• 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 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).

• 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 $0.851year^{-1}$.

• Journal of the Korean Society of Marine Environment & Safety
• /
• v.28 no.1
• /
• pp.1-9
• /
• 2022

The effect of sediments in a waste dumping area on marine organisms was evaluated using sediment toxicity tests with a benthic amphipod (Monocorophium acherusicum) and bioluminescent bacterium (Vibrio fischeri) in accordance with the Korean Standard Method for Marine Wastes (KSMMW). Nine sites in the East Sea-Byeong, East Sea-Jeong, and Yellow Sea-Byeong areas were sampled from 2016 to 2019. The test results showed that the relative average survival rate (benthic amphipods) and relative luminescence inhibition rate (luminescent bacteria) were below 30%, which were judged to be "non-toxic." However, in the t-test, a total of 12 benthic amphipod samples (6, 1, 1, and 4 in 2016, 2017, 2018, and 2019, respectively) were significantly different (p<0.05) from the control samples. To identify the source of toxicity on benthic amphipods, a simple linear regression analysis was performed between the levels of eight heavy metals (Cr, As, Ni, Cd, Cu, Pb, Zn, and Hg) in sediments and the relative average survival rate. The results indicated that Cr had the highest contribution to the toxicity of benthic amphipods (p = 0.000, R2 = 0.355). In addition, Cr was detected at the highest concentration at the DB-85 station and exceeded the Marine Environment Standards every year. Although the sediments were determined as "not toxic" according to the ecotoxicity criteria of the KSMMW, the results of the statistical significance tests and toxicity identification evaluation indicated that the toxic effect was not acceptable. Therefore, revising the criteria for determining the toxic effect by deriving a reference value through quantitative risk assessment using species sensitivity distribution curves is necessary in the future.

• Korean Journal of Psychosomatic Medicine
• /
• v.31 no.2
• /
• pp.108-117
• /
• 2023

Objectives : Somatic symptom disorder (SSD) is characterized by the manifestation of a variety of physical symptoms, but little is known about differences in autonomic nervous system activity according to symptom severity, especially within patient groups. In this study, we examined differences in heart rate variability (HRV) across symptom severity in a group of SSD patients to analyze a representative marker of autonomic nervous system changes by symptoms severity. Methods : Medical records were retrospectively reviewed for patients who were diagnosed with SSD based on DSM-5 from September 18, 2020 to October 29, 2021. We applied inverse probability of treatment weighting (IPTW) methods to generate more homogeneous comparisons in HRV parameters by correcting for selection biases due to sociodemographic and clinical characteristic differences between groups. Results : There were statistically significant correlations between the somatic symptom severity and LF (nu), HF (nu), LF/HF, as well as SD1/SD2 and Alpha1/Alpha2. After IPTW estimation, the mild to moderate group was corrected to 27 (53.0%) and the severe group to 24 (47.0%), and homogeneity was achieved as the differences in demographic and clinical characteristics were not significant. The analysis of inverse probability weighted regression adjustment model showed that the severe group was associated with significantly lower RMSSD (β=-0.70, p=0.003) and pNN20 (β=-1.04, p=0.019) in the time domain and higher LF (nu) (β=0.29, p<0.001), lower HF (nu) (β=-0.29, p<0.001), higher LF/HF (β=1.41, p=0.001), and in the nonlinear domain, significant differences were tested for SampEn15 (β=-0.35, p=0.014), SD1/SD2 (β=-0.68, p<0.001), and Alpha1/Alpha2 (ß=0.43, p=0.001). Conclusions : These results suggest that differences in HRV parameters by SSD severity were showed in the time, frequency and nonlinear domains, specific parameters demonstrating significantly higher sympathetic nerve activity and reduced ability of the parasympathetic nervous system in SSD patients with severe symptoms.

• Journal of Environmental Impact Assessment
• /
• v.32 no.6
• /
• pp.437-449
• /
• 2023

This study measured PM₁₀ concentrations and wind speeds in buffer green spaces and neighborhood parks located along the road, and compared them with roadside measurementresults to understand the effect of mitigating PM₁₀ concentrations by type of green space and the influence of wind speeds on it. As a result of the analysis, the effect of mitigating PM₁₀ concentration was different depending on the type of roadside green space, and an increase in wind speed had a significant effect on reducing PM₁₀ concentration. In buffer green areas with high planting density, wind speed was low and PM₁₀ stagnated inside, resulting in the highest concentration. On the other hand, green areas in neighborhood parks with relatively low planting density had high wind speeds and the lowest PM₁₀ concentration. The non-green area within the neighborhood park recorded the highest wind speed, which was advantageous for the spread of PM₁₀, but the concentration was higherthan that of the green area. Therefore, in orderto reduce PM₁₀ concentration in roadside green space, it is necessary to create green space with good ventilation, and the combined effect of green space and wind speed seems to be more advantageous in reducing PM₁₀ concentration. Green spaces capture and remove PM inside, contributing to reducing the concentration of PM outside. In order to manage PM in the entire city and on roads, it is necessary to increase planting density and leaf area in roadside green spaces, such as buffer green spaces, so that PM can be removed within the green spaces. However, in green spaces such as neighborhood parks that are actively used by city residents, in orderto minimize damage to users due to PM, it is desirable to create green spaces with a structure that allows PM to spread to the outside rather than stagnate inside.