• 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 Korean Society of Forest Science
• /
• v.103 no.3
• /
• pp.431-438
• /
• 2014

This study was conducted to assess forest biomass resource which is a carbon sink and a renewable resource in Korea. The total forest biomass resource potential was 804 million tons, and conifers, broadleaved forest and mixed forest accounted for 265 million tons, 282 million tons, and 257 million tons, respectively. Proportionately to regional forest stocks, biomass potential of Gangwon-do had most biomass potential, followed by Gyeongsangbuk-do and Gyeongsangnam-do. The woody biomass from the byproduct of sawn timber in commercial harvesting was 707 thousand ton/year, and that from the byproduct of forest tending was 592 thousand ton/year. The amount resulted in about 1,300 thousand ton/year of potential supplies from forest biomass resource into the energy market. It's tonnage of oil equivalent(toe) was 585 thousand ton/year. In this study, we developed a program (BiomassMap V2.0) for forest biomass resource mapping. Used system to develop this program was Microsoft Office Excel, Microsoft Office Access ArcGIS and Microsoft Visual Basic 6.0. Additionally, This program made use of tool such as ESRI MapObjects2.1 in order to take advantage of spatial information. This program shows the map of total biomass stock, annual biomass growth at forest land in Korea, and biomass production from forest tending and commercial harvesting. The information can also be managed by the program. The biomass resource map can be identified by regional and forest type for the purpose of utilization. So, we expect the map and program to be very useful for forest managers in the near future.

• Journal of the Korean Society of Groundwater Environment
• /
• v.5 no.3
• /
• pp.129-140
• /
• 1998

In this study two sites were selected to investigate groundwater contamination and spatial relationship between pollution level and its source. One is the Asan area, agricultural district where pollution sources are scattered. The other is the Gurogu area of Seoul city, industrial district where industrial complex and residential areas are located. Groundwater samples collected from these districts were analysis for chemical constituents. The attribute value files of the chemical constituents of groundwater and the spatial layers have been constructed and the pollution properties have been investigated to find out spatial relationships between the groundwater constituents and pollution sources using CIS. Relatively high contents of Si and HCO$_3$ in groundwater from the Asan area reflect the effect of water-rock interaction, whereas high contents of Cl, NO$_3$, SO$_4$and Ca in groundwater from the Gurogu area are due to the pollution of various sources. Pollution over the critical level of Korean Dinking Water Standard has been investigated from 15 sampling sites out of 40 in the Asan area, and 33 sampling sites out of 51 in the Gurogu area. There is pollution of NO$_3$, Cl, Fe, Mn, SO$_4$and Zn in groundwater from the Gurogu area, and that of NO$_3$, SO$_4$and Zn in groundwater from the Asan area. Principal pollution in both areas is NO$_3$contamination. Deep groundwater from the Asan area is not contaminated with NO$_3$except for one site and most of shallow groundwater near the potential point sources such as factory and stock farm is contaminated seriously. Groundwater from the Gurogu area has been already polluted seriously considering the fact of contamination of deep groundwater. This study reports a spatial relationship between the pollution level and pollution source using GIS.

• Journal of Korean Society of Forest Science
• /
• v.104 no.3
• /
• pp.421-426
• /
• 2015

The objective of this paper is to look into the growth of Cryptomeria japonica stand in South Korea along with the evaluation on their yields, followed by their carbon stocks and removals. A total of 106 sample plots were selected from Jeonnam, Gyeongnam, and Jeju, where the groups of standard are grown. We only used 92 plots data except outlier. As part of the analysis, the Weibull diameter distribution was applied. In order to estimate the diameter distribution, the growth estimation equation for each of the growth factors including the height, the diameter at breast height, and the basal area was drafted out and the verification for each equation was examined. The site index for figuring out the forest productivity of Cryptomeria japonica stand for each district was also developed as a Schumacher model and 30yr was used as a reference age for the estimation of the site index. It was found that the site index for Cryptomeria japonica stand in South Korea ranges from 10 to 16 and this result was used as a standard for developing the stand yield table. According to the site 14 in the stand yield table, the mean annual increment (MAI) of the Cryptomeria japonica reaches $7.6m^3/ha$ on its 25yr and its growing stock is estimated to be at $190.1m^3/ha$. This volume is about $20m^3$ as high as that of the Chamaesyparis obtusa. Furthermore, the annual carbon absorptions for a Cryptomeria japonica stand reached the peak at 25yr, which is 2.14 tC/ha/yr, $7.83tCO_2/ha/yr$. When compared to the other conifers, this rate is slightly higher than that of a Chamaecyparis obtusa ($7.5tCO_2/ha/yr$) but lower than that of the Pinus koraiensis ($10.4tCO_2/ha/yr$) and Larix kaempferi ($11.2tCO_2/ha/yr$). With such research result as a base, it is necessary to come up with the ways to enhance the utilization of Cryptomeria japonica as timbers, besides making use of their growth data.

• Journal of agricultural medicine and community health
• /
• v.29 no.1
• /
• pp.65-75
• /
• 2004

Objectives: Immunizations have been one of the most effective measures preventing from infectious diseases. It is quite important national infectious disease prevention policy to keep the immunizations rate high and monitor the immunizations rate continuously. To do this, Korean CDC introduced the National Immunization Registry Program(NIRP) which has been implementing since 2000 at the Public Health Centers(PHC). The National Immunization Registry Program will be near completed after sharing, connecting and transfering vaccination data between public and private sector. The aims of this study was to evaluate the immunization module of non-chart system in private clinic with health information system of public health center(made by POSDATA Co., LTD) and immunization registry program(made by BIT Computer Co., LTD). Methods: The analysis and survey were done by specialists in medical, health field, and health information fields from 2001. November to 2002. January. We made the analysis and recommendation about the immunization module of non-chart system in private clinic. Results and Conclusions: To make improvement on immunization module, the system will be revised on various function like receipt and registration, preliminary medical examination, reference and inquiry, registration of vaccine, print-out various sheet, function of transfer vaccination data, issue function of vaccination certification, function of reminder and recall, function of statistical calculation, and management of vaccine stock. There are needs of an accurate assessment of current immunization module on each private non-chart system. And further studies will be necessary to make it an accurate system under changing health policy related national immunization program. We hope that the result of this study may contribute to establish the National Immunization Registry Program.

• Journal of the Korean Society of Fisheries and Ocean Technology
• /
• v.31 no.2
• /
• pp.142-152
• /
• 1995

The combined bottom trawl and hydroacoustic survey was conducted by using the training ship Oshoro Maru belong to Hokkaido University in November 1989-1992 and the training ship Nagasaki Maru belong to Nagasaki University in April 1994 in the East China Sea, respectively. The aim of the investigations was to collect the target strength data of fish school in relation to the biomass estimation of fish in the survey area. The hydroacoustic survey was performed by using the scientific echo sounder system operating at three frequencies of 25, 50 and 100kHz with a microcomputer-based echo integrator. Fish samples were collected by bottom trawling and during the trawl surveys, the openings of otter board and net mouth were measured. The target strength of fish school was estimated from the relationship between the volume back scattering strength for the depth strata of bottom trawling and the weight per unit volume of trawl catches. A portion of the trawl catches preserved in frozon condition on board, the target strength measurements for the defrosted samples of ten species were conducted in the laboratory tank, and the relationship between target strength and fish weight was examined. In order to investigate the effect of swimbladder on target strength, the volume of the swimbladder of white croaker, Argyrosomus argentatus, sampled by bottom trawling was measured by directly removing the gas in the swimbladder with a syringe on board. The results obtained can be summarized as follows: 1.The relationship between the mean volume back scattering strength (, dB) for the depth strata of trawl hauls and the weight(C, $kg/\textrm{m}^3$) per unit volume of trawl catches were expressed by the following equations : 25kHz : = - 29.8+10Log(C) 50kHz : = - 32.4+10Log(C) 100kHz : = - 31.7+10Log(C) The mean target strength estimates for three frequencies of 25, 50 and 100 kHz derived from these equations were -29.8dB/kg, -32.4dB/kg and -31.7dB/kg, respectively. 2. The relationship between target strength and body weight for the fish samples of ten species collected by trawl surveys were expressed by the following equations : 25kHz : TS = - 34.0+10Log($W^{\frac{2}{3}}$) 100kHz : TS = - 37.8+10Log($W^{\frac{2}{3}}$) The mean target strength estimates for two frequencies of 25 and 100 kHz derived from these equations were -34.0dB/kg, -37.8dB/kg, respectively. 3. The representative target strength values for demersal fish populations of the East China Sea at two frequencies of 25 and 100 kHz were estimated to be -31.4dB/kg, -33.8dB/kg, respectively. 4. The ratio of the equivalent radius of swimbladder to body length of white croaker was 0.089 and the volume of swimbladder was estimated to be approximately 10% of total body volume.