• Asia pacific journal of information systems
• /
• v.19 no.2
• /
• pp.157-178
• /
• 2009

Corporate credit rating is a very important factor in the market for corporate debt. Information concerning corporate operations is often disseminated to market participants through the changes in credit ratings that are published by professional rating agencies, such as Standard and Poor's (S&P) and Moody's Investor Service. Since these agencies generally require a large fee for the service, and the periodically provided ratings sometimes do not reflect the default risk of the company at the time, it may be advantageous for bond-market participants to be able to classify credit ratings before the agencies actually publish them. As a result, it is very important for companies (especially, financial companies) to develop a proper model of credit rating. From a technical perspective, the credit rating constitutes a typical, multiclass, classification problem because rating agencies generally have ten or more categories of ratings. For example, S&P's ratings range from AAA for the highest-quality bonds to D for the lowest-quality bonds. The professional rating agencies emphasize the importance of analysts' subjective judgments in the determination of credit ratings. However, in practice, a mathematical model that uses the financial variables of companies plays an important role in determining credit ratings, since it is convenient to apply and cost efficient. These financial variables include the ratios that represent a company's leverage status, liquidity status, and profitability status. Several statistical and artificial intelligence (AI) techniques have been applied as tools for predicting credit ratings. Among them, artificial neural networks are most prevalent in the area of finance because of their broad applicability to many business problems and their preeminent ability to adapt. However, artificial neural networks also have many defects, including the difficulty in determining the values of the control parameters and the number of processing elements in the layer as well as the risk of over-fitting. Of late, because of their robustness and high accuracy, support vector machines (SVMs) have become popular as a solution for problems with generating accurate prediction. An SVM's solution may be globally optimal because SVMs seek to minimize structural risk. On the other hand, artificial neural network models may tend to find locally optimal solutions because they seek to minimize empirical risk. In addition, no parameters need to be tuned in SVMs, barring the upper bound for non-separable cases in linear SVMs. Since SVMs were originally devised for binary classification, however they are not intrinsically geared for multiclass classifications as in credit ratings. Thus, researchers have tried to extend the original SVM to multiclass classification. Hitherto, a variety of techniques to extend standard SVMs to multiclass SVMs (MSVMs) has been proposed in the literature Only a few types of MSVM are, however, tested using prior studies that apply MSVMs to credit ratings studies. In this study, we examined six different techniques of MSVMs: (1) One-Against-One, (2) One-Against-AIL (3) DAGSVM, (4) ECOC, (5) Method of Weston and Watkins, and (6) Method of Crammer and Singer. In addition, we examined the prediction accuracy of some modified version of conventional MSVM techniques. To find the most appropriate technique of MSVMs for corporate bond rating, we applied all the techniques of MSVMs to a real-world case of credit rating in Korea. The best application is in corporate bond rating, which is the most frequently studied area of credit rating for specific debt issues or other financial obligations. For our study the research data were collected from National Information and Credit Evaluation, Inc., a major bond-rating company in Korea. The data set is comprised of the bond-ratings for the year 2002 and various financial variables for 1,295 companies from the manufacturing industry in Korea. We compared the results of these techniques with one another, and with those of traditional methods for credit ratings, such as multiple discriminant analysis (MDA), multinomial logistic regression (MLOGIT), and artificial neural networks (ANNs). As a result, we found that DAGSVM with an ordered list was the best approach for the prediction of bond rating. In addition, we found that the modified version of ECOC approach can yield higher prediction accuracy for the cases showing clear patterns.

• Journal of the Korean Society for Marine Environment & Energy
• /
• v.18 no.2
• /
• pp.51-63
• /
• 2015

In order to investigation long-term variations of water qualities in the Saemangeum Salt-Water Lake formed after the sea-dike construction, the survey has carried out over 40 time from 2002 to 2010. The decreased salinity in surface water immediately after the dike construction has maintained on equal terms for years. After the dike construction, the early concentration of SPM in surface water has decreased but then it showed the tendency to move up and down due to the changes of water level in the lake. The elevated concentration of Chl-a in surface water initially after the dike construction was kept at the same conditions for years. The concentration of DIN in surface water has not changed before and shortly after the dike construction. However, the concentration of $NH_4-N$ in surface water has increased steadily after the dike construction. Consequently the concentration of DIN in the lake water after years has raised compared to pre-dike construction. The reduced concentration of DIP in surface water soon after the dike construction has increased after years as well as $NH_4-N$ due to the accumulation of organic matter to inside lake. Unlike with the unvaried $NO_3-N$, the concentration of DISi in surface water after the dike construction has immediately increased and maintained the enhanced level indicating the supply from other sources except the freshwater. Since the dike construction, the spatial characteristics of water quality was divided river sides and rest of the lake markedly. Stratification of river sides was more strong than the dike sides. In the warm seasons, hypoxia causing the release of nutrients and metals from sediment was observed downward about 1 m from surface of river sides. We strongly suggest to make some urgent measure to prevent low dissolved oxygen condition in the bottom layer of the river sides.

• Journal of radiological science and technology
• /
• v.28 no.4
• /
• pp.293-299
• /
• 2005

In the present investigation, we analyzed the data of 1,318 patients (2,636 images) who underwent mammographic examinations and obtained the distribution of the patient age and compressed breast thickness. We measured also average glandular doses (AGD) as function of compressed breast thickness. In order to obtain the values of AGD, we measured half value layer (HVL) and tube output (mR/mAs) for each kVp and target/filter combination. Entrance surface air kerma (ESAK) was calculated from the tube output as measured for each voltage used under clinical conditions and from the tube loading (mAs). AGD per exposure were calculated by multiplying the ESAK values by the conversion factors tabulated by Dance. We obtained in this study the following conclusions. The mean value of compressed breast thickness for cranio-caudal (CC) view was 35.8mm and that for medio-lateral oblique (MLO) view was 43.3 mm. The mean value of AGD for CC view was 1.55 mGy and that for MLO view was 1.70 mGy. The AGD for MLO view was 0.15 mGy (10%) higher than that for CC view because the thickness for MLO view was on average 4.8 mm higher than that for CC view. The values of AGD increased with increasing compressed brest thickness. The increased AGD value was on average 0.34 mGy per 10 mm in the thickness ranges $10{\sim}80\;mm$, therefore differences between the AGD values of each thickness were relative large. Thus, it is considered to need limited doses for mammography with the upper end of exposure range at several different compressed brest thickness.

• Journal of Chest Surgery
• /
• v.37 no.8
• /
• pp.665-671
• /
• 2004

Background: Lymph node metastasis is commonly reported in thoracic esophageal cancer, even in the early esophageal cancer which may be localized only in the mucosa or within the submucosal layer. Although lymph node metastasis greatly influence long-term outcome and cure of the disease, endoscopic mucosal resection or photodynamic therapy without lymph node dissection is widely attempted. The investigation of the pattern of lymph node metastasis and results of surgical resection of superficial esophageal cancer is needed. Material and Method: Pattern of lymph node metastsis and depth of tumor invasion were studied retrospectively from 44 patients with early esophageal cancer who underwent radical resection of the tumor from December, 1995 to August, 2001. Result: Lymph node metastasis was found in 10 patients (22.7%) out of total of 44 patients. Lymph node metastasis was found in 0% (0 of 3), 0% (0 of 4), 50% (2 of 4), and 24.24% (8 of 33) of tumors that invaded the intraepitherium, lamina propria, muscularis mucosa, and submucosa respectively. Anatomically distant lymph node metastases were found more frequently in recurrent laryngeal nerve node(5 cases of 10 patients) and in intraperitoneal node (8 cases of 10). than intrathoracic node (3 cases of 10). There was no operative mortality, however, there were 1 hospital death in patient with lamina propria cancer, 1 late death in patient with submucosal cancer. Three-year survival rates (except hospital death) were 100% in mucosal cancer and 97.0% in submucosal cancer (p>0.05), and 100% in the node negative group and 90.0% in the node positive group (p>0.05). Conclusion: The survival rate of superficial esophageal cancer patient who was recieved operative resection was excellent. But, lymph node metastasis were found in superficial esophageal cancer, even in esophageal cancer limited to the muscularis mucosa. Systemic lymph node dissection which includes recurrent laryngeal nerve nodes and intraperitoneal nodes was recommended for favorable outcome in superficial esophageal cancer.

• Applied Biological Chemistry
• /
• v.8
• /
• pp.65-73
• /
• 1967

For the study of method for salt elimination aimed at reforming tidal land into normal paddy fields in a short period with reduction of periods requiring for elimination of saline, CHP (a kind of Ca-hum ate), a soil conditioner made of peat as a main material was tried. In the pot experiment, effect on elimination of salt, improvement of physical-chemical characteristics and rice cultivation test were studied. The results of these tests are as follows: 1, CHP treatment somewhat improves aggregation state with some effect on aggregation. 2. CHP treatment is remarkably effective in permeability which increases with 1.0 percent treatment by three times in percolation rate, and by 4.5 times in volume of leached water respectively. 3. With the increase of CHP amounts, salt was eliminated in short period. When 80% of the total Na was leached in 1.0% CHP-A treated pot, control pot begins permeable. 4. CEC and phosphorous absorption capacity are not influenced by CHP treatment. 5. Growing state of rice is greatly influenced by rainfalls. Growth of rice in tidal land however are almost similar to those in normal paddy fields with layer amounts of CHP treatment. With salt content in the soils, saline hazard and numbers of ineffective stems, amounts of unmatured grain are increased. 6. With the treatment of CHP yields of rough rice were increased. With 0.5% CHP treatment the yields were similar to those of the normal paddy fields. With 1.0% CHP-A treatment, the yields were increased by 15 times more than those of none treated soil and by 25 percent more than normal paddy soils.

• Korean Journal of Soil Science and Fertilizer
• /
• v.18 no.3
• /
• pp.312-317
• /
• 1985

Growth response and nutrients uptake of tobacco grown on mulched and non mulched plots were investigated during the growing period. 1. The whole growing time was about 25 days shorter and relative growth rate was faster in the mulched plot than in the non mulched plot. 2. Nitrate content of leaf in the latter stage of tobacco grown on the non mulched plot was more continuously increased compared with mulched plot. As a result in the latter stage of tobacco leaf nitrate form of nitrogen level was much higher on non mulched plot than on mulched plot. 3. Reducing sugar content in cured leaves of tobacco grown on the non mulched plot was lower that of the mulched plot. This difference in reducing sugar content was remarkable in the bottom leaves that nitrate content was highest. 4. Tobacco growing on nonmulched soil may cause to be low quality owing to increasing of nitrogen compound and decreasing of reducing sugar content in cured leaves. 5. As distributions of nitrate and potassium content in leaves at different stalk position was similar each other, nitrate and potassium ion considered to be counter ion in absorption and translocation through the tobacco plant.

• Korean Journal of Veterinary Research
• /
• v.23 no.2
• /
• pp.137-148
• /
• 1983

This study was made for the better information of the male reproductive system on the meat-type drake, Cherry Belly X White Golden. The epithelium of ductules of epididymal region and deferent duct were observed histologically and histochemically with the progress of their development. India-ink absorbability on the luminal epithelium was also investigated after the administration of India-ink. The results are as follows; 1. Rete testis and various round ductules in immature form appeared in epididymis within 6 weeks after hatching, and simple cuboidal and simple columnar epithelium were found in the epithelia of the ductules within 8 weeks after hatching. Larger ductules were found on epididymal surface which was in the developing stage near to the immature efferent ductule. From 10th to 20th week, various ductules appeared in epididymis, and developing form of efferent ductules were much more increased on epididymal surface. The luminal epithelium of the ductules were composed of ciliated simple columnar and pseudostratified ciliated columnar cells. At the same time, deferent duct appeared. From the 21th week, various ductules in epididymis became abruptly matured. Lumen of rete testis was lined by simple squamous or simple cuboidal epithelium, and that of efferent ductules, having many folds and being larger than any others were lined by pseudostratified ciliated columnar epithelium in which ciliated columnar cells, non-ciliated cells(clear cells) and basal cells were noted. Connecting tubules of star shaped lumen were composed of pseudostratified ciliated columnar epithelium in which ciliated columnar cells, nonciliated cells, and basal cells were observed. The luminal surface of epididymal ducts was smooth and has thick pseudostratified columnar epithelium which was composed of high columnar cells and basal cells. From 26th week after hatching, sperm pooling was started in various ductules. 2. From 4th to 10th week, simple cuboidal epithelium of deferent duct transformed to simple columnar epithelium with the progress of aging. At the basement of epithelium, clear round cells were noted. From 12th to 20th week, high columnar cells with enlongated nucleus were noted on the luminal border of deferent ducts, forming folds of pseuclostratified columnar epithelium. From 20th week, the deferent duct started to have septa in it's lumen and composed mainly of pseudostratified columnar epithelium, and round cells disappeared. From 20th week, the lumen diameter of deferent duct became wider with the progress of aging, but there was no difference among the values of lumen diameter in upper, middle, and lower part of deferent ducts. At 26th week, the pooling period of sperms in deferent ducts, the lumen diameter became rapidly widen, especially in the lower part of deferent ducts. Thickness of muscular layer of ductus deferens showed gradual growth within 24 weeks but did abrupt thickening from 26th week. 3. Saliva resistant PAS granules were dotted on the top of nucleus in efferent ductules epithelium but the amount of the granules were little in the connecting ductules's epithelium. The granules reactive to acid phosphatase were abundant in the some epithelial cells of efferent ductules and connecting ductules, especially above the nucleus of cells. The granules reactive to alkaline phosphatase were noted on the luminal border of efferent ductules. Parts of free border of efferent ductules and middle portion of deferent ducts were stained slightly by alcian blue technique. India ink granules were found mainly in the epithelium of efferent ductules but were few in that of connecting ductules.

• Journal of Korea Water Resources Association
• /
• v.49 no.2
• /
• pp.133-144
• /
• 2016

In this study, Frequency Domain Reflectometry (FDR) and COSMIC-ray soil moisture (SM) stations were installed at Sungkyunkwan University in Suwon, South Korea. To provide reliable information about SM, soil property test, time series analysis of measured soil moisture, and comparison of measured SM with satellite-based SM product are conducted. In 2014, six FDR stations were set up for obtaining SM. Each of the stations had four FDR sensors with soil depth from 5 cm to 40 cm at 5~10 cm different intervals. The result showed that study region had heterogeneous soil layer properties such as sand and loamy sand. The measured SM data showed strong coupling with precipitation. Furthermore, they had a high correlation coefficient and a low root mean square deviation (RMSD) as compared to the satellite-based SM products. After verifying the accuracy of the data in 2014, four FDR stations and one COSMIC-ray station were additionally installed to establish the Soil Moisture site with FDR and COSMIC-ray, called SM-FC. COSMIC-ray-based SM had a high correlation coefficient of 0.95 compared with mean SM of FDR stations. From these results, the SM-FC will give a valuable insight for researchers into investigate satellite- and model-based SM validation study in South Korea.

• Korean Journal of Materials Research
• /
• v.6 no.7
• /
• pp.700-708
• /
• 1996

Electroless plating technique was utilized to flip chip bonding to improve surface mount characteristics. Each step of plating procedure was studied in terms pf pH, plating temperature and plating time. Al patterned 4 inch Si wafers were used as substrstes and zincate was used as an activation solution. Heat treatment was carried out for all the specimens in the temperature range from room temperature to $400^{\circ}C$ for $30^{\circ}C$ minutes in a vacuum furnace. Homogeneous distribution of Zn particles of size was obtained by the zincate treatment with pH 13 ~ 13.5, solution concentration of 15 ~ 25% at room temperature. The plating rates for both Ni-P and Au electroless plating steps increased with increasing the plating temperature and pH. The main crystallization planes of the plated Au were found to be (111) a pH 7 and (200) and (111) at pH 9 independent of the annealing temperature.

• Korean Journal of Agricultural and Forest Meteorology
• /
• v.3 no.4
• /
• pp.199-205
• /
• 2001

This study was conducted to figure out temperature profiles of a partially developed paddy rice canopy, which are necessary to run plant disease forecasting models. Air temperature over and within the developing rice canopy was monitored from one month after transplanting (June 29) to just before heading (August 24) in 1999 and 2001. During the study period, the temporal march of the within-canopy profile was analyzed and an empirical formula was developed for simulating the profile. A partially developed rice canopy temperature seemed to be controlled mainly by the ambient temperature above the canopy and the water temperature beneath the canopy, and to some extent by the solar altitude, resulting in alternating isothermal and inversion structures. On sunny days, air temperature at the height of maximum leafages was increased at the same rate as the ambient temperature above the canopy after sunrise. Below the height, the temperature increase was delayed until the solar noon. Air temperature near the water surface varied much less than those of the outer- and the upper-canopy, which kept increasing by the time of daily maximum temperature observed at the nearby synoptic station. After sunset, cooling rate is much less at the lower canopy, resulting in an isothermal profile at around the midnight. A fairly consistent drop in temperature at rice paddies compared with the nearby synoptic weather stations across geographic areas and time of day was found. According to this result, a cooling by 0.6 to 1.2$^{\circ}C$ is expected over paddy rice fields compared with the officially reported temperature during the summer months. An empirical equation for simulating the temperature profile was formulated from the field observations. Given the temperature estimates at 150 cm above the canopy and the maximum deviation at the lowest layer, air temperature at any height within the canopy can be predicted by this equation. As an application, temperature surfaces at several heights within rice fields were produced over the southwestern plains in Korea at a 1 km by 1km grid spacing, where rice paddies were identified by a satellite image analysis. The outer canopy temperature was prepared by a lapse rate corrected spatial interpolation of the synoptic temperature observations combined with the hourly cooling rate over the rice paddies.