• Journal of the Korea Academia-Industrial cooperation Society
• /
• v.17 no.10
• /
• pp.520-526
• /
• 2016

This study aims to develop a distress prediction model, in order to evaluate the distress prediction power for first-class hotels and to calculate the average financial ratio in the Seoul area by using the financial ratios of hotels in 2015. The sample data was collected from 19 first-class hotels in Seoul and the financial ratios extracted from 14 of these 19 hotels. The results show firstly that the seven financial ratios, viz. the current ratio, total borrowings and bonds payable to total assets, interest coverage ratio to operating income, operating income to sales, net income to stockholders' equity, ratio of cash flows from operating activities to sales and total assets turnover, enable the top-level corporations to be discriminated from the failed corporations and, secondly, by using these seven financial ratios, a discriminant function which classifies the corporations into top-level and failed ones is estimated by linear multiple discriminant analysis. The accuracy of prediction of this discriminant capability turned out to be 87.9%. The accuracy of the estimates obtained by discriminant analysis indicates that the distress prediction model's distress prediction power is 78.95%. According to the analysis results, hotel management groups which administrate low level corporations need to focus on the classification of these seven financial ratios. Furthermore, hotel corporations have very different financial structures and failure prediction indicators from other industries. In accordance with this finding, for the development of credit evaluation systems for such hotel corporations, there is a need for systems to be developed that reflect hotel corporations' financial features.

• Journal of Intelligence and Information Systems
• /
• v.24 no.4
• /
• pp.1-32
• /
• 2018

In addition to stakeholders including managers, employees, creditors, and investors of bankrupt companies, corporate defaults have a ripple effect on the local and national economy. Before the Asian financial crisis, the Korean government only analyzed SMEs and tried to improve the forecasting power of a default prediction model, rather than developing various corporate default models. As a result, even large corporations called 'chaebol enterprises' become bankrupt. Even after that, the analysis of past corporate defaults has been focused on specific variables, and when the government restructured immediately after the global financial crisis, they only focused on certain main variables such as 'debt ratio'. A multifaceted study of corporate default prediction models is essential to ensure diverse interests, to avoid situations like the 'Lehman Brothers Case' of the global financial crisis, to avoid total collapse in a single moment. The key variables used in corporate defaults vary over time. This is confirmed by Beaver (1967, 1968) and Altman's (1968) analysis that Deakins'(1972) study shows that the major factors affecting corporate failure have changed. In Grice's (2001) study, the importance of predictive variables was also found through Zmijewski's (1984) and Ohlson's (1980) models. However, the studies that have been carried out in the past use static models. Most of them do not consider the changes that occur in the course of time. Therefore, in order to construct consistent prediction models, it is necessary to compensate the time-dependent bias by means of a time series analysis algorithm reflecting dynamic change. Based on the global financial crisis, which has had a significant impact on Korea, this study is conducted using 10 years of annual corporate data from 2000 to 2009. Data are divided into training data, validation data, and test data respectively, and are divided into 7, 2, and 1 years respectively. In order to construct a consistent bankruptcy model in the flow of time change, we first train a time series deep learning algorithm model using the data before the financial crisis (2000~2006). The parameter tuning of the existing model and the deep learning time series algorithm is conducted with validation data including the financial crisis period (2007~2008). As a result, we construct a model that shows similar pattern to the results of the learning data and shows excellent prediction power. After that, each bankruptcy prediction model is restructured by integrating the learning data and validation data again (2000 ~ 2008), applying the optimal parameters as in the previous validation. Finally, each corporate default prediction model is evaluated and compared using test data (2009) based on the trained models over nine years. Then, the usefulness of the corporate default prediction model based on the deep learning time series algorithm is proved. In addition, by adding the Lasso regression analysis to the existing methods (multiple discriminant analysis, logit model) which select the variables, it is proved that the deep learning time series algorithm model based on the three bundles of variables is useful for robust corporate default prediction. The definition of bankruptcy used is the same as that of Lee (2015). Independent variables include financial information such as financial ratios used in previous studies. Multivariate discriminant analysis, logit model, and Lasso regression model are used to select the optimal variable group. The influence of the Multivariate discriminant analysis model proposed by Altman (1968), the Logit model proposed by Ohlson (1980), the non-time series machine learning algorithms, and the deep learning time series algorithms are compared. In the case of corporate data, there are limitations of 'nonlinear variables', 'multi-collinearity' of variables, and 'lack of data'. While the logit model is nonlinear, the Lasso regression model solves the multi-collinearity problem, and the deep learning time series algorithm using the variable data generation method complements the lack of data. Big Data Technology, a leading technology in the future, is moving from simple human analysis, to automated AI analysis, and finally towards future intertwined AI applications. Although the study of the corporate default prediction model using the time series algorithm is still in its early stages, deep learning algorithm is much faster than regression analysis at corporate default prediction modeling. Also, it is more effective on prediction power. Through the Fourth Industrial Revolution, the current government and other overseas governments are working hard to integrate the system in everyday life of their nation and society. Yet the field of deep learning time series research for the financial industry is still insufficient. This is an initial study on deep learning time series algorithm analysis of corporate defaults. Therefore it is hoped that it will be used as a comparative analysis data for non-specialists who start a study combining financial data and deep learning time series algorithm.

• Journal of Veterinary Clinics
• /
• v.27 no.5
• /
• pp.533-539
• /
• 2010

Stem cell-based therapy is under intensive investigation to treat acute renal failure (ARF). The purpose of this study was to evaluate available ARF models, and suggest a model appropriate to therapeutic evaluation of the stem cells in preclinical approach by determining the optimum concentration of nephrotoxic agents and duration of ischemia induction. Three different types of available acute kidney injury (AKI) animal models were analyzed using rats: Cisplatin (saline, 5 and 7.5 mg/kg, IP) or glycerol (saline, 8 and 10 ml/kg, IM)-induced nephrotoxicity as toxic models and ischemia-induced (sham, 35 and 45 minutes) nephropathy as an ischemic model. The relevance and applicability to investigate especially the regenerative ability of stem cells were evaluated regarding morphology, renal function and survival at this time point. In the point of renal function, 10 ml glycerol/kg and 7.5 mg cisplatin/kg model in toxic models and 45 min model in ischemia models showed significant decrease for the longer observation time compared to 8 ml glycerol/kg, 5 mg cisplatin/kg and the 35 min ischemia models, respectively. All groups were observed no mortality except 45 min-ischemia model with 50% survival. Histological significant alterations including cast formation in the tubular lumen, tubular necrosis and apoptosis were revealed on the second day in either ischemiaor glycerol-induced models, and on day 5 in cisplatin-induced models. The results indicate that ischemia 35 min-, cisplatin 7.5 mg/kg- and glycerol 10 ml/kg-induced AKI would be ideal animal models to monitor a outcome parameter related to the therapeutic effects on renal function with noninvasive techniques in the same animal at multiple time points. Our findings also suggest that the best time points for the functional or histological interpretation of renal will be on day 2 in both glycerol- and ischemia-induced AKI models and on day 5 in cisplatin-induced AKI.

• Journal of Preventive Medicine and Public Health
• /
• v.30 no.1 s.56
• /
• pp.195-207
• /
• 1997

High price equipment is one of the major factors that increases national health expenditure in developed countries. Computerized Tomography(CT), one of the important high price equipment, has been concerns of health service researchers and policy makers in many countries. In Korea, CT, first introduced in 1984, have spreaded nationwide with rapid speed. Though the Committee for Approving Import of High Price Medical Equipment, founded in 1981, tried to regulate the introduction of high price medical equipment including CT, the effort resulted in failure. The exact situation of diffusion of the high price equipment, however, was not yet investigated. We aimed at the description of the diffusion of CT in Korea and analysis of influencing factors on hospitals for the adoption of CT. We mainly used the database of CT, made in 1996 by the National Federation of Medical Insurance for the purpose of insurance payment for CT. Also characteristics of hospitals were gathered from yearbooks published by the central and local governments and by the Korean Hospital Association. We calculated the cumulative number of the CT per one million population year by year. In turn, multiple linear logistic regression was done to find out the contributing factors for the adoption of CT by each hospital. In the logistic regression model, it is regarded as dependent factor whether a hospital retained CT or not in 1988 and 1993. The major categories of the independent factors were hospital characteristics, environmental factors and competitive conditions of hospitals at the period of the adoption. The results are as follows: Number of CT scanners per one million persons in Korea marked more higher level compared with those of most OECD countries. Major influencing factors on the adoption of CT scanners were hospital characteristics, such as hospital referral level, and competitive condition of hospitals, such as number of CT scanners per 10,000 persons in each district where the hospital was located. In Korea, CT diffused with rather rapid speed, comparable with those of the United States and Japan. The major factors contributing on the adoption of CT for hospitals were competitive condition and hospital characteristics rather than regional health care need for CT. In conclusion, a kind of regulating mechanism would be necessary for the prevention of the indiscreet adoption and inefficient use of high price equipment including CT.

• Clinical and Experimental Pediatrics
• /
• v.51 no.6
• /
• pp.584-596
• /
• 2008

Purpose : This study was conducted to investigate treatment compliance and related factors in pediatric patients. Methods : Three hundred and fifty-five patients diagnosed with various acute diseases at a teaching hospital or clinic in October 2003 were enrolled. Data were analyzed using the Health Belief Model, which includes items on self-efficacy and family assistance. Results : The study found that 62.9% of pediatric patients adhered faithfully to agreed-upon hospital revisits, 41.6% complied with dose timings instructions, 65.8% precisely took medication, and 27.2% complied with all of these requirements. According to ${\chi}^2$ test analysis, the factors found to be related to therapeutic compliance (the taking of medicines requested) were; susceptibility, severity, benefit, barriers, mother's self-efficacy, and family assistance (P<.05). Multiple logistic analysis and path analysis showed that susceptibility, severity, barriers, and mother's self-efficacy were related to therapeutic compliance (P<.05). Moreover, mother's self-efficacy was identified as the most important factor. Conclusion : To improve therapeutic compliance among pediatric patients, parental education is necessary, and a health care professional must take a thorough history of how the medication was taken before it is assumed that treatment failure is attributable to the medication prescribed. Furthermore, the type of device recommended for dosing should be determined by clinicians. In addition, it is important that pediatric medications be discussed in relation to their palatability and internal acceptability.

• Journal of Intelligence and Information Systems
• /
• v.27 no.4
• /
• pp.1-22
• /
• 2021

Aspect Based Sentiment Analysis (ABSA), which analyzes sentiment based on aspects that appear in the text, is drawing attention because it can be used in various business industries. ABSA is a study that analyzes sentiment by aspects for multiple aspects that a text has. It is being studied in various forms depending on the purpose, such as analyzing all targets or just aspects and sentiments. Here, the aspect refers to the property of a target, and the target refers to the text that causes the sentiment. For example, for restaurant reviews, you could set the aspect into food taste, food price, quality of service, mood of the restaurant, etc. Also, if there is a review that says, "The pasta was delicious, but the salad was not," the words "steak" and "salad," which are directly mentioned in the sentence, become the "target." So far, in ABSA, most studies have analyzed sentiment only based on aspects or targets. However, even with the same aspects or targets, sentiment analysis may be inaccurate. Instances would be when aspects or sentiment are divided or when sentiment exists without a target. For example, sentences like, "Pizza and the salad were good, but the steak was disappointing." Although the aspect of this sentence is limited to "food," conflicting sentiments coexist. In addition, in the case of sentences such as "Shrimp was delicious, but the price was extravagant," although the target here is "shrimp," there are opposite sentiments coexisting that are dependent on the aspect. Finally, in sentences like "The food arrived too late and is cold now." there is no target (NULL), but it transmits a negative sentiment toward the aspect "service." Like this, failure to consider both aspects and targets - when sentiment or aspect is divided or when sentiment exists without a target - creates a dual dependency problem. To address this problem, this research analyzes sentiment by considering both aspects and targets (Target-Aspect-Sentiment Detection, hereby TASD). This study detected the limitations of existing research in the field of TASD: local contexts are not fully captured, and the number of epochs and batch size dramatically lowers the F1-score. The current model excels in spotting overall context and relations between each word. However, it struggles with phrases in the local context and is relatively slow when learning. Therefore, this study tries to improve the model's performance. To achieve the objective of this research, we additionally used auxiliary loss in aspect-sentiment classification by constructing CNN(Convolutional Neural Network) layers parallel to existing models. If existing models have analyzed aspect-sentiment through BERT encoding, Pooler, and Linear layers, this research added CNN layer-adaptive average pooling to existing models, and learning was progressed by adding additional loss values for aspect-sentiment to existing loss. In other words, when learning, the auxiliary loss, computed through CNN layers, allowed the local context to be captured more fitted. After learning, the model is designed to do aspect-sentiment analysis through the existing method. To evaluate the performance of this model, two datasets, SemEval-2015 task 12 and SemEval-2016 task 5, were used and the f1-score increased compared to the existing models. When the batch was 8 and epoch was 5, the difference was largest between the F1-score of existing models and this study with 29 and 45, respectively. Even when batch and epoch were adjusted, the F1-scores were higher than the existing models. It can be said that even when the batch and epoch numbers were small, they can be learned effectively compared to the existing models. Therefore, it can be useful in situations where resources are limited. Through this study, aspect-based sentiments can be more accurately analyzed. Through various uses in business, such as development or establishing marketing strategies, both consumers and sellers will be able to make efficient decisions. In addition, it is believed that the model can be fully learned and utilized by small businesses, those that do not have much data, given that they use a pre-training model and recorded a relatively high F1-score even with limited resources.

• Management & Information Systems Review
• /
• v.36 no.3
• /
• pp.219-237
• /
• 2017

Looking into the top-five innovative sectors in Korea's manufacturing and service industries, this study empirically analyzes the effect of innovation performance on R&D investment, which is one of the most important strategic decisions for corporate management. In the midst of an uncertain business environment, R&D investment has been regarded as the most important strategic decision making in corporate management related to innovation. Corporate management, however, tend to be reluctant to make sufficient R&D investment due to the risk of an investment failure. Therefore, having R&D investment by offsetting this risk has been deemed as a key task for corporate management. However, prior studies have failed to identify which factors affect companies' strategic decision making on R&D investment. This study is to remedy this weakness of prior study. Relying on path dependency theory at organization-level and dominant logic at individual-level, this study empirically examines the multiple regression model, which sees entrepreneurial orientation as a positive mediator between innovation performance and R&D investment. The results found in the analysis of 242 local companies in the manufacturing and service sectors represent that innovation performance has a direct and positive effect on R&D investment, while it indirectly affects R&D investment through the mediating roles of entrepreneurial orientation. They also revealed that innovation performance had a meaningful impact on entrepreneurial orientation, which is an inclination to seek innovation, led to R&D investment. The founding of this study imply that innovation performance in the past affects innovation strategies in the future, and such a relationship could be strengthened by entrepreneurial orientation as the dominant logic of corporate management.

• Journal of Preventive Medicine and Public Health
• /
• v.30 no.3 s.58
• /
• pp.585-598
• /
• 1997

Background : Although there are growing concerns about the adverse health effect of air pollution, not much evidence on health effect of current air pollution level had been accumulated yet in Korea. This study was designed to evaluate the chronic health effect of ai. pollution using Korean Medical Insurance Corporation (KMIC) data and air quality data. Medical insurance data in Korea have some drawback in accuracy, but they do have some strength especially in their national coverage, in having unified ID system and individual information which enables various data linkage and chronic health effect study. Method : This study utilized the data of Korean Environmental Surveillance System Study (Surveillance Study), which consist of asthma, acute bronchitis, chronic obstructive pulmonary diseases (COPD), cardiovascular diseases (congestive heart failure and ischemic heart disease), all cancers, accidents and congenital anomaly, i. e., mainly potential environmental diseases. We reconstructed a nested case-control study wit5h Surveillance Study data and air pollution data in Korea. Among 1,037,210 insured who completed? questionnaire and physical examination in 1992, disease free (for chronic respiratory disease and cancer) persons, between the age of 35-64 with smoking status information were selected to reconstruct cohort of 564,991 persons. The cohort was followed-up to 1995 (1992-5) and the subjects who had the diseases in Surveillance Study were selected. Finally, the patients, with address information and available air pollution data, left to be 'final subjects' Cases were defined to all lung cancer cases (424) and COPD admission cases (89), while control groups are determined to all other patients than two case groups among 'final subjects'. That is, cases are putative chronic environmental diseases, while controls are mainly acute environmental diseases. for exposure, Air quality data in 73 monitoring sites between 1991 - 1993 were analyzed to surrogate air pollution exposure level of located areas (58 areas). Five major air pollutants data, TSP, $O_3,\;SO_2$, CO, NOx was available and the area means were applied to the residents of the local area. 3-year arithmetic mean value, the counts of days violating both long-term and shot-term standards during the period were used as indices of exposure. Multiple logistic regression model was applied. All analyses were performed adjusting for current and past smoking history, age, gender. Results : Plain arithmetic means of pollutants level did not succeed in revealing any relation to the risk of lung cancer or COPD, while the cumulative counts of non-at-tainment days did. All pollutants indices failed to show significant positive findings with COPD excess. Lung cancer risks were significantly and consistently associated with the increase of $O_3$ and CO exceedance counts (to corrected error level -0.017) and less strongly and consistently with $SO_2$ and TSP. $SO_2$ and TSP showed weaker and less consistent relationship. $O_3$ and CO were estimated to increase the risks of lung cancer by 2.04 and 1.46 respectively, the maximal probable risks, derived from comparing more polluted area (95%) with cleaner area (5%). Conclusions : Although not decisive due to potential misclassication of exposure, these results wert drawn by relatively conservative interpretation, and could be used as an evidence of chronic health effect especially for lung cancer. $O_3$ might be a candidate for promoter of lung cancer, while CO should be considered as surrogated measure of motor vehicle emissions. The control selection in this study could have been less appropriate for COPD, and further evaluation with another setting might be necessary.