• 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 Intelligence and Information Systems
• /
• v.23 no.4
• /
• pp.127-146
• /
• 2017

Services using artificial intelligence have begun to emerge in daily life. Artificial intelligence is applied to products in consumer electronics and communications such as artificial intelligence refrigerators and speakers. In the financial sector, using Kensho's artificial intelligence technology, the process of the stock trading system in Goldman Sachs was improved. For example, two stock traders could handle the work of 600 stock traders and the analytical work for 15 people for 4weeks could be processed in 5 minutes. Especially, big data analysis through machine learning among artificial intelligence fields is actively applied throughout the financial industry. The stock market analysis and investment modeling through machine learning theory are also actively studied. The limits of linearity problem existing in financial time series studies are overcome by using machine learning theory such as artificial intelligence prediction model. The study of quantitative financial data based on the past stock market-related numerical data is widely performed using artificial intelligence to forecast future movements of stock price or indices. Various other studies have been conducted to predict the future direction of the market or the stock price of companies by learning based on a large amount of text data such as various news and comments related to the stock market. Investing on commodity asset, one of alternative assets, is usually used for enhancing the stability and safety of traditional stock and bond asset portfolio. There are relatively few researches on the investment model about commodity asset than mainstream assets like equity and bond. Recently machine learning techniques are widely applied on financial world, especially on stock and bond investment model and it makes better trading model on this field and makes the change on the whole financial area. In this study we made investment model using Support Vector Machine among the machine learning models. There are some researches on commodity asset focusing on the price prediction of the specific commodity but it is hard to find the researches about investment model of commodity as asset allocation using machine learning model. We propose a method of forecasting four major commodity indices, portfolio made of commodity futures, and individual commodity futures, using SVM model. The four major commodity indices are Goldman Sachs Commodity Index(GSCI), Dow Jones UBS Commodity Index(DJUI), Thomson Reuters/Core Commodity CRB Index(TRCI), and Rogers International Commodity Index(RI). We selected each two individual futures among three sectors as energy, agriculture, and metals that are actively traded on CME market and have enough liquidity. They are Crude Oil, Natural Gas, Corn, Wheat, Gold and Silver Futures. We made the equally weighted portfolio with six commodity futures for comparing with other commodity indices. We set the 19 macroeconomic indicators including stock market indices, exports & imports trade data, labor market data, and composite leading indicators as the input data of the model because commodity asset is very closely related with the macroeconomic activities. They are 14 US economic indicators, two Chinese economic indicators and two Korean economic indicators. Data period is from January 1990 to May 2017. We set the former 195 monthly data as training data and the latter 125 monthly data as test data. In this study, we verified that the performance of the equally weighted commodity futures portfolio rebalanced by the SVM model is better than that of other commodity indices. The prediction accuracy of the model for the commodity indices does not exceed 50% regardless of the SVM kernel function. On the other hand, the prediction accuracy of equally weighted commodity futures portfolio is 53%. The prediction accuracy of the individual commodity futures model is better than that of commodity indices model especially in agriculture and metal sectors. The individual commodity futures portfolio excluding the energy sector has outperformed the three sectors covered by individual commodity futures portfolio. In order to verify the validity of the model, it is judged that the analysis results should be similar despite variations in data period. So we also examined the odd numbered year data as training data and the even numbered year data as test data and we confirmed that the analysis results are similar. As a result, when we allocate commodity assets to traditional portfolio composed of stock, bond, and cash, we can get more effective investment performance not by investing commodity indices but by investing commodity futures. Especially we can get better performance by rebalanced commodity futures portfolio designed by SVM model.

• The Journal of the Convergence on Culture Technology
• /
• v.8 no.2
• /
• pp.227-234
• /
• 2022

Seok Jeon Hwang Wook (18913~1999), a descendant of a traditional literary writer in the western part of Honam, did not join the flow of modern and contemporary calligraphy and painting. And throughout his life, he enjoyed himself without losing the appearance of a scholar, immersed himself in traditional calligraphy, and gained spotlight at his late age for his original hand grabbing calligraphy. Immediately after the Korean War, all of his property was lost due to his two sons' left-wing activities, causing great pain at home. Even in the most painful and difficult time in human history, he relied on brushes, poetry, and gayageum to keep his upright scholarly spirit and national love. And beyond the pleasures of the worldly senses, he played with self-satisfaction in the 'true pleasure(大樂)' without greed. In the course of his studies, he focused on honing the fonts of Wang Hui-ji, Gu Yang-sun, An Jin-gyeong, Jo Maeng-bu, and Xin-wi and Lee Sam-man without a special teacher. In particular, he faced a crisis of having to give up his brush due to tremor that came after his 60th birthday, but he showed a strong will. He transformed it into a new style of art, such as developing hand grabbing calligraphy(握筆法) with a strong and strong energy that no one could match. From 1965 to 1983, 'right hand grabbing calligraphy' was used, and from 1984 to 1993, 'left hand grabbing calligraphy' was used. She made her name as a calligrapher widely known in 1973 (age 76) with her first solo exhibition, The Calligraphy Exhibition commemorating her 60th wedding anniversary. His writing method is naturally rough and sloppy by breaking away from the previous calligraphy methods and artificial technique, and is unfamiliar yet full of muscle. And the calm, strong and rough chuhoegsa(錐劃沙) and the heavy yet majestic ininni(印印泥) individual handwriting expressed a strange feeling and achieved original Seokjeon calligraphy that went beyond the existing calligraphy writing methods, and his indomitable calligraphy spirit was As a unique existence in the history of calligraphy, he still remains as a model.

• Journal of Korean Ophthalmic Optics Society
• /
• v.16 no.4
• /
• pp.383-390
• /
• 2011

Purpose: The present study was conducted to investigate whether refractive powers of soft contact lenses were induced by the deposition of tear proteins when wearing soft contact lenses. Methods: The soft contact lenses (material: etafilcon A, hilafilcon A and comfilcon A) with refractive powers of -1.00 D, -3.00 D, -5.00 D and -7.00 D were incubated in artificial tear for 1 day, 3 days, 5 days, 7 days and 14 days, respectively. After incubation, their refractive powers were measured by wet cell method with an auto-lens meter and their protein deposited on the lenses was determined by the method of Lowry. Results: Among three types of soft contact lenses, the most protein deposition was detected in ionic etafilcon A lens material and significant change of its refractive power was manifested. In other words, refractive powers of etafilcon A lenses firstly decreased after 1 day incubation in artificial tear and then gradually increased with increasing incubation period again. The observed change in refractive powers of all diopters of etafilcon A material was beyond the scope of standard error and bigger in the lens with lower optical power. On the other hand, non-ionic hilafilcon A showed less protein deposition as much as about 20% in etafilacon A and statistically significant increase of refractive powers with increasing incubation period in artificial tear. The change in refractive power of hilafilcon A was also beyond the scope of the standard of error when incubating in artificial tear and greater in the lens with lower diopter. The least protein deposit was shown in silicone hydrogel lens material, comfilcon A as approximately 10% of it in etafilcon A, indicating less change in refractive power within the standard range of error. Conclusions: The large change of refractive powers that was beyond the scope of standard error by the deposition of tear proteins on soft contact lenses was differently detected depending on lens materials in the current study. Thus, the deposition of tear proteins induced by longer period of lens wearing may be one of the causes that induces blurred vision, suggesting that soft contact lens wearers with the amount of tear proteins may need to choose proper lens material.

• Journal of Soil and Groundwater Environment
• /
• v.12 no.2
• /
• pp.9-19
• /
• 2007

This study investigated the interaction between groundwater and stream water systems, which is caused by the artificial weir on streambed, enforcing external stresses on the groundwater system. The study area is in Nami Natural Recreation Woods located in Chungcheongnam-do Geumsan-gun Nami-myeon Geoncheon-ri. In this study both of hydrophysical methods (hydraulic head) and hyrdochemical investigations (pH, EC, major ion analysis) were applied. In order to identify the relationship between each of study results, cross-correlation analysis is performed. From results of hydrophysical methods, water level fluctuation at BH-14, installed by the weir, shows the double-recession pattern much more frequently and much higher amplitudes than the fluctuation at each of other monitoring wells. Using the results by hydrochemical investigations, hydrochemical properties at BH-14 is similar to the hydrochemical characteristics in stream water. To analyze the interrelationships between the results from each of applied methods, cross-correlation analysis was applied. Results from the correlation analyses, water levels at BH-14 and stream weir showed the highest cross-correlation in hydrophysical aspects. On the other hand, the correlation between stream weir and bridge was the highest in hydrochemical aspects. The difference between the results from each of methods is due that the hydrophysical response at BH-14, such as water level, is induced by the pressure propagation-not with mass transfer, but the hydrochemical interaction, caused by mass transport, takes much more times. In conclusion impermeable artificial weir on streambed changes the interfacial condition between the stream and surrounding aquifers. The induced water flux into the groundwater system during flood period make water level at BH-14 increase instantly and groundwater quality higly similar to the quality of stream water. Referred similarities in both of water level and water quality at BH-14 become much higher when water level at weir grow higher.

• Korean Journal of Ecology and Environment
• /
• v.39 no.1 s.115
• /
• pp.100-109
• /
• 2006

This study evaluated the effects of water velocity, substrates, and phosphorus concentrations on the growth of filamentous periphytic algae (FPA) in the two types of artificial channel systems using treated wastewater. Controlled parameters included 5 ${\sim}$ 15 cm $s^{-1}$ for the water velocity; 10 and 20 mm wire meshes, natural fiber net, gravel and tile for the substrates: and 0.05 ${\sim}$ 1.0 mgP $L^{-1}$ for the P concentration. Algal growth rate of FPA was compared using both chi. a and dry weight change with time. Under the controlled water velocity range, the growth of FPA increased with the velocity, but the maximum growth rate was shown in the velocity of 10 cm $s^{-1}$. The substrate that showed the maximum growth of FPA differed between the artificial channel and indoor channel, due to the influence of suspended matters which caused the clogging of the meshed substrates. Under the controled range of P concentration, the growth rates of all three FPA species (Spirogyra turfosa, Oedogonium fovelatum, Rhizoclonium riparium) increased with the P increase, but they showed the differential growth rates among different P concentrations. The results of this study suggest that under the circumstance having an large amount of nutrients FPA develop the biomass rapidly and that even a little increase over the threshold velocity causes the detachment of filamentous periphytic algae. Thus, FPA dynamics in eutrophic streams, such as those receiving treated wastewater, seem to be sensitive to the water velocity. On the other hand, detached algal filaments could deteriorate water quality and ecosystem function in receiving streams or down-stream, and thus they need to be recognized as an important factor in water quality management in eutrophic streams.

• Journal of Korean Tunnelling and Underground Space Association
• /
• v.21 no.1
• /
• pp.31-48
• /
• 2019

The artificial ground freezing (AGF) method is a groundwater cutoff and/or ground reinforcement method suitable for constructing underground structures in soft ground and urban areas. The AGF method conducts a freezing process by employing a refrigerant circulating through a set of embedded freezing pipes to form frozen walls serving as excavation supports and/or cutoff walls. However, thermal expansion of the pore water during freezing may cause excessive deformation of the ground. On the other hand, as the frozen soil is thawed after completion of the construction, mechanical characteristics of the thawed soil are changed due to the plastic deformation of the ground and the rearrangement of soil fabric. This paper performed a field experiment to evaluate the freezing rate of marine clay in the application of the AGF method. The field experiment was carried out by circulating liquid nitrogen, which is a cryogenic refrigerant, through one freezing pipe installed at a depth of 3.2 m in the ground. Also, a piezo-cone penetration test (CPTu) and a lateral load test (LLT) were performed on the marine clay before and after application of the AGF method to evaluate a change in strength and stiffness of it, which was induced by freezing-thawing. The experimental results indicate that about 11.9 tons of liquid nitrogen were consumed for 3.5 days to form a cylindrical frozen body with a volume of about $2.12m^3$. In addition, the strength and stiffness of the ground were reduced by 48.5% and 22.7%, respectively, after a freezing-thawing cycle.

• Fashion & Textile Research Journal
• /
• v.7 no.2
• /
• pp.143-152
• /
• 2005

A concept of 'digital' is changing a living pattern of moderners, with having influence on the whole life of modern society. The purpose of this study is arrange the frame of conformity to the 'fashion as culture' by considering the social and cultural phenomena being shown in relation to digital, which is a concept being watched most for the 21st century and by trying to analyze a tendency of digital culture being shown in the modernly fashion design based on this. The digital culture, which is a concept of generalizing the phenomena of interactional changes in the sub-structure being derived by digital technology, is being shown as a tendency of fusionization and globalization, and due to this, the culture of digital nomads is being formed. On the other hand, a tendency of amenity caused by the reaction against the coldly digital technology, is forming one axis of digital culture. As the culture, which experiences the process of a change by digital technology, is reflected even on the fashion, the fusion of technology and the human body, brought about the appearance and the development of the artificial body, by allowing the wearable computer to be introduced to fashion and by being connected directly to the body. This means the expansion of range for fashion. The destruction of a border between space and space, is making an opportunity of forming another ego inside the cyber space, with bringing about the mixed loading between the cyber space and the real space. As the border between the cyber space and the real space is being collapsed, the space of newly self-realization is being created. The collapse of gender is being shown as the pursuit of gender, which is a nomadic concept of not giving priority to anywhere of male gender and female gender. The tendency of sensitive design introduced the sports look as the largely fashion trend. Fascinated with Zen thoughts is leading to a response to the swiftly and coldly social conditions caused by machine. The digital culture by digital technology and the fashion tendency being shown by its influence, meet the needs of self-realization and self-expansion for a human being, and satisfy the needs for the expression of self-identity for a human being, and enable the search for introspection about inner existence inside the self.

• Analytical Science and Technology
• /
• v.26 no.6
• /
• pp.401-406
• /
• 2013

Oxygen($O_2$) consumption and carbon dioxide($CO_2$) excretion of a fertile chicken egg during incubation were measured by a gas mass spectrometer. A closed sample chamber was developed to collect gas samples during the 20 days of artificial incubation of both a fertile and an infertile egg. After leaving an egg in the sample chamber for an hour, using a gas-tight syringe, samples of 2 mL of gas were collected from the closed sample chamber and analyzed using a gas mass spectrometer in 2~4 day intervals. The $O_2$ consumption and $CO_2$ excretion of chicken embryos increased rapidly after 10 days from the starting point of incubation. After 20 days, 23 mL of $O_2$ was consumed and 16 mL of $CO_2$ was excreted per hour. Throughout the whole period of incubation, concentration of $O_2$ decreased 4.3 mol% and $CO_2$ increased only 3.1 mole%, i.e., the mole of consumed $O_2$ and the mole of excreted $CO_2$ were not the same. On the other hand, during the same period, concentration of $N_2$ increased about 1.3 mol% and the increased mole fraction of $N_2$ was comparable with the difference (1.2 mol%) between the mole fraction of consumed $O_2$ and excreted $CO_2$. Therefore, we can attribute the increase of $N_2$ mole% to the difference of mole fraction between consumed $O_2$ and excreted $CO_2$. In this study, through the analysis of gas, we could explain the respiration of a fertile chicken egg during incubation.

• Journal of the Korean earth science society
• /
• v.23 no.7
• /
• pp.565-574
• /
• 2002

Based on previous investigations of aerial photographs and topographical surveys, this study focuses on the sedimentologic features of the Daebudo area including sedimentation processes, sedimentary facies and hydrologic conditions of the erosional coast. A total of 137 surface sediments and one core (by hand auger) sediment were obtained to interpret the depositional environment of the erosional coast in the macro-tidal coast. Surface sediments are distributed from sandy gravel (sG) to silt (Z). Textural parameters are characterized not only by coarse, poorly sorted, positive skewed and multi-modal distribution in the supra-tidal flat, but also finer, relatively well-sorted, symmetric distribution in the intertidal flat. According to the C/M diagram, sediment transport modes of study area are characterized by the mixed mode of suspension and bedload in the upper-, middle-tidal flat and by uniform suspension in the lower-tidal flat due to tidal effect. Vertical sediment distribution of the core, collected near shoreline, shows coarsening-upward, poorly sorted pattern by the input of detritus resulting from coastal erosion. Considering the sedimentological features of the study area, it appears to be composed of a coastal zone changed by not only artificial reclamation, but also by natural processes such as strong wave action due to typhoons and storms during high water level and long/short-term sea level rising. As a result, tide-dominated erosional coasts show that the shore is affected by local, temporal and hydrological conditions near high tide level and that the intertidal flat is represented by a general tide-dominated sedimentary environment.