• Journal of Intelligence and Information Systems
• /
• v.26 no.2
• /
• pp.105-129
• /
• 2020

This study uses corporate data from 2012 to 2018 when K-IFRS was applied in earnest to predict default risks. The data used in the analysis totaled 10,545 rows, consisting of 160 columns including 38 in the statement of financial position, 26 in the statement of comprehensive income, 11 in the statement of cash flows, and 76 in the index of financial ratios. Unlike most previous prior studies used the default event as the basis for learning about default risk, this study calculated default risk using the market capitalization and stock price volatility of each company based on the Merton model. Through this, it was able to solve the problem of data imbalance due to the scarcity of default events, which had been pointed out as the limitation of the existing methodology, and the problem of reflecting the difference in default risk that exists within ordinary companies. Because learning was conducted only by using corporate information available to unlisted companies, default risks of unlisted companies without stock price information can be appropriately derived. Through this, it can provide stable default risk assessment services to unlisted companies that are difficult to determine proper default risk with traditional credit rating models such as small and medium-sized companies and startups. Although there has been an active study of predicting corporate default risks using machine learning recently, model bias issues exist because most studies are making predictions based on a single model. Stable and reliable valuation methodology is required for the calculation of default risk, given that the entity's default risk information is very widely utilized in the market and the sensitivity to the difference in default risk is high. Also, Strict standards are also required for methods of calculation. The credit rating method stipulated by the Financial Services Commission in the Financial Investment Regulations calls for the preparation of evaluation methods, including verification of the adequacy of evaluation methods, in consideration of past statistical data and experiences on credit ratings and changes in future market conditions. This study allowed the reduction of individual models' bias by utilizing stacking ensemble techniques that synthesize various machine learning models. This allows us to capture complex nonlinear relationships between default risk and various corporate information and maximize the advantages of machine learning-based default risk prediction models that take less time to calculate. To calculate forecasts by sub model to be used as input data for the Stacking Ensemble model, training data were divided into seven pieces, and sub-models were trained in a divided set to produce forecasts. To compare the predictive power of the Stacking Ensemble model, Random Forest, MLP, and CNN models were trained with full training data, then the predictive power of each model was verified on the test set. The analysis showed that the Stacking Ensemble model exceeded the predictive power of the Random Forest model, which had the best performance on a single model. Next, to check for statistically significant differences between the Stacking Ensemble model and the forecasts for each individual model, the Pair between the Stacking Ensemble model and each individual model was constructed. Because the results of the Shapiro-wilk normality test also showed that all Pair did not follow normality, Using the nonparametric method wilcoxon rank sum test, we checked whether the two model forecasts that make up the Pair showed statistically significant differences. The analysis showed that the forecasts of the Staging Ensemble model showed statistically significant differences from those of the MLP model and CNN model. In addition, this study can provide a methodology that allows existing credit rating agencies to apply machine learning-based bankruptcy risk prediction methodologies, given that traditional credit rating models can also be reflected as sub-models to calculate the final default probability. Also, the Stacking Ensemble techniques proposed in this study can help design to meet the requirements of the Financial Investment Business Regulations through the combination of various sub-models. We hope that this research will be used as a resource to increase practical use by overcoming and improving the limitations of existing machine learning-based models.

• Journal of Chest Surgery
• /
• v.38 no.4 s.249
• /
• pp.277-283
• /
• 2005

Arterial oxygen saturation $(SaO_2)$ instability frequently takes place after systemic-pulmonary shunt without shunt occlusion. We analyzed actual incidence and risk factors for $SaO_2$ instability after shunt operations, and possible mechanisms were speculated on. Material and Method: Ninety three patients, who underwent modified Blalock-Taussig shunt from January 1996 to December 2000, were enrolled in this study. Adequacy of shunt was verified in all patients, either by ensuing one ventricle or biventricular repair later on or by appropriate pulmonary artery growth on postoperative angiogram. Age, body weight, hemoglobin level at operation were 3 day to 36 years (median: 1.8 months), 2.5kg to 51kg (median: 4.1kg) and $10.7\~24.3$ gm/dL (median: 15.2 gm/dL) respectively. Preoperative diagnoses were functional single ventricle with pulmonary stenosis or atresia in 39, tetralogy of Fallot in 38 and pulmonary atresia with intact ventricular septum in 16. Pulmonary blood flow (PBF) was maintained pre-operatively by patent ductus or previous shunt in 64 and by forward flow through stenotic right ventricular outflow tract (RVOT) in 29. $SaO_2$ instability was defined as $SaO_2$ less than $50\%$ for more than 1 hour with neither anatomic obstruction of shunt nor respiratory problem. Result: 10 patients $(10.7\%)$ showed $SaO_2$ instability after shunt operation. After shunt occlusion was ruled out by echocardiogram, they received measures to lower pulmonary vascular resistance (PVR), which worked within a few hours in all patients. Risk factors for $SaO_2$ instability included older age at operation (p=0.039), lower preoperative $SaO_2$ (p=0.0001) and emergency operation (p=0.001). PBF through stenotic RVOT showed marginal statistical significance (p=0.065). Conclusion: $SaO_2$ instability occurs frequently after shunt operation, especially in patients with severe hypoxia pre-operatively or unstable clinical condition necessitating emergency operation. Temporary elevation of pulmonary vascular resistance is a possible mechanism in this specific clinical setting.

• Journal of the Korean Society for Marine Environment & Energy
• /
• v.19 no.3
• /
• pp.227-235
• /
• 2016

This paper emphasized the necessity of the marine spatial planning (MSP) through the analysis of the major developmental projects which could make a contradiction based on the adequacy of the site selection and environmental impacts. The conflicting affairs between space utilization and management plan happen in the following ways: marine renewable energy development, sand mining, reclamation, construction of golf course in coastal area, thermal effluent and waste heat, erosion causing port development. The conflict of stakeholder continues caused by the accumulated environmental impact. For the reasons mentioned above, we found two things. First, it is necessary to comprehend the fact of developmental planning and MSP. Second, it is still unsatisfactory to connect the relevance of laws related to the spatial planning. For the reinforcement of marine environmental policy management, it is necessary to consolidate the property of site selection and assessment of developmental scale. Especially, while the strategic environmental assessment is in progress based on site selection and property of scale, consistent diagnosis is needed in the following concerns: the fact of the marine spatial planning, the relevance between national developmental plan and regional developmental plan, fisheries regulation, marine protected animals. For the environmentally sound and sustainable development (ESSD), MSP should have to be prepared based in a way of top-down including coastal and EEZ plan, relevance of ocean-use zoning and sector planning, 3-D spatial information. And also integrated information system have to be prepared through high-tech marine spatial information. In conclusion, consistent and relevant strategy for MSP should have to include the whole information related to the maritime affairs such as harbor, fishing port, fishing ground, coastal management, marine ecosystem generally.

• Korean Journal of Cognitive Science
• /
• v.15 no.2
• /
• pp.1-15
• /
• 2004

The structure of sensibility from motion was developed for the purpose of understanding relationship between sensibilities and physical factors to apply it to dynamic visual display. Seventy adjectives were collected by assessing adequacy to express sensibilities from motion and reporting sensibilities recalled from dynamic displays with achromatic color. Various motion displays with a moving single dot were rated according to the degree of sensibility corresponding to each adjective, on the basis of the Semantic Differential (SD) method. The results of assessment were analyzed by means of the factor analysis to reduce 70 words into 19 fundamental sensibilities from motion. The Multidimensional Scaling (MDS) technique constructed the sensibility space in motion, in which 19 sensibilities were scattered with two dimensions, active-passive and bright-dark Motion types systemically varied in kinematic factors were placed on the two-dimensional space of motion sensibility, in order to analyze important variables affecting sensibility from motion. Patterns of placement indicate that speed and both of cycle and amplitude in trajectories tend to partially determine sensibility. Although color and motion affected sensibility according to the in dimensions, it seemed that combination of motion and color made each have dominant effect individually in a certain sensibility dimension, motion to active-passive and color to bright-dark.

• Journal of Nutrition and Health
• /
• v.42 no.1
• /
• pp.38-47
• /
• 2009

The purpose of the study was to develop an eating habit checklist for screening elementary school children at risk of inadequate micronutrient intake. Eating habits, food intake, and anthropometric data were collected from 142 children (80 boys and 62 girls) in the $4^{th}$ to $6^{th}$ grades of elementary schools. Percentage of Recommended Intakes (RI) and Mean Adequacy Ratio (MAR) of six micronutrients; vitamin A, riboflavin, vitamin C, calcium, iron, zinc, and the number of nutrients the children consumed below EAR among the six nutrients were used as indices to detect the risk of inadequate micronutrient intake. Pearson correlation coefficients were calculated between eating habit scores and inadequate micronutrient intake indices in order to select questions included in the checklist. Meal frequency, enough time for breakfast, regularity of dinner, appetite, eating frequencies of Kimchi, milk, fruits and beans showed significant correlations with indices of inadequate micronutrient intake. Stepwise regression analysis was performed to give each item a different weight by prediction strength. To determine the cut-off point of the test score, sensitivity, specificity, and positive predictive values were calculated. The 8-item checklist with test results from 0 to 12 points was developed, and those with equal or higher than 6 points were diagnosed as high-risk group of inadequate micronutrient intake, and those with 4 or 5 points were diagnosed as moderate-risk group. Among our subjects 14.1% was diagnosed as high-risk group, and 30.3% as moderate-risk group. The proportions of the subjects who consumed below EAR of all micronutrients but vitamin C were highest in the high-risk group, and there were significant differences in the proportions of the subjects with intake below EAR of all micronutrients except vitamin B6 among the three groups. This checklist will provide a useful screening tool to identify children at risk of inadequate micronutrient intake.

• Korean Journal of Construction Engineering and Management
• /
• v.12 no.6
• /
• pp.65-78
• /
• 2011

Construction business, which is complex and long-term business, requires accurate estimation and verification in construction costs and payment procedure from project planning to the completion of construction phase. And more importantly, it is necessary to investigate and determine the risk factors related to construction costs during the entire process including design planning, construction drawings, and quantity calculating. But, currently, it is not seem to be adequate to cope with the risk and increased construction costs against the operational budget in terms of actual costs when screening and estimating the bidding cost of public apartment. Therefore, this study selected and analyzed 40 sites' report of construction completion account from 2004 to 2010 focused on the adequacy on the modification of contract and design planning and on the complication of the budget in the beginning of the project. This study deducted various risk causes and results by analyzing actual costs according to year, architectural area, region, construction cost and sale/lease classification. We could find out construction risk according to annual variation of government policy and economy, and also deducted risk items by construction characteristic according to region and architectural area. Study result, we first found out the problems of lowest price award system according to the construction costs. The weight of the cost increase risk was analyzed that subcontract and material costs are very high. Roof and tile work were analyzed highly in subcontract cost risk and reinforcing bar and cement were analyzed highly in material cost risk, among direct construction cost. Finally, this study results could be used in comparing the categories of the construction costs made by specific construction process, belonging to the construction costs, with the operational budget made in the beginning of the project that can enable to grasp unpredictable risks over the construction costs and making quantitative analysis for it through analyzing the range of fluctuation and variations led by the fluctuations in the actual construction costs.

• Journal of Yeungnam Medical Science
• /
• v.16 no.2
• /
• pp.333-341
• /
• 1999

Background and Methods: In order to evaluate characteristics and modulatory factors of blood pressure in peritoneal dialysis(PD), studies were conducted on the 69 patients who had underwent peritoneal equilibration test(PET). Results: The results were as follows; 1) All patients received an antihypertensive drug before PD, but, 15 of 69 patients successfully quit taking the antihypertensive drug after peritoneal dialysis. 2) During peritoneal dialysis, mean arterial pressure(MAP) was significantly decreased for the first 3 months, and this lasted for 1 year, and antihypertensive drug requirements were significantly decreased continuously up to 9 months(p<0.05). 3) After changing the modality from hemodialysis to peritoneal dialysis, MAP(mmHg, from $107.0{\pm}4.5$ to $98.6{\pm}8.8$, p<0.05), antihypertensive drug requirements(from $5.6{\pm}2.6$, to $2.0{\pm}2.5$, p<0.01) and erythropoietin dosages(Uint/week, from $4600{\pm}2660$ to $2000{\pm}1630$, p<0.05) were decreased. 4) Multiple logistic regression analysis showed that MAP(p<0.01) and daily ultrafiltration volume(p<0.05) can contribute to the determination of antihypertensive drug requirements. However the relationship between antihypertensive drug requirements and PET results or dialysis adequacy indices(weekly Kt/V, weekly creatinine clearance) was not revealed. Conclusion: In conclusion, the prescription of antihypertensive drugs should be considered according to daily ultrafiltration volume, especially during first year after initiating PD, and follow-ups for over a year may be needed.

• Journal of Korean Home Economics Education Association
• /
• v.18 no.4 s.42
• /
• pp.67-84
• /
• 2006

This study was carried out to investigate nutrient intake, dietary self-efficacy, and physical activity self-efficacy of elementary school students by obesity index in Gyeongbuk area. The survey was conducted from June 7 to June 18 in 2005. The study was peformed by analyzing a questionnaire answered by 523 elementary school student in 5th and 6th grade. The obesity index was gained by height and weight data. Nutrient intakes was evaluated by 24hr-dietary record. Statistical data analysis were completed using the SPSS 12.0 program. The results were summarized as follows; The result of the body measurement was that 31.7% of underweight group, 45.1% of normal group, 12.8% of overweight group, 10.3% of obese group. 13.9% of underweight group experienced weight control, and 17.5% of the subject respond they will try the weight control in the future. Male students showed significantly higher exercise frequency than female students(p<0.001). Male underweight group and female obese group show the highest exercise frequency. Daily energy intake of the subject showed 80.1% in male students and 87.5% in female students revealed under the recommended dietary allowance(RDA) for Korean. The intake ratio of energy nutrients was identical in male and female of underweight group and obese group, so this showed that intake style was similar in two groups. By investigating through MAR(mean adequacy ratio), underweight group of male students and both normal and overweight group of female students were lowest, while overweight group of male students and underweight group of female students were the highest. Physical activity self-efficacy of male students was higher than female students, and physical activity self-efficacy by obesity index was higher in underweight group of male students and obese group in female.

• Journal of Environmental Impact Assessment
• /
• v.30 no.6
• /
• pp.339-354
• /
• 2021

The purpose of this study is to provide valuable information and data by analyzing the environmental status and potential forrenewable energy projects (or plans) based on environmental assessment (EA) data, so that more objective and scientific environmental assessments can be conducted. The study also suggests regional directions that could satisfy the goals of nature conservation and renewable energy. Based on the analysis of EA data that was conducted up until June 2019, the study analyzed the size, location and characteristics of both onshore wind power and onshore photovoltaic. The environmentally available potential by region was also derived by considering the main constraints and requirements related to the potential siting ofrenewable energy projects at the EA. Based on EA data, 63 out of 80 (79%) onshore wind power projects are shown to be located in mountainous areas. For onshore photovoltaic projects, a total of 7,363 projects were subjected to environmental assessment over the country. The environmentally potential area for onshore wind power, considering all the environmental regulatory factors, is 2,440 km². For onshore photovoltaic, the environmentally available area estimated as idle farmland is 2,877 km². The distribution and characteristics of the environmentally available potential of the region may be the most important factor that local governments should bear in mind in terms of promoting renewable energy development projects in the region. Based on the results of this study, even if we consider the national energy plan including the expected future increase, as well as environmental goals and socio-economic acceptance through an environmental assessment, the available resources forrenewable energy projects are not insufficient. It is possible to examine the adequacy of the target distribution rate of renewable energy sources by region taking into consideration the quantitative and scientific results such as the environmentally available potential data derived from this study.

• Korean Journal of Occupational Therapy
• /
• v.26 no.4
• /
• pp.57-72
• /
• 2018

Objective : This study aims to identify the self-reported driving abilities of elderly drivers and their correlations to the demographic factors that influence them, and to verify the adequacy of the hypothetical model, constructed based on vision, auditory, cognition, motor, and psychological factors, in order to present a path model on the self-reported driving abilities of elderly drivers. Methods : The participants in this study were 122 elderly drivers aged 65 years or older residing in the community. This study evaluated the following factors of the participants: Vision and hearing, motor ability, cognitive ability, depression, self-reported driving abilities. Results : The results of this study are as follows. In the case of men, the self-reported driving ability score was higher than for women, and those driving 6-7 days per week had higher scores than those driving 3 days or less. The period of holding a driver's license and driving experience positively correlated with self-reported driving abilities. The final model of factors influencing the self-reported driving abilities of elderly drivers had a p value (.911) exceeding .05; TLI (1.202), NFI (.949), and CFI (1.000) of over .90; and RMSEA (.000) of lower than 0.1, indicating that the hypothesis model fit the data well. First, the directly influential factors on the self-reported driving abilities of elderly drivers were depression, decreased hearing, and grip strength. Second, age was found to have a direct influence on depression and grip strength; moreover, depression and grip strength as a mediator indirectly influenced their self-reported driving abilities. Third, depression was found to have a direct influence on their delayed cognitive processing and grip strength. Conclusion : The significance of this study is in the identification of direct and indirect factors influencing the self-reported driving abilities of elderly drivers in regional communities, and in the verification of multi-dimensional effects of diverse factors influencing such abilities.