• Journal of Intelligence and Information Systems
• /
• v.23 no.3
• /
• pp.139-153
• /
• 2017

Corporate bankruptcy can cause great losses not only to stakeholders but also to many related sectors in society. Through the economic crises, bankruptcy have increased and bankruptcy prediction models have become more and more important. Therefore, corporate bankruptcy has been regarded as one of the major topics of research in business management. Also, many studies in the industry are in progress and important. Previous studies attempted to utilize various methodologies to improve the bankruptcy prediction accuracy and to resolve the overfitting problem, such as Multivariate Discriminant Analysis (MDA), Generalized Linear Model (GLM). These methods are based on statistics. Recently, researchers have used machine learning methodologies such as Support Vector Machine (SVM), Artificial Neural Network (ANN). Furthermore, fuzzy theory and genetic algorithms were used. Because of this change, many of bankruptcy models are developed. Also, performance has been improved. In general, the company's financial and accounting information will change over time. Likewise, the market situation also changes, so there are many difficulties in predicting bankruptcy only with information at a certain point in time. However, even though traditional research has problems that don't take into account the time effect, dynamic model has not been studied much. When we ignore the time effect, we get the biased results. So the static model may not be suitable for predicting bankruptcy. Thus, using the dynamic model, there is a possibility that bankruptcy prediction model is improved. In this paper, we propose RNN (Recurrent Neural Network) which is one of the deep learning methodologies. The RNN learns time series data and the performance is known to be good. Prior to experiment, we selected non-financial firms listed on the KOSPI, KOSDAQ and KONEX markets from 2010 to 2016 for the estimation of the bankruptcy prediction model and the comparison of forecasting performance. In order to prevent a mistake of predicting bankruptcy by using the financial information already reflected in the deterioration of the financial condition of the company, the financial information was collected with a lag of two years, and the default period was defined from January to December of the year. Then we defined the bankruptcy. The bankruptcy we defined is the abolition of the listing due to sluggish earnings. We confirmed abolition of the list at KIND that is corporate stock information website. Then we selected variables at previous papers. The first set of variables are Z-score variables. These variables have become traditional variables in predicting bankruptcy. The second set of variables are dynamic variable set. Finally we selected 240 normal companies and 226 bankrupt companies at the first variable set. Likewise, we selected 229 normal companies and 226 bankrupt companies at the second variable set. We created a model that reflects dynamic changes in time-series financial data and by comparing the suggested model with the analysis of existing bankruptcy predictive models, we found that the suggested model could help to improve the accuracy of bankruptcy predictions. We used financial data in KIS Value (Financial database) and selected Multivariate Discriminant Analysis (MDA), Generalized Linear Model called logistic regression (GLM), Support Vector Machine (SVM), Artificial Neural Network (ANN) model as benchmark. The result of the experiment proved that RNN's performance was better than comparative model. The accuracy of RNN was high in both sets of variables and the Area Under the Curve (AUC) value was also high. Also when we saw the hit-ratio table, the ratio of RNNs that predicted a poor company to be bankrupt was higher than that of other comparative models. However the limitation of this paper is that an overfitting problem occurs during RNN learning. But we expect to be able to solve the overfitting problem by selecting more learning data and appropriate variables. From these result, it is expected that this research will contribute to the development of a bankruptcy prediction by proposing a new dynamic model.

• Sleep Medicine and Psychophysiology
• /
• v.24 no.1
• /
• pp.32-37
• /
• 2017

Objectives: A supine sleep position increases sleep apneas compared to non-supine positions in obstructive sleep apnea syndrome (OSAS). However, supine position time (SPT) is not highly associated with apnea-hypopnea index (AHI) in OSAS. We evaluated the correlation among sleep-related variables and SPT in OSAS. Methods: A total of 365 men with OSAS were enrolled in this study. We analyzed how SPT was correlated with demographic data, sleep structure-related variables, OSAS-related variables and heart rate variability (HRV). Multiple linear regression analysis was conducted to investigate the factors that affected SPT. Results: SPT had the most significant correlation with total sleep time (TST ; r = 0.443, p < 0.001), followed by sleep efficiency (SE ; r = 0.300, p < 0.001). Snoring time (r = 0.238, p < 0.001), time at < 90% SpO2 (r = 0.188, p < 0.001), apnea-hypopnea index (AHI ; r = 0.180, p = 0.001) and oxygen desaturation index (ODI ; r = 0.149, p = 0.004) were significantly correlated with SPT. Multiple regression analysis revealed that TST (t = 7.781, p < 0.001), snoring time (t = 3.794, p < 0.001), AHI (t = 3.768, p < 0.001) and NN50 count (t = 1.993, p = 0.047) were associated with SPT. Conclusion: SPT was more highly associated with sleep structure-related parameters than OSAS-related variables. SPT was correlated with TST, SE, AHI, snoring time and NN50 count. This suggests that SPT is likely to be determined by sleep structure, HRV and the severity of OSAS.

• The korean journal of orthodontics
• /
• v.41 no.2
• /
• pp.87-97
• /
• 2011

Objective: Facial asymmetry is usually evaluated from the difference in length and angulation of the maxilla and mandible. However, asymmetric position or shape of the condyle can also affect the expression of asymmetry. The purpose of this study was to evaluate the correlation between condylar asymmetry and chin point deviation in facial asymmetry. Methods: Cone-beam CT images of fifty adult skeletal Class III patients were studied. Thirty patients who had more than 4 mm menton deviation were categorized in the asymmetric group. Twenty patients with less than 4 mm menton deviation were assigned to the symmetric group. Anteroposterior and transverse condyle positions were evaluated from the cranial base. The greatest mediolateral diameter (GMD) of the condyle in the axial plane and angulation to the coronal plane were measured. The height and volume of the condyles were evaluated. Results: The symmetric group had no statistical difference between both condyles in position, angulation, GMD, height and volume. In the asymmetric group, the non-deviated side condyle was larger in GMD, height and volume than the deviated side. There was no statistical difference in condyle position and angulation. The GMD, height difference and condylar volume ratio (non-deviated/deviated) were positively correlated with chin deviation. From the linear regression analysis, condylar volume ratio was a significant factor affecting chin deviation. Conclusions: These findings suggests that the non-deviated side condyle is larger than the deviated side. In addition, condylar asymmetry can affect the expression of facial asymmetry.

• Journal of Life Science
• /
• v.20 no.7
• /
• pp.1012-1018
• /
• 2010

The aim of this study was to determine whether Alzheimer's amyloid precursor protein (APP) is dysregulated in adipose tissues of C57BL/6 male mice by high-fat diet (HFD) induced obesity, aging, or streptozotocin (STZ)-induced diabetes. APP mRNA expression was examined by quantitative real-time PCR (QPCR) in subcutaneous (SAT) and epididymal adipose tissues (EAT) from mice in 8 different condition groups. By combining conditions of age (16 weeks/26 weeks of age), diet (normal diet (ND)/high-fat diet), and induction of diabetes (non-diabetic/diabetic), 88 mice were divided into 8 different groups. QPCR demonstrated that APP expression in SAT was significantly increased by about two-fold in HFD-induced obese mice compared to both 16 week-old and 26 week-old mice in the ND group (16 weeks p=0.001; 26 weeks p<0.0001), but no changes in EAT was found. Particular effects of aging on APP gene expression were not observed in either adipose tissue depots. Significantly decreased APP expression was found in SAT in STZ-induced diabetic mice fed on ND or HFD at 16 weeks of age (ND p<0.05; HFD p<0.01). Linear regression analysis demonstrated that APP expression levels correlated with body weight in both the non-diabetic group (R=0.657, p<0.0001, n=39) and the diabetic group (R=0.508, p=<0.0001, n=49), but did not correlate with plasma glucose levels, which suggests that decreased APP expression in STZ-induced diabetic mice is most likely due to weight loss rather than hyperglycemia. These data confirm APP dysregulation by weight changes in humans and suggest a possible role linking midlife obesity with the later development of amyloidogenesis in the brain of older patients with Alzheimer's disease.

• Journal of Intelligence and Information Systems
• /
• v.21 no.2
• /
• pp.191-204
• /
• 2015

According to the '2013 Performance Assessment Report on the Financial Program' from the National Assembly Budget Office, the unfilled recruitment ratio of Software(SW) Developers in South Korea was 25% in the 2012 fiscal year. Moreover, the unfilled recruitment ratio of highly-qualified SW developers reaches almost 80%. This phenomenon is intensified in small and medium enterprises consisting of less than 300 employees. Young job-seekers in South Korea are increasingly avoiding becoming a SW developer and even the current SW developers want to change careers, which hinders the national development of IT industries. The Korean government has recently realized the problem and implemented policies to foster young SW developers. Due to this effort, it has become easier to find young SW developers at the beginning-level. However, it is still hard to recruit highly-qualified SW developers for many IT companies. This is because in order to become a SW developing expert, having a long term experiences are important. Thus, improving job continuity intentions of current SW developers is more important than fostering new SW developers. Therefore, this study surveyed the job continuity intentions of SW developers and analyzed the factors associated with them. As a method, we carried out a survey from September 2014 to October 2014, which was targeted on 130 SW developers who were working in IT industries in South Korea. We gathered the demographic information and characteristics of the respondents, work environments of a SW industry, and social positions for SW developers. Afterward, a regression analysis and a decision tree method were performed to analyze the data. These two methods are widely used data mining techniques, which have explanation ability and are mutually complementary. We first performed a linear regression method to find the important factors assaociated with a job continuity intension of SW developers. The result showed that an 'expected age' to work as a SW developer were the most significant factor associated with the job continuity intention. We supposed that the major cause of this phenomenon is the structural problem of IT industries in South Korea, which requires SW developers to change the work field from developing area to management as they are promoted. Also, a 'motivation' to become a SW developer and a 'personality (introverted tendency)' of a SW developer are highly importantly factors associated with the job continuity intention. Next, the decision tree method was performed to extract the characteristics of highly motivated developers and the low motivated ones. We used well-known C4.5 algorithm for decision tree analysis. The results showed that 'motivation', 'personality', and 'expected age' were also important factors influencing the job continuity intentions, which was similar to the results of the regression analysis. In addition to that, the 'ability to learn' new technology was a crucial factor for the decision rules of job continuity. In other words, a person with high ability to learn new technology tends to work as a SW developer for a longer period of time. The decision rule also showed that a 'social position' of SW developers and a 'prospect' of SW industry were minor factors influencing job continuity intensions. On the other hand, 'type of an employment (regular position/ non-regular position)' and 'type of company (ordering company/ service providing company)' did not affect the job continuity intension in both methods. In this research, we demonstrated the job continuity intentions of SW developers, who were actually working at IT companies in South Korea, and we analyzed the factors associated with them. These results can be used for human resource management in many IT companies when recruiting or fostering highly-qualified SW experts. It can also help to build SW developer fostering policy and to solve the problem of unfilled recruitment of SW Developers in South Korea.

• The korean journal of orthodontics
• /
• v.39 no.5
• /
• pp.300-309
• /
• 2009

Objective: The purpose of this study was to evaluate the correlation between menton deviation and dental compensation in facial asymmetry. Methods: Tooth axis and distance of first molar and canine to the reference plane were investigated by cone-beam computerized tomography. The subjects consisted of 50 patients with asymmetric mandibles (male 21, female 29, mean age 24.3 years). Control groups were also assessed (male 11, female 9, mean age 25.6 years). Nine measurements (5 linear measurements and 4 angular measurements) were measured in order to evaluate the correlation between menton deviation and the linear and angular difference of first molar and canine in the deviated and none-deviated sides using the defined MPR images. The differences between deviated and non-deviated side, according to menton deviation, were statistically analyzed using stepwise multiple regression analysis. Results: From the result, Menton deviation was negatively correlated with mandibular first molar's angular measurement (${\Delta\angle}LM6$-Mn plane (dev.-ndev.)) and positively with maxillary fist molar's angular measurement (${\Delta\angle}UM6$-FH plane (dev.-ndev.)) (p < 0.01). Two angular measurements (${\Delta\angle}LM6$-Mn plane (dev.-ndev.), ${\Delta\angle}UM6$-FH plane (dev.-ndev.)) explained the variability in menton deviation with a significant $r^2$ value of 0.589. Conclusions: This study suggests that the tooth axis of upper and lower first molars leans towards the deviated side of Menton when there is mandibular asymmetry with Menton deviation.

• Journal of the Korean Association of Geographic Information Studies
• /
• v.25 no.1
• /
• pp.133-149
• /
• 2022

Existing domestic studies on estimating rice yield were mainly implemented at the level of cities and counties in the entire nation using MODIS satellite images with low spatial resolution. Unlike previous studies, this study tried to estimate rice yield at the level of eup-myon-dong in Gimje-si, Jeollabuk-do using Sentinel-2 satellite images with medium spatial resolution, rainfall and soil data, and then to evaluate its accuracy. Five vegetation indices such as NDVI, LAI, EVI2, MCARI1 and MCARI2 derived from Sentinel-2 images of August 1, 2018 for Gimje-si, Jeollabuk-do, rainfall and paddy soil-type data were aggregated by the level of eup-myon-dong and then rice yield was estimated with gamma generalized linear model, an expanded variant of multi-variate regression analysis to solve the non-normality problem of dependent variable. In the rice yield model finally developed, EVI2, rainfall days in September, and saline soils ratio were used as significant independent variables. The coefficient of determination representing the model fit was 0.68 and the RMSE for showing the model accuracy was 62.29kg/10a. This model estimated the total rice production in Gimje-si in 2018 to be 96,914.6M/T, which was very close to 94,470.3M/T the actual amount specified in the Statistical Yearbook with an error of 0.46%. Also, the rice production per unit area of Gimje-si was amounted to 552kg/10a, which was almost consistent with 550kg/10a of the statistical data. This result is similar to that of the previous studies and it demonstrated that the rice yield can be estimated using Sentinel-2 satellite images at the level of cities and counties or smaller districts in Korea.

• Journal of Intelligence and Information Systems
• /
• v.23 no.2
• /
• pp.107-122
• /
• 2017

Volatility in the stock market returns is a measure of investment risk. It plays a central role in portfolio optimization, asset pricing and risk management as well as most theoretical financial models. Engle(1982) presented a pioneering paper on the stock market volatility that explains the time-variant characteristics embedded in the stock market return volatility. His model, Autoregressive Conditional Heteroscedasticity (ARCH), was generalized by Bollerslev(1986) as GARCH models. Empirical studies have shown that GARCH models describes well the fat-tailed return distributions and volatility clustering phenomenon appearing in stock prices. The parameters of the GARCH models are generally estimated by the maximum likelihood estimation (MLE) based on the standard normal density. But, since 1987 Black Monday, the stock market prices have become very complex and shown a lot of noisy terms. Recent studies start to apply artificial intelligent approach in estimating the GARCH parameters as a substitute for the MLE. The paper presents SVR-based GARCH process and compares with MLE-based GARCH process to estimate the parameters of GARCH models which are known to well forecast stock market volatility. Kernel functions used in SVR estimation process are linear, polynomial and radial. We analyzed the suggested models with KOSPI 200 Index. This index is constituted by 200 blue chip stocks listed in the Korea Exchange. We sampled KOSPI 200 daily closing values from 2010 to 2015. Sample observations are 1487 days. We used 1187 days to train the suggested GARCH models and the remaining 300 days were used as testing data. First, symmetric and asymmetric GARCH models are estimated by MLE. We forecasted KOSPI 200 Index return volatility and the statistical metric MSE shows better results for the asymmetric GARCH models such as E-GARCH or GJR-GARCH. This is consistent with the documented non-normal return distribution characteristics with fat-tail and leptokurtosis. Compared with MLE estimation process, SVR-based GARCH models outperform the MLE methodology in KOSPI 200 Index return volatility forecasting. Polynomial kernel function shows exceptionally lower forecasting accuracy. We suggested Intelligent Volatility Trading System (IVTS) that utilizes the forecasted volatility results. IVTS entry rules are as follows. If forecasted tomorrow volatility will increase then buy volatility today. If forecasted tomorrow volatility will decrease then sell volatility today. If forecasted volatility direction does not change we hold the existing buy or sell positions. IVTS is assumed to buy and sell historical volatility values. This is somewhat unreal because we cannot trade historical volatility values themselves. But our simulation results are meaningful since the Korea Exchange introduced volatility futures contract that traders can trade since November 2014. The trading systems with SVR-based GARCH models show higher returns than MLE-based GARCH in the testing period. And trading profitable percentages of MLE-based GARCH IVTS models range from 47.5% to 50.0%, trading profitable percentages of SVR-based GARCH IVTS models range from 51.8% to 59.7%. MLE-based symmetric S-GARCH shows +150.2% return and SVR-based symmetric S-GARCH shows +526.4% return. MLE-based asymmetric E-GARCH shows -72% return and SVR-based asymmetric E-GARCH shows +245.6% return. MLE-based asymmetric GJR-GARCH shows -98.7% return and SVR-based asymmetric GJR-GARCH shows +126.3% return. Linear kernel function shows higher trading returns than radial kernel function. Best performance of SVR-based IVTS is +526.4% and that of MLE-based IVTS is +150.2%. SVR-based GARCH IVTS shows higher trading frequency. This study has some limitations. Our models are solely based on SVR. Other artificial intelligence models are needed to search for better performance. We do not consider costs incurred in the trading process including brokerage commissions and slippage costs. IVTS trading performance is unreal since we use historical volatility values as trading objects. The exact forecasting of stock market volatility is essential in the real trading as well as asset pricing models. Further studies on other machine learning-based GARCH models can give better information for the stock market investors.

• Journal of agricultural medicine and community health
• /
• v.26 no.2
• /
• pp.97-109
• /
• 2001

To investigate the total cholesterol level and its related factors in the rural and sea-board, 2,840 adults who participated voluntarily were examined during the study period December 1999 to February 2000. The height, weight, and fasting serum total cholesterol were measured. Body mass index was calculated. Information on age, gender, smoking, alcohol, and menopausal status in women were collected using a questionnaire by interviewing method. The mean value of total cholesterol was 191.6mg/ dl in sea- board and 173.6mg/ dl in rural men, respectively, and 206.9mg/ dl and 186.9mg/ dl in sea-board and in rural women. By simple analysis, in men, area, BMI and smoking were significant risk factors(p<0.01). Area(p<0.01), age(p<0.01), BMI(p<0.01), smoking(p<0.05), and menopausal status (p<0.01) were significant. In multiple linear regression analysis, the significant factors for total cholesterol in men were area(sea-board versus rural area; p<0.01), body mass index(the more obese; p<0.01), and smoking (non-smoker versus smoker ; p<0.05). Those in women were area(sea-board versus rural area; p<0.01), body mass index(the more obese; p<0.01), and menopausal status(menopause versus normal; p<0.01). Thus, in both gender, the significant factors related with total cholesterol were area and body mass index, and in addition to those, menopausal status was proved as a significant risk factor in women.

• Clinical and Experimental Pediatrics
• /
• v.50 no.6
• /
• pp.549-555
• /
• 2007

Purpose : Pulse wave velocity (PWV) and ankle brachial index (ABI) are simple, non-invasive methods to assess arterial stiffness. These parameters are also known to be closely related to cardiovascular risk factors and diseases. The purposes of this study were to measure blood pressure, PWV, ABI in healthy Korean adolescents, set up their normal values and assess their correlations. Methods : Three hundred ninety two healthy adolescents (213 boys and 179 girls) underwent measurement of brachial ankle pulse wave velocity (baPWV), ABI, body mass index(BMI) and blood pressure from four extremities. Linear regression analysis was performed to reveal the correlations between PWV, ABI and independent variables. Results : Blood pressure and PWV were significantly higher in all extremities in males compared to females. Blood pressure of both brachial and ankle showed positive correlation with body weight, height, and BMI, whereas ABI showed no correlation with any of these indices. Conclusion : Blood pressure increases as body weight, height and BMI increases. PWV shows positive correlation with blood pressure. It will be helpful to predict the risks of cardiovascular diseases in adolescents.