• 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.

• The Journal of the Acoustical Society of Korea
• /
• v.35 no.4
• /
• pp.261-271
• /
• 2016

In the prediction of response of a pile in soil, numerical approaches such as a finite element method are generally applied due to complicate nonlinear behaviors of soils. However, the numerical methods based on the finite elements require heavy efforts in pile and soil modelling and also take long computing time. So their usage is limited especially in the early design stage in which principal dimensions and properties are not specified and tend to vary. On the contrary, theoretical approaches adopting linear approximations for soils are relatively simple and easy to model and take short computing time. Therefore, if they are validated to be reliable, they would be applicable in predicting responses of a pile in soil, particularly in early design stage. In case of wind turbines regarded in this study, it is required to assess their natural frequencies in early stages, and in this simulation the supporting pile inserted in soil could be replaced with a simplified elastic boundary condition at the bottom end of the wind turbine tower. To do this, analysis for a pile in soil is performed in this study to extract the spring constants at the top end of the pile. The pile in soil can be modelled as a beam on elastic spring by assuming that the soils deform within an elastic range. In this study, it is attempted to predict pile deformations and influence factors for lateral loads by means of the beam-on-spring model. As two example supporting structures for wind turbines, mono pile and suction pile models with different diameters are examined by evaluating their influence factors and validated by comparing them with those reported in literature. In addition, the deflection profiles along the depth and spring constants at the top end of the piles are compared to assess their supporting features.

• The korean journal of orthodontics
• /
• v.33 no.4 s.99
• /
• pp.235-245
• /
• 2003

The goal of the present study was to evaluate the effects of PNAM appliance and cheiloplasty on alveolar molding. Samples consisted of 16 unilateral cleft lip and palate infants (10 males and 6 female, mean age=37.0 days after birth, average alveolar cleft gap=10.46m), who were treated with PNAM appliances by one orthodontist and rotation- advancement cheiloplasty by one surgeon in Seoul National University Hospital. Average duration of alveolar molding treatment was 13.10 weeks and these patients were recalled at average 8.31 weeks after cheiloplasty. These patients' models were obtained at initial visit (T0, mean age : $37.0\pm27.89$ days after birth), after successful alveolar molding (T1, mean age : $119.25\pm40.18$ days after birth), and after cheilopasty (T2, mean age : $190.81\pm42.78$ days after birth). Seven linear and five angular variables were measured using 1 : 1 photometry and soft ware program(V-ceph. Cybermed. Seoul, Korea). Paired t-test was performed to investigate statistical significance at p<0.05 level. 1 The posterior parts of alveolar segments were the stable structures during alveolar molding treatment period and after cheiloplasty in infants. 2. The closure of cleft gap during alveolar molding was usually due to backward bending of the whole part of the greater segment. 3. Although forward growth of the greater segment was hindered by alveolar molding, it resumed after cheiloplasty. 4. Increase of anterior inter-segment angle after cheiloplasty was due to the molding effect of the lip scar pressure.

• The korean journal of orthodontics
• /
• v.33 no.3 s.98
• /
• pp.211-222
• /
• 2003

The purpose of this study was to determine whether there is an association between disk displacement of the Temporomandibular Joint (TMJ) and dentofacial asymmetry In orthodontic patients. The subjects consisted of 60 female orthodontic patients between the ages of 18 and 38 years (mean age 23.3 years) who had visited the Department of Orthodontics at Seoul National University Dental Hospital from January 2000 to April 2002. On the basis of magnetic resonance imaging (MRI) of their bilateral TMJs, the subjects were divided Into four groups'. bilateral normal group (twenty-one persons); disk displacement of right TMJ group (six persons); disk displacement of left TMJ group (nine persons); and disk displacement of both TMJs group (twenty-four persons) Postero-anterior (PA) cephalograms and diagnostic models which had been taken before orthodontic treatment were measured. In the linear measurements, a line connecting the right and left Latero-Orbitale (Lo) represented the horizontal reference line (H). The vertical reference line (V) was constructed as a line bisecting and running perpendicular to H. One-way analysis of variance (ANOVA) was used to test whether the mean values of measurements between groups were significantly different. In addition, Bonferronil's multiple comparison test was performed at a level of 0.05. The results were as follows; 1 In the diagnostic model analysis, the overjet, nght molar relationship, and left molar relationship were significantly different among the four groups. 2. In the PA cephalometric analysis, differences in the right and left vertical position of the lower first molar and Ag were significantly dissimilar among the four groups. 3. If the disk displacement of TMJ was present on one side, the ipsilateral ramus was shorter, resulting in asymmetry in the vertical position of Ag. This study indicated that dentofacial asymmetry might be related to the disk displacement of TMJ.

• Korean Journal of Agricultural and Forest Meteorology
• /
• v.8 no.3
• /
• pp.190-198
• /
• 2006

Radiation use efficiency (RUE), the amount of biomass produced per unit intercepted photosynthetically active radiation (PAR), constitutes a main part of crop growth simulation models. The objective of the present study was to evaluate the variation of RUE of rice plants under various nitrogen nutritive conditions. from 1998 to 2000, shoot dry weight (DW), intercepted PAR of rice canopies, and nitrogen nutritive status were measured in various nitrogen fertilization regimes using japonica and Tongil-type varieties. These data were used for estimating the average RUEs before heading and the relationship between RUE and the nitrogen nutritive status. The canopy extinction coefficient (K) increased with the growth of rice until maximum tillering stage and maintained constant at about 0.4 from maximum tillering to heading stage, rapidly increasing again after heading stage. The DW growth revealed significant linear correlation with the cumulative PAR interception of the canopy, enabling the estimation of the average RUE before heading with the slopes of the regression lines. Average RUE tended to increase with the increased level of nitrogen fertilization. RUE increased approaching maximum as the nitrogen nutrition index (NNI) calculated by the ratio of actual shoot N concentration to the critical N concentration for the maximum growth at any growth stage and the specific leaf nitrogen $(SLN;\;g/m^2\;leaf\;area)$ increased. This relationship between RUE (g/MJ of PAR) and N nutritive status was expressed well by the following exponential functions: $$RUE=3.13\{1-exp(-4.33NNNI+1.26)\}$$ $$RUE=3.17\{1-exp(-1.33SLN+0.04)\}$$ The above equations explained, respectively, about 80% and 75% of the average RUE variation due to varying nitrogen nutritive status of rice plants. However, these equations would have some limitations if incorporated as a component model to simulate the rice growth as they are based on relationships averaged over the entire growth period before heading.

• Korean Journal of Agricultural and Forest Meteorology
• /
• v.11 no.2
• /
• pp.72-78
• /
• 2009

The demand for rainfall data in gridded digital formats has increased in recent years due to the close linkage between hydrological models and decision support systems using the geographic information system. One of the most widely used tools for digital rainfall mapping is the PRISM (parameter-elevation regressions on independent slopes model) which uses point data (rain gauge stations), a digital elevation model (DEM), and other spatial datasets to generate repeatable estimates of monthly and annual precipitation. In the PRISM, rain gauge stations are assigned with weights that account for other climatically important factors besides elevation, and aspects and the topographic exposure are simulated by dividing the terrain into topographic facets. The size of facet or grid cell resolution is determined by the density of rain gauge stations and a $5{\times}5km$ grid cell is considered as the lowest limit under the situation in Korea. The PRISM algorithms using a 270m DEM for South Korea were implemented in a script language environment (Python) and relevant weights for each 270m grid cell were derived from the monthly data from 432 official rain gauge stations. Weighted monthly precipitation data from at least 5 nearby stations for each grid cell were regressed to the elevation and the selected linear regression equations with the 270m DEM were used to generate a digital precipitation map of South Korea at 270m resolution. Among 1.25 million grid cells, precipitation estimates at 166 cells, where the measurements were made by the Korea Water Corporation rain gauge network, were extracted and the monthly estimation errors were evaluated. An average of 10% reduction in the root mean square error (RMSE) was found for any months with more than 100mm monthly precipitation compared to the RMSE associated with the original 5km PRISM estimates. This modified PRISM may be used for rainfall mapping in rainy season (May to September) at much higher spatial resolution than the original PRISM without losing the data accuracy.

• KSCE Journal of Civil and Environmental Engineering Research
• /
• v.37 no.1
• /
• pp.9-17
• /
• 2017

Characteristics of aerodynamic damping ratios of a helical $180^{\circ}$ model which shows better aerodynamic behavior in both along-wind and across-wind responses on a super tall building was investigated by an aeroelastic model test. The aerodynamic damping ratio was evaluated from the wind-induced responses of the model by using Random Decrement (RD) technique. Further, various triggering levels in evaluation of aerodynamic damping ratios using RD technique were also examined. As a result, it was found that when at least 2000 segments were used for evaluating aerodynamic damping ratio for ensemble averaging, the aerodynamic damping ratio can be obtained more consistently with lower irregular fluctuations. This is good agreement with those of previous studies. Another notable observation was that for square and helical $180^{\circ}$ models, the aerodynamic damping ratios in along-wind direction showed similar linear trends with reduced wind speeds regarding of building shapes. On the other hand, for the helical $180^{\circ}$ model, the aerodynamic damping ratio in across-wind direction showed quite different trends with those of the square model. In addition, the aerodynamic damping ratios of the helical $180^{\circ}$ model showed very similar trends with respect to the change of wind direction, and showed gradually increasing trends having small fluctuations with reduced wind speeds. Another observation was that in definition of triggering levels in RD technique on aerodynamic damping ratios, it may be possible to adopt the triggering levels of "standard deviation" or "${\sqrt{2}}$ times of the standard deviation" of the response time history if RD functions have a large number of triggering points. Further, these triggering levels may result in similar values and distributions with reduced wind speeds and either may be acceptable.

• Journal of Korea Water Resources Association
• /
• v.39 no.5 s.166
• /
• pp.453-466
• /
• 2006

The objective of this study was to analyze the changes in the hydrological environment in Soyanggang-dam watershed due to climate change results (in yews 2050 and 2100) which were simulated using CCCma CGCM2 based on SRES A2 and B2. The SRES A2 and B2 were used to estimate NDVI values for selected land use using the relation of NDVI-Temperature using linear regression of observed data (in years 1998$\sim$2002). Land use change based on SRES A2 and B2 was estimated every 5- and 10-year period using the CA-Markov technique based on the 1985, 1990, 1995 and 2000 land cover map classified by Landsat TM satellite images. As a result, the trend in land use change in each land class was reflected. When land use changes in years 2050 and 2100 were simulated using the CA-Markov method, the forest class area declined while the urban, bareground and grassland classes increased. When simulation was done further for future scenarios, the transition change converged and no increasing trend was reflected. The impact assessment of evapotranspiration was conducted by comparing the observed data with the computed results based on three cases supposition scenarios of meteorological data (temperature, global radiation and wind speed) using the FAO Penman-Monteith method. The results showed that the runoff was reduced by about 50% compared with the present hydrologic condition when each SRES and periods were compared. If there was no land use change, the runoff would decline further to about 3$\sim$5%.

• Journal of the Korean Institute of Landscape Architecture
• /
• v.44 no.4
• /
• pp.100-108
• /
• 2016

The climatic index for tourism(CIT) has recently been advanced, which includes complete human energy balance models such as physiological equivalent temperature(PET) and universal thermal climate index(UTCI). This study investigated human thermal sensation and comfort at Woljung-ri Beach, Jeju, Republic of Korea, in spring and summer 2015 for landscape planning and design in beach areas. Microclimatic data measurements and human thermal sensation/comfort surveys from ISO 10551 were conducted together. There were 869 adults that participated. As a result, perceptual and thermal preference that consider only physiological aspects had high coefficients of determination($r^2$) with PET in linear regression analyses: 92.8% and 87.6%, respectively. However, affective evaluation, personal acceptability and personal tolerance, which consider both physiological and psychological aspects, had low $r^2s$: 60.0%, 21.1% and 46.4%, respectively. However, the correlations between them and PET were all significant at the 0.01 level. The neutral PET range in perceptual for human thermal sensation was $25{\sim}27^{\circ}C$, but a PET range less or equal to 20% dissatisfaction, which was recommended by ASHRAE Standard 55, could not be achieved in perceptual. Only PET ranges in affective evaluation and personal tolerance affected by both aspects were qualified for the recommendation as $21{\sim}32^{\circ}C$ and $17{\sim}37^{\circ}C$, respectively. Therefore, the PET range of $21{\sim}32^{\circ}C$ is recommended to be used for the human thermal comfort zone of beach areas in landscape planning and design as well as tourism and recreational planning. PET heat stress level ranges on the beach were $2{\sim}5^{\circ}C$ higher than those in inland urban areas of the Republic of Korea. Also, they were similar to high results of tropical areas such as Taiwan and Nigeria, and higher than those of western and middle Europe and Tel Aviv, Israel.

• Journal of agriculture & life science
• /
• v.46 no.1
• /
• pp.123-131
• /
• 2012

This study was conducted to estimate correlation structure between Hanwoo steer growth traits - body weights at 6 month, 12 month, 18 month and 24 month of age, average daily gain, carcass traits, body size traits at 18 months of age. Hanwoo progeny test data(body weight, body size traits) collected from 2004 to 2008 on a total of 1,838 steers at Hanwoo Improvement Main Center(NACF) were analyzed. Carcass traits were used to score the 24 months of age and slaughter. Correlation analyses were performed with observed scales of the traits and with residuals considering fixed effects in generalized linear models. The correlated coefficient estimated between live weight at slaughter(24 months of age) and cold carcass weight was high at 0.92. Correlation between beef yield index values and backfat thickness was estimated to be high and negative at -0.92. Hip height and wither height was found to be highly correlated(0.89). Chest width and chest depth also was found to be highly correlated at 0.73. Rump width was highly correlated with chest depth(0.75) and chest width(0.74). Correlation between pelvic width and rump width was estimated to be 0.74. Hipbone width was shown to be highly correlated with chest depth(0.73), chest width(0.70), rump width(0.75), or pelvic width(0.75). Correlation between wither height and carcass weight was 0.48 in observed scale. Chest girth was phenotyically (residual correlation) correlated with carcass weight (0.51), the estimates of which were some higher than than with the other carcass traits. This study will be utilized for Hanwoo Steers genetic evaluation.