• 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.

• KOREAN JOURNAL OF CROP SCIENCE
• /
• v.51 no.7
• /
• pp.571-583
• /
• 2006

To secure high yield and good quality of rice, plant growth and nitrogen (N) nutrition status should be taken into account for managing panicle N topdressing (PN). This research aimed at investigating the rice yield response to PN under different plant growth and N nutrition status that was conditioned by different rates of basal and tillering N fertilizer (BTN). Stepwise multiple regression (SMR) was used for the analysis of yield response to (i) BTN and PN, and (ii) shoot N content at PIS (BTNup) and shoot N uptake from PIS to harvest (PNup). Rice yield increased significantly as BTN and PN Increased, but there was no significant interaction between BTN and PN. Yield increased almost linearly with the increasing BTN and PN up to $10{\sim}12$ and $6{\sim}7\;kgN/10a$, and with the increasing BTNup and PNup up to $6{\sim}7$ and $5{\sim}6\;kgN/10a$, respectively. But yield increment tended to decrease above those levels. These declines resulted from the decreased ripened grain ratio and 1000 grain weight even though spikelet number per unit area increased more at above those N levels. Spikelet number per unit area had the linear relationships with the shoot N uptake until heading, and with yield. Like most yield response curves, yield response in this experiment followed the diminishing return function with BTNup, PNup, and plant N uptake from seeding to harvest. Regardless of the degree of BTNup and PNup, yield had a quadratic relationship ($R^{2}$>0.88) with whole shoot N accumulation until harvest, suggesting that the yield determination was closely related with the whole shoot N uptake until harvest regardless of the differences in seasonal shoot N uptake.

• Korean Journal of Remote Sensing
• /
• v.35 no.6_1
• /
• pp.883-893
• /
• 2019

In this study, crop coefficients were calculated in two different methods and the results were evaluated. In the first method, appropriateness of GLDAS-based evapotranspiration was evaluated by comparing it with observed data of Cheongmi-cheon (CMC) Flux tower. Then, crop coefficient was calculated by dividing actual evapotranspiration with potential evapotranspiration that derived from GLDAS. In the second method, crop coefficient was determined by using MLR (Multiple Linear Regression) analysis with vegetation index (NDVI, EVI, LAI and SAVI) derived from MODIS and in-situ soil moisture data observed in CMC, In comparison of two crop coefficients over the entire period, for each crop coefficient GLDAS K_c and SM&VI K_c, shows the mean value of 0.412 and 0.378, the bias of 0.031 and -0.004, the RMSE of 0.092 and 0.069, and the Index of Agree (IOA) of 0.944 and 0.958. Overall, both methods showed similar patterns with observed evapotranspiration, but the SM&VI-based method showed better results. One step further, the statistical evaluation of GLDAS K_c and SM&VI K_c in specific period was performed according to the growth phase of the crop. The result shows that GLDAS K_c was better in the early and mid-phase of the crop growth, and SM&VI K_c was better in the latter phase. This result seems to be because of reduced accuracy of MODIS sensors due to yellow dust in spring and rain clouds in summer. If the observational accuracy of the MODIS sensor is improved in subsequent study, the accuracy of the SM&VI-based method will also be improved and this method will be applicable in determining the crop coefficient of unmeasured basin or predicting the crop coefficient of a certain area.

• Toxicological Research
• /
• v.33 no.2
• /
• pp.107-118
• /
• 2017

Although alternative test methods based on the 3Rs (Replacement, Reduction, Refinement) are being developed to replace animal testing in reproductive and developmental toxicology, they are still in an early stage. Consequently, we aimed to develop alternative test methods in male animals using mouse spermatogonial stem cells (mSSCs). Here, we modified the OECD TG 489 and optimized the in vitro comet assay in our previous study. This study aimed to verify the validity of in vitro tests involving mSSCs by comparing their results with those of in vivo tests using C57BL/6 mice by gavage. We selected hydroxyurea (HU), which is known to chemically induce male reproductive toxicity. The 50% inhibitory concentration ($IC_{50}$) value of HU was 0.9 mM, as determined by the MTT assay. In the in vitro comet assay, % tail DNA and Olive tail moment (OTM) after HU administration increased significantly, compared to the control. Annexin V, PI staining and TUNEL assays showed that HU caused apoptosis in mSSCs. In order to compare in vitro tests with in vivo tests, the same substances were administered to male C57BL/6 mice. Reproductive toxicity was observed at 25, 50, 100, and 200 mg/kg/day as measured by clinical measures of reduction in sperm motility and testicular weight. The comet assay, DCFH-DA assay, H&E staining, and TUNEL assay were also performed. The results of the test with C57BL/6 mice were similar to those with mSSCs for HU treatment. Finally, linear regression analysis showed a strong positive correlation between results of in vitro tests and those of in vivo. In conclusion, the present study is the first to demonstrate the effect of HU-induced DNA damage, ROS formation, and apoptosis in mSSCs. Further, the results of the current study suggest that mSSCs could be a useful model to predict male reproductive toxicity.

• Korean Journal of Environmental Biology
• /
• v.37 no.4
• /
• pp.568-578
• /
• 2019

The nymphal development of the potato aphid, Macrosiphum euphorbiae (Thomas), was studied at seven constant temperatures (12.5, 15.0, 17.5, 20.0, 22.5, 25.0, and 27.5±1℃), 65±5% relative humidity (RH), and 16:8 h light/dark photoperiods. The developmental investigation of M. euphorbiae was separated into two steps, the 1^st through 2^nd and the 3^rd through 4^th stages. The mortality was under 10% at six temperatures. However, it was 53.0% at 27.5℃. The developmental time of the entire nymph stage was 15.5 days at 15.0℃, 6.7 days at 25.0℃, and 9.7 days at 27.5℃. In the immature stage, the lower threshold temperature of the larvae was 2.6℃ and the thermal constant was 144.5 DD. In our analysis of the temperature-development experiment, the Logan-6 model equation was most appropriate for the non-linear regression models (r²=0.99). When the distribution completion model of each development stage of M. euphorbiae larvae was applied to the 2-parameter and 3-parameter Weibull functions, each of the model's goodness of fit was very similar (r²=0.92 and 0.93, respectively). The adult longevity decreased as the temperature increased but the total fecundity of the females at each temperature was highest at 20℃. The life table parameters were calculated using the whole lifespan periods of M. euphorbiae at the above six temperatures. The net reproduction rate (R₀) was highest at 20.0℃(63.2). The intrinsic rate of increase (r_m) was highest at 25℃(1.393). The finite rate of doubling time (D_t) was the shortest at 25.0℃(2.091). The finite rate of increase (λ) was also the highest at 25.0℃(1.393). The mean generation time(T) was the shortest at 25.0℃(9.929).

• Journal of Nutrition and Health
• /
• v.41 no.8
• /
• pp.733-741
• /
• 2008

In the present study, we comprehensively examined the associations of plasma levels of total adiponectin and high molecular weight (HMW) adiponectin with the features of cardiometabolic risks including body fat distribution, dyslipidemia, insulin resistance and inflammatory markers in a cross-sectional study of 110 treated hypertensive patients. Blood lipid profiles, high sensitivity C-reactive protein (hsCRP) and homeostasis model assessment of insulin resistance (HOMA- IR) derived from fasting glucose and insulin concentrations were determined. Plasma levels of tumor necrosis factor-${\alpha}$ (TNF-${\alpha}$), interleukin-6 (IL-6) and intercellular adhesion molecule-1 (ICAM-1) were analyzed using ELISA. The results showed that plasma levels of HMW-adiponectin were negatively associated with body mass index (BMI, r = - 0.203, p < 0.05) and waist circumference (r = -0.307, p < 0.01), which was not shown in total adiponectin. Plasma levels of HMW-adiponectin were negatively associated with triglyceride (r = -0.223, p < 0.05) and positively associated with HDL-cholesterol (r = 0.228, p < 0.05). Plasma levels of adiponectin were positively associated with HDL-cholesterol (r = 0.224, p < 0.05). Plasma levels of HMW-adiponectin were negatively associated with hsCRP (r = -0.276, p < 0.01) and IL-6 (r = -0.272, p < 0.01). In addition, there were weak associations between plasma levels of HMWadiponectin and TNF-${\alpha}$ (r = -0.163, p = 0.07) and ICAM-1 (r = -0.158, p = 0.09). However, there were no significant associations of total adiponectin with inflammatory markers except hsCRP (r = -0.203, p < 0.05). Stepwise multiple linear regression analysis showed that only plasma levels of HMW-adiponectin was an independent factor influencing serum levels of hsCRP, a marker of systemic low grade inflammation, after adjusting for age, gender, BMI, waist circumference, alcohol intake, smoking status, blood lipids, total adiponectin and drug use (p < 0.01). These results suggest that HMW-adiponectin, rather than total adiponectin, is likely to be closely associated with the features of cardiometabolic risks in treated hypertensive patients and might be effective biomarker for the prediction of cardiovascular disease.

• Tuberculosis and Respiratory Diseases
• /
• v.54 no.4
• /
• pp.395-402
• /
• 2003

Background : Patients with chronic obstructive pulmonary disease (COPD) are at increased risk for osteoporosis, which has implications for mobility and even mortality. The goal of this pilot study was to evaluate bone mineral density (BMD) and risk factors for osteoporosis in a limited number of men with COPD. Methods : We checked BMD, $FEV_1$(% of predicted) and investigated risk factors for osteoporosis in 44 male patients with COPD who visited our hospital from January to August 2002. Results : Mean(${\pm}$) age was $69{\pm}9$ yrs, body mass index(BMI) $21{\pm}3kg/m^2$, $FEV_1$ $50{\pm}18%$ of predicted, lumbar spine T-score $-3.0{\pm}1.2$, lumbar spine Z-score $-2.0{\pm}1.2$, and lumbar spine BMD $0.76{\pm}0.13g/cm^2$. Osteoporosis(T-score below -2.5) was present in 27 patients(61.4%) and osteopenia(T-score between -1 and -2.5) in 17(38.6%). None of the patients had normal BMD. There was no relationship between BMD and $FEV_1$(% of predicted). There were significant differences in smoking, alcohol consumption, exercise, cumulative steroid dose, BMI and BMD among the three groups according to $FEV_1$(% of predicted) (group1 : ${\geq}65%$, group2 : 50-64%, group3 : ${\leq}49%$), except age. However, there were no significant differences in these variables between the osteopenia and osteoporosis groups, except BMI. Linear Regression(Stepwise) analysis showed that lumbar BMD was correlated with BMI & exercise. Conclusion : BMD is significantly reduced in men with COPD. There was no relationship between BMD and pulmonary function.

• Korean Journal of Environment and Ecology
• /
• v.25 no.3
• /
• pp.318-326
• /
• 2011

The population ecological characteristics of the Crucian carp, Carassius auratus, were determined in order to estimate stock of the mid-upper system of the Seomjin River. The fish ranged in size from 95 to 288mm total length. The age was determined by counting the scale annulus. The scales displayed clear annulus that were used to estimate the age. The oldest fish observed in this study was 5 years old. Age-2 fishes were the most numerous in the sample(n=38), followed in frequency be age-3(n=22). Marginal index analysis validated the formation of a single annulus per year. The relationship between body length and body weight was BW = $0.0038BL^{3.73}$($R^2$=0.96) (p<0.01). The relationship between the scale radius and body length was BL = 2.362R+2.76($R^2$=0.89). The von Bertalanffy growth parameters estimated from a non-linear regression method were $L_{\infty}$=33.2 cm, $W_{\infty}$=1,798.4 g, $K=0.20year^{-1}$ and $t_0$=-0.51year. Therefore, Growth in length of the fish was expressed by the von Bertalanffy's growth equation as $L_t=33.23$($1-e^{-0.20(t+0.51)}$)($R^2$=0.98). The annual survival rate was estimated to be 0.427year$^{-1}$. The instantaneous coefficient of natural mortality of estimated from the Zhang and Megrey method was $0.784year^{-1}$, and instantaneous coefficient of fishing mortality was calculated $0.067year^{-1}$. From the estimates of survival rate, the instantaneous coefficient of total mortality was estimated to be $0.851year^{-1}$.

• Tuberculosis and Respiratory Diseases
• /
• v.81 no.1
• /
• pp.42-48
• /
• 2018

Background: The diffusing capacity of the lung is influenced by multiple factors such as age, sex, height, weight, ethnicity and smoking status. Although a prediction equation for the diffusing capacity of Korea was proposed in the mid-1980s, this equation is not used currently. The aim of this study was to develop a new prediction equation for the diffusing capacity for Koreans. Methods: Using the data of the Korean National Health and Nutrition Examination Survey, a total of 140 nonsmokers with normal chest X-rays were enrolled in this study. Results: Using linear regression analysis, a new predicting equation for diffusing capacity was developed. For men, the following new equations were developed: carbon monoxide diffusing capacity (DLco)=-10.4433-0.1434${\times}$age (year)+0.2482${\times}$heights (cm); DLco/alveolar volume (VA)=6.01507-0.02374${\times}$age (year)-0.00233${\times}$heights (cm). For women the prediction equations were described as followed: DLco=-12.8895-0.0532${\times}$age (year)+0.2145${\times}$heights (cm) and DLco/VA=7.69516-0.02219${\times}$age (year)-0.01377${\times}$heights (cm). All equations were internally validated by k-fold cross validation method. Conclusion: In this study, we developed new prediction equations for the diffusing capacity of the lungs of Koreans. A further study is needed to validate the new predicting equation for diffusing capacity.

• Korean journal of applied entomology
• /
• v.47 no.2
• /
• pp.163-168
• /
• 2008

Temperature dependent development of Tetranychus. urticae Koch was studied on the leaf of eggplant at 17, 22, 27, 32 and $37^{\circ}C$. T. urticae showed a minimum mortality at $27^{\circ}C$ and it increased at higher or lower temperatures than $27^{\circ}C$. The hatchability was low at 17 and $37^{\circ}C$. The duration of development decreased with increasing temperatures i.e., 5.3d at $37^{\circ}C$ and 25.8d at $17^{\circ}C$. Linear regression analysis of temperature vs. rate of development yielded the higher $r^2{\geq}0.88$ resulting in a good fit of the estimated line in the range of $17{\sim}37^{\circ}C$. Developmental zero temperature was $12.5^{\circ}C$ for the entire immature stage of female and $12.8^{\circ}C$ for that of male. Thermal constants were 80.5 and 74.7 degree days for those of female and male, respectively. Adult life span and oviposition period decreased with increasing temperatures. The number of eggs laid per female peaked at 141.0 eggs at $27^{\circ}C$, while that was a minimum 78.0 eggs at $37^{\circ}C$. Rate of hatchability, ratio of female, and $R_o$ were increased up to $27^{\circ}C$, and than declined thereafter. Intrinsic rate of natural increase (Rm) increased with rising temperatures and showed a maximum 0.5652 at $37^{\circ}C$. Also, ${\lambda}$ increased with increasing temperature. Doubling time (Dt) and generation time (T) decreased with increasing temperature.