ and ‘crowding(AF5)’. \circled6 Regression analysis was employed to get the predictor factors of overall satisfaction with a result of 60.0%($R^2$). The variance was explained as ‘quality of the picnic space’, ‘convenience and interest factor while using the park’, ‘park program for maintain and management in the park’, ‘visually beauty while using the park’, ‘safety and accessibility of the parks’, ‘quality of the pond’, ‘crowding’, ‘quality of the square’.

• Journal of the Korea Academia-Industrial cooperation Society
• /
• v.17 no.10
• /
• pp.382-395
• /
• 2016

The purpose of this study is to examine how area characteristics influence the health of a population in a particular area by investigating how area deprivation and social capital influence self-rated health. For this study, a multi-level logistic regression was employed to analyze the data collected by Community Health Survey conducted on a target population of 229,186 living at 253 administrative areas of Korea in 2011. First, an analysis was conducted for subjects who have rated their self-health assessment as 'fair', 'poor', and 'very poor' in a 5 -item response survey. Then, a second analysis was conducted for the same subjects by excluding those with a rating of 'fair'. As a result, we found that area deprivation significantly influenced the population's health, according to our second analysis, while it was not significant according to our first analysis. Moreover, social capital was not significant in both analyses. Area deprivation-although the value of it was not so high-seems to explain the differences of individual self-rated health assessment as a contextual effect. In addition, influence of area characteristics is not limited to certain local areas, but to all local areas of Korea. Therefore, it is suggested that efforts to improve area characteristics are necessary to upgrade the individual's health level. A standardized classification system-distinguishing between good and poor self-rated health-is necessary through further comparative studies on self-rated health assessment.

• Korean Journal of Remote Sensing
• /
• v.18 no.4
• /
• pp.209-220
• /
• 2002

We carried out studies on SAR image intensity and interferometric phase over oyster sea farms. Strong backscattering was observed in amplitude images, and that was considered as a radar signal double bouncing from horizontal bars. These sea farming structures are not visible in satellite optical images except IKONOS image, so that it demonstrates the value of radar remote sensing as an effective tool in support of sea farm detection. The intensity of the image is sensitive to system parameters including wavelength, polarization, and look direction, but does not correlate to tide height. We found that the strongest backscattering can be obtained by L-band HH-polarization with a look direction perpendicular to the horizontal bar. We also succeeded in generating 21 coherent JERS-1 SAR interferometric pairs over the oyster farms. The general trend of the fringe rate of the interferometric phases appeared to be governed by altitude of ambiguity. The general trend was modeled by an inverse function and removed to have a residual phase. The residual phase showed a linear relation with the tide height. The results demonstrate for the first time that SAR can possibly be used to estimate sea level. However, the r.m.s. error of a regression line is 11.7 cm, and that is so far too large to make reliable assessments of sea level in practical applications. Further studies is required to improve the accuracy specifically using multi-polarization SAR data.

• Journal of the Korean Regional Science Association
• /
• v.36 no.4
• /
• pp.3-23
• /
• 2020

This study aims to conceptualize the settlement inclusivity for overcoming social exclusion and the decline in quality of life of older people and to examine its effects on their mental health. The concept of the settlement inclusivity for older people focuses on the immediate environment around the place where they live. We proposed two domains for the conceptual framework; social domain that provides opportunities for community cohesion; spatial domain that provides security of residential area and access to basic services within walking distance. The social domain was represented by participation and interdependence, while the spatial domain by security and accessibility in the settlement inclusivity. Zero-inflated negative binomial regression model was constructed with 2017 National Survey of Older Koreans data to analyze the factors influencing depressive symptoms of older adults. The empirical results demonstrate that increased level of neighborhood network and social participation is associated with a decrease in the number of depressive symptoms. In addition, higher satisfaction in neighborhood environment and good accessibility to public transport/stores are associated with fewer depressive symptoms. Finally, housing condition and home ownership have a moderating effect on the relationship between social network/participation and depressive symptoms level, whereas they have no direct effects on depressive symptoms. This study demonstrates multi-dimensionally and mutually significant associations between settlement inclusivity and depressive symptoms for older people providing implications for urban planning and policies to improve mental well-being of older population.