• 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.41 no.2
• /
• pp.109-125
• /
• 2023

This study was conducted to select target fish species as baseline research for accumulation analysis of major hazardous chemicals entering the aquatic ecosystem in Korea and to analyze the impact on fish community. The test bed was selected from a sewage treatment plant, which could directly confirm the impact of the inflow of harmful chemicals, and the Geum River estuary where harmful chemicals introduced into the water system were concentrated. A multivariable metric model was developed to select target candidate fish species for hazardous chemical analysis. Details consisted of seven metrics: (1) commercially useful metric, (2) top-carnivorous species metric, (3) pollution fish indicator metric, (4) tolerance fish metric, (5) common abundant metric, (6) sampling availability (collectability) metric, and (7) widely distributed fish metric. Based on seven metric models for candidate fish species, eight species were selected as target candidates. The co-occurring dominant fish with target candidates was tolerant (50%), indicating that the highest abundance of tolerant species could be used as a water pollution indicator. A multi-metric fish-based model analysis for aquatic ecosystem health evaluation showed that the ecosystem health was diagnosed as "bad conditions". Physicochemical water quality variables also influenced fish feeding and tolerance guild in the testbed. Eight water quality parameters appeared high at the T1 site, indicating a large impact of discharging water from the sewage treatment plant. T2 site showed massive algal bloom, with chlorophyll concentration about 15 times higher compared to the reference site.

• Journal of Intelligence and Information Systems
• /
• v.18 no.4
• /
• pp.43-57
• /
• 2012

To enhance the competitive advantage in a constantly changing business environment, an enterprise management must make the right decision in many business activities based on both internal and external information. Thus, providing accurate information plays a prominent role in management's decision making. Intuitively, historical data can provide a feasible estimate through the forecasting models. Therefore, if the service department can estimate the service quantity for the next period, the service department can then effectively control the inventory of service related resources such as human, parts, and other facilities. In addition, the production department can make load map for improving its product quality. Therefore, obtaining an accurate service forecast most likely appears to be critical to manufacturing companies. Numerous investigations addressing this problem have generally employed statistical methods, such as regression or autoregressive and moving average simulation. However, these methods are only efficient for data with are seasonal or cyclical. If the data are influenced by the special characteristics of product, they are not feasible. In our research, we propose a forecasting framework that predicts service demand of manufacturing organization by combining Case-based reasoning (CBR) and leveraging an unsupervised artificial neural network based clustering analysis (i.e., Self-Organizing Maps; SOM). We believe that this is one of the first attempts at applying unsupervised artificial neural network-based machine-learning techniques in the service forecasting domain. Our proposed approach has several appealing features : (1) We applied CBR and SOM in a new forecasting domain such as service demand forecasting. (2) We proposed our combined approach between CBR and SOM in order to overcome limitations of traditional statistical forecasting methods and We have developed a service forecasting tool based on the proposed approach using an unsupervised artificial neural network and Case-based reasoning. In this research, we conducted an empirical study on a real digital TV manufacturer (i.e., Company A). In addition, we have empirically evaluated the proposed approach and tool using real sales and service related data from digital TV manufacturer. In our empirical experiments, we intend to explore the performance of our proposed service forecasting framework when compared to the performances predicted by other two service forecasting methods; one is traditional CBR based forecasting model and the other is the existing service forecasting model used by Company A. We ran each service forecasting 144 times; each time, input data were randomly sampled for each service forecasting framework. To evaluate accuracy of forecasting results, we used Mean Absolute Percentage Error (MAPE) as primary performance measure in our experiments. We conducted one-way ANOVA test with the 144 measurements of MAPE for three different service forecasting approaches. For example, the F-ratio of MAPE for three different service forecasting approaches is 67.25 and the p-value is 0.000. This means that the difference between the MAPE of the three different service forecasting approaches is significant at the level of 0.000. Since there is a significant difference among the different service forecasting approaches, we conducted Tukey's HSD post hoc test to determine exactly which means of MAPE are significantly different from which other ones. In terms of MAPE, Tukey's HSD post hoc test grouped the three different service forecasting approaches into three different subsets in the following order: our proposed approach > traditional CBR-based service forecasting approach > the existing forecasting approach used by Company A. Consequently, our empirical experiments show that our proposed approach outperformed the traditional CBR based forecasting model and the existing service forecasting model used by Company A. The rest of this paper is organized as follows. Section 2 provides some research background information such as summary of CBR and SOM. Section 3 presents a hybrid service forecasting framework based on Case-based Reasoning and Self-Organizing Maps, while the empirical evaluation results are summarized in Section 4. Conclusion and future research directions are finally discussed in Section 5.

• Journal of muscle and joint health
• /
• v.8 no.1
• /
• pp.122-140
• /
• 2001

The aims of this study were to understand and to predict the determinent factors affecting the exercise behaviors and physical fitness by testing the Pender's revised health promotion model, and to help the patients with rheumatoid arthritis and osteoarthritis perform the continous exercise program, and to help them maximize the physical effect such as muscle strength, endurance, and functional status and mental effects including self efficacy and quality of life, and improve the physical and mental well being, and to provide a basis for the nursing intervention strategies. Of the selected variables in this study, the endogenous variables included the physical fitness, exercise score, exercise participation, perceived benefits of action, perceived barriers of action to exercise, activity-related affect(depression) and perceived self-efficacy, interpersonal influences(family support), situational factors(duration of arthritis, fatigue) and the exogenous variables included personal sociocultural factor(education level), personal biologic factor(body mass index), personal psychologic factor(perceived health status) and prior related behavior factors(previous participation in exercise, life-style). We analyzed the clinical records of 208 patients with rheumatoid arthritis and degenerative arthritis who visited the outpatient clinics at H university hospital in Seoul. Data were composed of self reported qustionnaire and good of fitness score which were obtained by padalling the ergometer of bicycle for 9 minutes. SPSS Win 8.0 and Window LISREL 8.12a were used for statistical analysis. Of 75 hypothetical paths that influence on physical fitness, exercise participation, exercise score, perceived benefits of action, perceived barriers of action to exercise, activity-related affect(depression) and perceived self-efficacy, interpersonal influences(family support), situational factors(duration of arthritis, fatigue), 40 were supported. The physical fitness was directly influenced by life-style, perceived health status, education level, family support, fatigue, which explained 12% of physical fitness. The exercise participation were directly influenced by life-style, education level, past exercise behavior, perceived benefits of action, perceived barriers of action, depression and duration of arthritis, which explained 47% of exercise participation. Exercise score were directly affected by perceived self efficacy. BMI, life-style, past exercise behavior, perceived benefits of action, family support, perceived health status. perceived barriers of action, and fatigue, which explained 70%. Perceived benefits of action was directly influenced by BMI, life-style, which explained 39%. Perceived barriers of action were directly influeced by past exercise behavior, perceived health status, which explained 7%. Perceived self efficacy were directly influeced by level of education, perceived health status, life-style, which explained 57%. Depression were directly influeced by past exercise behavior, BMI, life-style, which explained 27%. Family support were directly influeced by life-style, perceived health status, which explained 29%. Fatigue were directly influeced by BMI, life-style, perceived health status. which explained 41%. Duration of arthritis were directly influeced by life-style, past exercise behavior, BMI, which explained 6%. In conclusion, important variables for physical fitness were life-style, and variable affecting exercise participation were life-style. Perceived self-efficacy of exercise was a significant predictor of exercise score. BMI, Life-style, perceived benefits of action, family support, past exercise behavior showed direct effects on perceived self-efficacy. Therefore, disease related factor should be minimized for physical performance and well being in nursing intervention for patients with rheumatoid arthritis, and plans to promote and continue exercise should be seeked to reduce disability. In addition, Exercise program should be planned and performed by the exact evaluation of exercise according to the ability of the patients and the contents to improve the importance of exercise and self efficacy in self control program, dedicated educational program should be involved. This study suggest that the methods to reduce the disease related factors, the importance of daily life-style, recognition of benefit of exercise, and educational program to promote self efficacy should be considered in the exercise behavior promotion and nursing intervention for continous performance. The significance of this study is also thought to provide patients with chronic arthritis the specific data for maximal physical and mental well being through exercise, chronic therapeutic procedure, daily adaptation and confrontation in nursing intervention.

• Journal of the Korean Institute of Landscape Architecture
• /
• v.44 no.6
• /
• pp.60-72
• /
• 2016

This study aims to suggest strategies of development and management for large parks by examining experimental cases of park governance models related to a shift away from public administration. The shifts towards governance as well as public-private partnership in city parks have involved the need for new public management. This study has analyzed two exemplary cases of Presidio Park and Sydney Harbour National Park in the aspects of planning process and management strategies, as the results derived the meaning and effect of park governance management and is also an essential prerequisite for the achievement of the model. There are six dimensions of research frames--namely policy, governance, partnership, finances and funds, design and maintenance-management, and evaluation-monitoring-taken as the basis for this study. Through the analysis, several key characteristics of these cases were elicited. First, the park planning process must be consistent in carrying a policy from planning to implementation, and furthermore, an independent operation body which can properly authorize an execution and uphold its responsibility from the public could serve in adaptable park services. Second, it has been suggested to build various partnerships with PAs and NGOs, private corporations, community groups, and academic institutes that allow it to expand the diversity of the park activities. Third, there has been experimental exploration to achieve a financially self-sufficient model by establishing internal revenue models and hence allow the reduction of reliance on public finances. The result of this type of park management would allow for improving park quality and make the park space a vital part of the local economy. Fourth, the strategies for a local community's participation are needed to allow the community to become a producer as well as a consumer. This study shows that the direction and significance of the park governance model regarding the fact that the plans sought by the two parks are extending the layout of public-centered discussion to the private sector and the third non-governmental sector including to the local community group. This shows both implications and limitations, such as the risk of privatization through non-governmental activities at the park or the violation of essential functions as a public good due to a profit-generating management policy for securing financial self-sufficiency. At the current point in which plans are under way for the development and management of large parks, a park governance model requires continuous study and expansion of discussion in the future.

• The Korean Journal of Nuclear Medicine
• /
• v.38 no.6
• /
• pp.528-531
• /
• 2004

Purpose: PET has some disadvantage in the imaging of small animal due to poor resolution. With the advent of microPET scanner, it is possible to image small animals. However, the image quality was not good enough as human image. Due to larger brain, cat brain imaging was superior to mouse or rat. In this study, we established the cat brain infarction model and evaluate it and its temporal charge using microPET scanner. Materials and Methods: Two adult male cats were used. Anesthesia was done with xylazine and ketamine HCl. A burr hole was made at 1cm right lateral to the bregma. Collagenase type IV 10 ${\mu}l$ was injected using 30 G needle for 5 minutes to establish the infarction model. $^{18}F$-FDG microPET (Concorde Microsystems Inc., Knoxville, TN) scans were performed 1, 11 and 32 days after the infarction. In addition, $^{18}F$-FDG PET scans were performed using human PET scanner (Gemini, Philips medical systems, CA, USA) 13 and 47 days after the infarction. Results: Two cat brain infarction models were established. The glucose metabolism of an infarction lesion improved with time. An infarction lesion was also distinguishable in the human PET scan. Conclusion: We successfully established the cat brain infarction model and evaluated the infarcted lesion and its temporal change using $^{18}F$-FDG microPET scanner.

• The Korean Journal of Nuclear Medicine Technology
• /
• v.18 no.2
• /
• pp.33-38
• /
• 2014

Purpose Auto exposure control (AEC) in SPECT/CT automatically controls the exposure dose (mA) according to patient's shape and size. The aim of this study was to evaluate the effect of AEC in SPECT/CT on exposure dose reduction and image quality. Materials and Methods The model of SPECT/CT used in this study was Discovery 670 (GE, USA), Smart mA for AEC; and $^{99m}Tc$ as a radioisotope. To compare SPECT and CT images by CT exposure dose variation, we used a standard technique set at 80, 100, 120, 140 kVp, 10, 30, 50, 100, 150, 200, 250 mA, and AEC at 80, 100, 120, 140 kVp, 10-250 mA. To evaluate resolution and contrast of SPECT images, triple line phantom and flangeless Esser PET phantom were used. For CT images, noise and uniformity were checked by anthropomrphic chest phantom. For dose evaluation to find DLP value, anthropomorphic chest phantom was used and the CT protocol of torso was applied by standard technique (120 kVp, 100 mA) and AEC (120 kVp, 10-250 mA). Results When standard and AEC were applied, the resolutions at SPECT images with attenuation correction (AC) were the same as FWHM by center 3.65 mm, left 3.48 mm, right 3.61 mm. Contrasts of standard and AEC showed no significant difference: standard 53.5, 29.8, 22.5, 15.8, 6.0, AEC 53.5, 29.6, 22.4, 15.7, 6.1 In CT images, noise values at standard and AEC were 15.4 and 18.5 respectively. The application of AEC increases noise but the value of coefficient variation were 33.8, 24.9 respectively, obtaining uniform noise image. The values of DLP at standard and AEC were 426.78 and 352.09 each, which shows that the application of AEC decreases exposure dose more than standard by approximately 18%. Conclusion The results of our study show that there was no difference of AC in SPECT images based on the CT exposure dose variation at SPECT/CT images. It was found that the increased CT exposure dose leads to the improvement of CT image quality but also increases the exposure dose. Thus, the use of AEC in SPECT/CT contributes to obtaining equal AC SPECT images, and uniform noise in CT images while reducing exposure dose.

• Korean Journal of Ecology and Environment
• /
• v.39 no.2 s.116
• /
• pp.145-156
• /
• 2006

The objective of this study was to evaluate biological health conditions and physicochemical status using multi-metric models at five sites of the Keum-Ho River during August 2004 and June 2005. The research approach was based on a qualitative habitat evaluation index (QHEI), index of biological integrity (IBI) using fish assemblage, and long-term chemical data (1995 ${\sim}$ 2004), which was obtained from the Ministry of Environment, Korea. For the biological health assessments, regional model of the IBI in Korea (An,2003), was applied for this study. Mean IBI in the river was 30 and varied from 23 to 48 depending on the sampling sites. The river health was judged to be "fair condition", according to the stream health criteria of US EPA (1993) and Barbour et al. (1999). According to the analysis of the chemical water quality data of the river, BOD, COD, conductivity, TP, TN, and TSS largely varied epending on the sampling sites, seasons and years. Variabilities of some parameters including BOD, COD, TP, TN, and conductivity were greater in the downstream than in the upstream reach. This phenomenon was evident in the dilution by the rain during the monsoon. This indicates that precipitation is a very important factor of the chemical variations of water quality. Community analyses showed that species diversity index was highest (H=0.78) in the site 1, while community dominance index was highest in the site 3, where Opsariichthys uncirostris largely dominated. In contrast, the proportions of omnivore and tolerant species were greater in the downstream reach, than in the upstream reach. Overall, this study suggests that some sites in the downstream reach may need to restore the aquatic ecosystem for better biological health.

• Journal of the Korean Society of Radiology
• /
• v.13 no.4
• /
• pp.503-508
• /
• 2019

In short a binary value according to a change in the tube voltage by using one of VOLUME AXIAL MODE of scanning techniques of chest CT image quality evaluation in order to obtain high image and to present the appropriate tube voltage. CT instruments were GE Revolution (GE Healthcare, Wisconsin USA) model and Phantom used Pediatric Whole Body Phantom PBU-70. The test method was examined in Volume Axial mode using the pediatric protocol used in the Y university hospital of mass-produced material. The tube voltage was set to 70kvp, 80kvp, 100kvp, and mAs was set to smart mA-ODM. The mean SNR difference of the heart was $-4.53{\pm}0.26$ at 70 kvp, $-3.34{\pm}0.18$ at 80 kvp, $-1.87{\pm}0.15$ at 100 kvp, and SNR at 70 kvp was about -2.66 higher than 100 kvp and statistically significant (p<0.05) In the Lung SNR mean difference analysis, $-78.20{\pm}4.16$ at 70 kvp, $-79.10{\pm}4.39$ at 80 kvp, $-77.43{\pm}4.72$ at 100 kvp, and SNR at 70 kvp at about -0.77 higher than 100 kvp were statistically significant. (p<0.05). Lung CNR mean difference was $73.67{\pm}3.95$ at 70 kvp, $75.76{\pm}4.25$ at 80 kvp, $75.57{\pm}4.62$ at 100 kvp and 20.9 CNR at 80 kvp higher than 70 kvp and statistically significant (p<0.05) At 100 kvp of tube voltage, the SNR was close to 1 while maintaining the quality of the heart image when 70 kvp and 80 kvp were compared. However, there is no difference in SNR between 70 kvp and 80 kvp, and 70 kvp can be used to reduce the radiation dose. On the other and, CNR showed an approximate value of 1 at 70 kvp. There is no difference between 80 kvp and 100 kvp. Therefore, 80 kvp can reduce the radiation dose by pediatric chest CT. In addition, it is possible to perform a scan with a short scan time of 0.3 seconds in the volume axial mode test, which is useful for pediatric patients who need to move or relax.

• Journal of Digital Convergence
• /
• v.11 no.5
• /
• pp.347-354
• /
• 2013

In contrast to the increase in demand for high quality healthcare, there is limited medical human resources such as doctors and nurses so an excessive amount of workload is being forced to them. Therefore, a patient monitoring system using USN(Ubiquitous Sensor Network) is becoming a solution. This paper proposes a patient monitoring system applying USN in maternity hospital to reduce the workload of nurses. According to the efficiency evaluation test based on the model of two university hospitals(S, K University Hospital) and their doctor's diagnosis, the results showed that under the circumstances that one nurse is in charge of 12 patients(6 normal delivery patients and 6 cesarean delivery patients), a total of 1,260 minutes of workload was saved during hospitalization period(5 days). Also, we compared the workload of nurses with or without our proposed system, and the figures showed that in case of normal delivery patients, the workload of nurses decreased by 50 minutes per patient, whereas in case of cesarean delivery patients, the workload of nurses decreased by 130 minutes per patient.