• Journal of Intelligence and Information Systems
• /
• v.24 no.4
• /
• pp.1-32
• /
• 2018

In addition to stakeholders including managers, employees, creditors, and investors of bankrupt companies, corporate defaults have a ripple effect on the local and national economy. Before the Asian financial crisis, the Korean government only analyzed SMEs and tried to improve the forecasting power of a default prediction model, rather than developing various corporate default models. As a result, even large corporations called 'chaebol enterprises' become bankrupt. Even after that, the analysis of past corporate defaults has been focused on specific variables, and when the government restructured immediately after the global financial crisis, they only focused on certain main variables such as 'debt ratio'. A multifaceted study of corporate default prediction models is essential to ensure diverse interests, to avoid situations like the 'Lehman Brothers Case' of the global financial crisis, to avoid total collapse in a single moment. The key variables used in corporate defaults vary over time. This is confirmed by Beaver (1967, 1968) and Altman's (1968) analysis that Deakins'(1972) study shows that the major factors affecting corporate failure have changed. In Grice's (2001) study, the importance of predictive variables was also found through Zmijewski's (1984) and Ohlson's (1980) models. However, the studies that have been carried out in the past use static models. Most of them do not consider the changes that occur in the course of time. Therefore, in order to construct consistent prediction models, it is necessary to compensate the time-dependent bias by means of a time series analysis algorithm reflecting dynamic change. Based on the global financial crisis, which has had a significant impact on Korea, this study is conducted using 10 years of annual corporate data from 2000 to 2009. Data are divided into training data, validation data, and test data respectively, and are divided into 7, 2, and 1 years respectively. In order to construct a consistent bankruptcy model in the flow of time change, we first train a time series deep learning algorithm model using the data before the financial crisis (2000~2006). The parameter tuning of the existing model and the deep learning time series algorithm is conducted with validation data including the financial crisis period (2007~2008). As a result, we construct a model that shows similar pattern to the results of the learning data and shows excellent prediction power. After that, each bankruptcy prediction model is restructured by integrating the learning data and validation data again (2000 ~ 2008), applying the optimal parameters as in the previous validation. Finally, each corporate default prediction model is evaluated and compared using test data (2009) based on the trained models over nine years. Then, the usefulness of the corporate default prediction model based on the deep learning time series algorithm is proved. In addition, by adding the Lasso regression analysis to the existing methods (multiple discriminant analysis, logit model) which select the variables, it is proved that the deep learning time series algorithm model based on the three bundles of variables is useful for robust corporate default prediction. The definition of bankruptcy used is the same as that of Lee (2015). Independent variables include financial information such as financial ratios used in previous studies. Multivariate discriminant analysis, logit model, and Lasso regression model are used to select the optimal variable group. The influence of the Multivariate discriminant analysis model proposed by Altman (1968), the Logit model proposed by Ohlson (1980), the non-time series machine learning algorithms, and the deep learning time series algorithms are compared. In the case of corporate data, there are limitations of 'nonlinear variables', 'multi-collinearity' of variables, and 'lack of data'. While the logit model is nonlinear, the Lasso regression model solves the multi-collinearity problem, and the deep learning time series algorithm using the variable data generation method complements the lack of data. Big Data Technology, a leading technology in the future, is moving from simple human analysis, to automated AI analysis, and finally towards future intertwined AI applications. Although the study of the corporate default prediction model using the time series algorithm is still in its early stages, deep learning algorithm is much faster than regression analysis at corporate default prediction modeling. Also, it is more effective on prediction power. Through the Fourth Industrial Revolution, the current government and other overseas governments are working hard to integrate the system in everyday life of their nation and society. Yet the field of deep learning time series research for the financial industry is still insufficient. This is an initial study on deep learning time series algorithm analysis of corporate defaults. Therefore it is hoped that it will be used as a comparative analysis data for non-specialists who start a study combining financial data and deep learning time series algorithm.

• Clinical and Experimental Pediatrics
• /
• v.52 no.11
• /
• pp.1228-1233
• /
• 2009

Purpose : This study aimed to evaluate whether a shorter time from the arrival at a hospital to delivery is related to the occurrence of cerebral palsy in premature infants of less than 34 weeks of gestational age. Methods : We studied 142 newborns of less than 34 weeks of gestational age. The time from the arrival at the hospital to delivery was measured. The correlation between the time required for delivery and the occurrence of cerebral palsy was elucidated by diagnosing cerebral palsy in neonates using the Korean Infant Development Screening Test and neurological examination. Results : Preliminary result suggested that a shorter time from hospital arrival to delivery was related to a lower development score for gross motor activity and to a higher frequency of cerebral palsy occurrence. Moreover, it was responsible for a tendency of obtaining lower Apgar scores at 1 and 5 minutes. The shorter delivery time was associated with a higher probability of respiratory distress syndrome (RDS) occurrence when the length of delivery time was less than 6 hours and there was a higher probability of a shorter gestation period. However, the multifactor analysis revealed that there was little impact of delivery time on the occurrence of cerebral palsy. Conclusions : The length of hospital arrival time to delivery did not significantly influence the occurrence of cerebral palsy in premature infants of less than 34 weeks of gestational age.

• Journal of Life Science
• /
• v.20 no.4
• /
• pp.543-548
• /
• 2010

The purpose of this study was to examine the differences in kinetics between 6 months of rehabilitation training and 12 months of rehabilitation training after total hip arthroplasty. 10 unilateral THA participants performed kinetic tests. Three dimensional kinematics and hip flexors and abductors electromyography (EMG) were collected during each trial. T-test was used for statistical analysis (p<0.05). There was no significant difference in EMG data between the two groups, but the mean comparison EMG data was higher in the 12 months rehabilitation training group than the 6 months rehabilitation training group. The moment value was found with motion-dependent interaction analyzing method which was used by Feltner and Dapena. There was no significant difference between moment values of the two groups. There was no significant difference between ground reaction forces of the two groups; however, there were some differences shown in Fz (vertical reaction force) between the two groups ($892{\pm}104\;N$, $820{\pm}87\;N$). The first peak impact force was about 9% lower in the 12 months group compared to the 6 months group. The second peak active force was nearly equal between the two groups. More research is necessary to determine exactly what constitutes optimal rehabilitation training biomechanics for patients with total hip arthroplasty.

• Journal of Korea Water Resources Association
• /
• v.44 no.10
• /
• pp.797-807
• /
• 2011

Phenomenon of vegetation recruitment on the sand bar is drastically rising in the streams and rivers in Korea. In the 1960s prior to industrialization and urbanization, most of the streams were consisted of sands and gravels, what we call, 'White River'. Owing to dam construction, stream maintenance, etc. carried out since the '70s, the characteristic of flow duration and sediment transport have been disturbed resulting in the abundance of vegetation in the waterfront, that is, 'Green River' is under progress. This study purposed to identify the correlation among water level, water temperature, rainfall, soil moisture and soil texture out of the factors which give an effect on the vegetation recruitment on the sand bar of unregulated stream. To this purpose, this study selected the downstream of Naeseong Stream, one of sand rivers in Korea, as the river section for test and conducted the monitoring and analysis for 289 days. In addition, this study analyzed the aerial photos taken from 1970 to 2009 in order to identify the aged change in vegetation from the past to the present. The range of the tested river section was 361 m in transverse length and about 2 km in longitudinal length. According to the survey analysis, the tested river section in Naeseong Stream was a gaining river showing the higher underground-water level by 20~30 m compared to Stream water level. The difference in the underground water temperature was less than $5^{\circ}C$ by day and season and the Stream temperature did not fall to $10^{\circ}C$ and less from May when the vegetation germination begins in earnest. The impact factor on soil moisture was the underground water level in the lower layer and the rainfall in the upper layer and it was found that all the upper and lower layer were influenced by soil particle size. The soil from surface to 1 m-underground out of 6 soil moisture-measured points was sand with the $D_{50}$ size of 0.07~1.37 mm and it's assumed that the capillary height possible in the particle size would reach around 14~43 cm. On the other hand, according to the result of space analysis on the tested river section of unregulated stream for 40 years, it was found that the artificial disturbance and drought promoted the vegetation recruitment and the flooding resulted in the frequency extinction of vegetation communities. Even though the small and large scales of recruitment and extinction in vegetation have been repeated since 1970, the present vegetation area increased clearly compared to the past. It's found that the vegetation area is gradually increasing over time.

• Journal of dental hygiene science
• /
• v.16 no.6
• /
• pp.481-487
• /
• 2016

The elderly population with dementia is rapidly growing in South Korea. The aim of this study was to investigate the relationship between dementia and oral health in 197 subjects aged ${\geq}65$ years. The questionnaire included questions on subjective health status, subjective health concern, subjective oral health status and behavior, mastication ability, Oral Health Impact Profile-14 (OHIP-14), and Korean Dementia Screening Questionnaires (KDSQ). Oral examination was conducted by a single dentist to evaluate upper or lower denture use, and determine the numbers of remaining and functioning teeth, including implant and fixed prosthesis. The subjects who required a dementia test (KDSQ-C [cognition] of ${\geq}6$) had significant differences in systemic disease prevalence rate, subjective health status, subjective health concern, KDSQ-V (vascular disease) score, KDSQ-D (depression) score, subjective oral treatment need, key food mastication ability and OHIP-14 score compared to the healthy subjects. The proportion of denture wearers, total remaining teeth, total functioning teeth, toothbrushing frequency, oral pain severity, symptoms of periodontal disease, subjective oral health status, and subjective oral health concern showed no significant differences between the two groups. KDSQ-C and OHIP-14 scores showed a strong positive relationship, while KDSQ-C score and total remaining teeth or key food mastication ability showed a weak negative relationship. In the multiple regression analysis, the KDSQ-D, KDSQ-V, and OHIP-14 scores influenced the KDSQ-C scores. We suggest a relationship between oral health and cognitive impairment.

• Economic and Environmental Geology
• /
• v.37 no.1
• /
• pp.73-86
• /
• 2004

In order to estimate the post-ingestion bioavailability of heavy metals and to assess the risk of adverse health effects on human exposure to toxic heavy metals, environmental geochemical surveys were undertaken around the Dogok Au-Ag-Cu and the Hwacheon Au-Ag-Pb-Zn mine sites. Human risk assessment of toxic heavy metals was performed with the results of the SBET(simple bioavailability extraction test) analysis for soil and chemical analytical data for crop plant and water. Arsenic and other heavy metals were highly elevated in tailings from the Dogok(218 As mg/kg, 90.2 Cd mg/kg, 3,053 Cu mg/kg, 9,473 Pb mg/kg, 14,500 Zn mg/kg) and the Hwacheon(72 As mg/kg, 12.4 Cd mg/kg. 578 Pb mg/kg, 1,304 Zn mg/kg) mines. These significant concentrations can impact on soils and waters around the tailing dumps. The quantities of As, Cd and Zn extracted from paddy soils in the Hwacheon mine using the SBET analysis were 55.4%, 20.8% and 26.4% bioavailability, respectively, and for farmland soils in the Dogok mine, 40.8%, 37.6% and 33.0% bioavailability, respectively. From the results of human risk assessment, HI(Hazard Index) value exceeded 1.0 for As in the Hwacheon mine and for Cd in the Dogok mine. Thus, toxic risks for As and Cd exist via exposure(ingestion) of contaminated soil, water and rice grain in these mine sites. The cancer risk for As by the consumption of rice and groundwater in the Hwacheon mine area was 8E-4 and 1E-4, respectively. This risk level exceeds the acceptable risk(1 in 100,000) for regulatory purpose. Therefore, regular ingestion of locally grown rice and ground-water by the local population can pose a potential health threat due to long-term arsenic exposure.

• Korean journal of applied entomology
• /
• v.46 no.1 s.145
• /
• pp.87-95
• /
• 2007

Many kinds of environment friendly agricultural materials were used for the insect pest control and the control of plant diseases, furthermore they support the growth of crops in the greenhouses and the kindly environment friendly farming. Phytoseiulus persimilis might be used for control of two-spotted mites with environment friendly agricultural materials at the same time. For testing the toxicity of environment friendly agricultural materials against to p. persimilis, 61 environment friendly agricultural materials were selected by material contents and using methods. When environment friendly agricultural materials were directly sprayed on P. persimilis, IEFAM C, FEFAM A, EFAMSM A, D, EFAMPE A, EFAMCh B, EFAMME A, and EFAMMo C killed over 90%. However, there was no effects to FEFAM C, D, EFAMSM C, EFAML A, EFAMME C, E, H, J, EFAMMo G and I against P. persimilis. P. persimilis adults were not survived in vial for 48 hours after sprayed and dried with the environment friendly agricultural materials, fer examples, EFAMSM I, EFAMME A, EFAMMo A, C, and I. Otherwise, EFAMCh C and EFAMMo B were no effects to P. persimilis. Some environment friendly agricultural materials are of different qualities, and consequently test of their foxily have to necessary.

• Journal of Korean Home Economics Education Association
• /
• v.26 no.1
• /
• pp.101-118
• /
• 2014

"Career maturity" is very crucial for high school students since it has an impact on their career path and decision-making. Not only that, it is also important in self-realization and happiness as well as maximizing human resources. When it comes to understanding high school students' career path, it is necessary to know how they perceive school life since they spend most of their time in school. It's also vital to observe in the perspective of students' personal growth. This study seeks to understand the relationship between "adaptation to school life" "self-esteem" and "career maturity". To accomplish this, the 7th additional surveys conducted by Welfare Panel Study were used. The survey was conducted among 496 high school students in order to come up with descriptive statistics and correlation between "adaptation to school life" and "self-esteem" as well as the level of "career maturity". Hierarchical multiple regression analysis was used to understand the effects of "adaptation to school life" and "self-esteem" on "career maturity." The Baron and Kennny mediation analysis were used to understand the effects when the mediating role of "self-esteem" comes into the relationship between "adaptation to school life" and "career maturity". The results of the analysis are as follows: First, the average age for high school students' "career maturity" is 2.07, while it is 1.91 for "self-esteem". For "adaptation to school life," the relationship between "obedience to school regulations" and "relationship with friends" was relatively higher than the relationship between "attitude toward school life" and "interest in school life" Second, high school students' "career maturity" "adaptation to school life" and "self-esteem" were thought to be statistically meaningful since it showed that they had a positive relationship with each other. Third, "interest in school life" "attitude toward school life" and "obedience to school life" and "relationship with friends" in which all of these are the sub factors for "adaptation to school life" together with "self-esteem" had an influence on high school students' "career maturity". Lastly, the relationship between "adaptation to school life" and "career maturity" was proved to be influenced by the partial mediating role of "self-esteem". As the study seeks to find relationships and the factors that affect high school students' "career maturity" meaningful information is given out for the development and progress of educational programs for "career maturity". This was done by understanding the fundamental and systematic approach towards "career maturity" in the students' perspective.

• Korean Journal of Environmental Biology
• /
• v.29 no.4
• /
• pp.251-257
• /
• 2011

Cobalt is a naturally occurring element found in rocks, soil, water and/or is among the harmful pollutants as generated by industrialized. In the environment, cobalt has two oxidation states, cobalt (II) (Co (II)) and cobalt (III) (Co (III)). If coastal water is contaminated by cobalt, it through the food chain can have an impact on marine ecosystems. Therefore, we examined the gametotoxic and embryotoxic effects of Co (II) at various concentrations (10, 100, 500, 1000, 2500 ppb) in the sea urchin $Hemicentrotus$ $pulcherrimus$. Spawning was induced by injecting 1 mL of 0.5 M KCl into coelomic cavity. Males released white or cream-colored sperms and females released yellow or orange-colored eggs. Experiment was begun within 30 min the collection of both gametes. The fertilization and embryo development rates test were performed for 10 min and 64 h after fertilization, respectively. The fertilization rates in the control condition (not including Co (II)) and experimental group were not significantly changed. The embryo development rates in the control condition were greater than 90% and were significantly decreased with concentration dependent manner. The normal embryogenesis rate was significantly inhibited in exposed to cobalt (II) ($EC_{50}$=71.84 ppb, 95% Cl=16.71-203.36 ppb). The NOEC and LOEC of normal embryogenesis rate were <10 ppb and 10 ppb, respectively. These results suggest that the early embryo stages of $H.$ $pulcherrimus$ have toxic effect at greater than 10 ppb of Co (II) concentration.

• Korean Security Journal
• /
• no.24
• /
• pp.53-66
• /
• 2010

This study aims to analyze kinematic variables regarding lateral break-fall quantitatively that can protect the body, prevent the injury and minimize the impact. To this end, three Hapkido, judo athletes of H University with experience of over 5 years were selected. Test was conducted through three dimensional image analysis by checking the time and order the subjects reach a mat. In this study, lateral break-fall was repeated five times and among them, the best movement was selected. The picture shot with high-speed camera was analyzed by using KWON3D ver. 3.1 program through three dimensional coordinate calculation based on DLT method and smoothing process of data. Study results were as follows. 1. With respect to time variables shown in lateral break-fall of A, B, C athletes, there is small difference in temporal variables and in the order the body reaches a mat. With respect to average value, hand is ($0.94{\pm}0.20$), elbow ($0.97{\pm}0.17$), hip ($0.97{\pm}0.18$), back ($0.98{\pm}0.18$), and shoulder ($1.04{\pm}0.16$). Time variable the body reaches a mat in lateral break-fall is in hand, elbow, hip, back and shoulder. 2. With respect to moving distance variables shown in lateral break-fall of A, B, C athletes, hand is ($34.33{\pm}34.59$), elbow ($52.00{\pm}26.06$), hip ($70.00{\pm}15.72$), back ($153.67{\pm}17.93$), and should ($130.67{\pm}29.02$). The fact that this study contributed to improving security martial arts technique and protecting the body by understanding the principle of lateral break-fall movement is of significance. In addition, the fact that this study provided systematic basic data for improving security martial arts technique is significant.