• Journal of Intelligence and Information Systems
• /
• v.22 no.1
• /
• pp.139-157
• /
• 2016

Bankruptcy involves considerable costs, so it can have significant effects on a country's economy. Thus, bankruptcy prediction is an important issue. Over the past several decades, many researchers have addressed topics associated with bankruptcy prediction. Early research on bankruptcy prediction employed conventional statistical methods such as univariate analysis, discriminant analysis, multiple regression, and logistic regression. Later on, many studies began utilizing artificial intelligence techniques such as inductive learning, neural networks, and case-based reasoning. Currently, ensemble models are being utilized to enhance the accuracy of bankruptcy prediction. Ensemble classification involves combining multiple classifiers to obtain more accurate predictions than those obtained using individual models. Ensemble learning techniques are known to be very useful for improving the generalization ability of the classifier. Base classifiers in the ensemble must be as accurate and diverse as possible in order to enhance the generalization ability of an ensemble model. Commonly used methods for constructing ensemble classifiers include bagging, boosting, and random subspace. The random subspace method selects a random feature subset for each classifier from the original feature space to diversify the base classifiers of an ensemble. Each ensemble member is trained by a randomly chosen feature subspace from the original feature set, and predictions from each ensemble member are combined by an aggregation method. The k-nearest neighbors (KNN) classifier is robust with respect to variations in the dataset but is very sensitive to changes in the feature space. For this reason, KNN is a good classifier for the random subspace method. The KNN random subspace ensemble model has been shown to be very effective for improving an individual KNN model. The k parameter of KNN base classifiers and selected feature subsets for base classifiers play an important role in determining the performance of the KNN ensemble model. However, few studies have focused on optimizing the k parameter and feature subsets of base classifiers in the ensemble. This study proposed a new ensemble method that improves upon the performance KNN ensemble model by optimizing both k parameters and feature subsets of base classifiers. A genetic algorithm was used to optimize the KNN ensemble model and improve the prediction accuracy of the ensemble model. The proposed model was applied to a bankruptcy prediction problem by using a real dataset from Korean companies. The research data included 1800 externally non-audited firms that filed for bankruptcy (900 cases) or non-bankruptcy (900 cases). Initially, the dataset consisted of 134 financial ratios. Prior to the experiments, 75 financial ratios were selected based on an independent sample t-test of each financial ratio as an input variable and bankruptcy or non-bankruptcy as an output variable. Of these, 24 financial ratios were selected by using a logistic regression backward feature selection method. The complete dataset was separated into two parts: training and validation. The training dataset was further divided into two portions: one for the training model and the other to avoid overfitting. The prediction accuracy against this dataset was used to determine the fitness value in order to avoid overfitting. The validation dataset was used to evaluate the effectiveness of the final model. A 10-fold cross-validation was implemented to compare the performances of the proposed model and other models. To evaluate the effectiveness of the proposed model, the classification accuracy of the proposed model was compared with that of other models. The Q-statistic values and average classification accuracies of base classifiers were investigated. The experimental results showed that the proposed model outperformed other models, such as the single model and random subspace ensemble model.

• Journal of Nutrition and Health
• /
• v.40 no.8
• /
• pp.736-744
• /
• 2007

Leptin, as an adipocyte-derived hormone, is an important regulator of food intake and energy expenditure. In the cross-sectional study, leptin was shown to be positively related to body adiposity and metabolic disorders in adults. However, there were very few studies which reported the leptin as a predictor of weight gain over time. We examined whether serum leptin can be used as an indicator of the present and 1-year past weight status in very young children. First grade students from elementary schools in Gwacheon City were enrolled in the study since 2005. The study subjects(total 375 students; 195 boys and 180 girls) participated in the investigation of both 2005 and 2006. Physical examinations including height, weight, waist circumference were done. To examine the prevalence of obesity, obesity index was used. Serum leptin was measured, and their nutritional status was also evaluated based on 3-Day dietary records. Serum leptin levels were strongly positively related with the value of the present BMI and with the value of the BMI one year before. We found no association with leptin levels and amount of energy intake and macronutrient intake in this children population. Children were divided into three groups according to leptin tertiles. The highest leptin tertile group showed highest prevalence of obesity in year 2006 as well as in year 2005. Serum leptin levels can reflect the weight status now and as well as 1-year before. Possibly serum leptin levels can predict the weight gain of year later. Without an action against the obesity on children with high leptin level, those children would maintain the excess adiposity growth and progress into the obesity-related metabolic disorders. Further studies are needed to predict the obesity as early as possible and preventive system then after.

• Spatial Information Research
• /
• v.22 no.1
• /
• pp.55-63
• /
• 2014

Near surface air temperature data which are one of the essential factors in hydrology, meteorology and climatology, have drawn a substantial amount of attention from various academic domains and societies. Meteorological observations, however, have high spatio-temporal constraints with the limits in the number and distribution over the earth surface. To overcome such limits, many studies have sought to estimate the near surface air temperature from satellite image data at a regional or continental scale with simple regression methods. Alternatively, we applied various Kriging methods such as ordinary Kriging, universal Kriging, Cokriging, Regression Kriging in search of an optimal estimation method based on near surface air temperature data observed from automatic weather stations (AWS) in South Korea throughout 2010 (365 days) and MODIS land surface temperature (LST) data (MOD11A1, 365 images). Due to high spatial heterogeneity, auxiliary data have been also analyzed such as land cover, DEM (digital elevation model) to consider factors that can affect near surface air temperature. Prior to the main estimation, we calculated root mean square error (RMSE) of temperature differences from the 365-days LST and AWS data by season and landcover. The results show that the coefficient of variation (CV) of RMSE by season is 0.86, but the equivalent value of CV by landcover is 0.00746. Seasonal differences between LST and AWS data were greater than that those by landcover. Seasonal RMSE was the lowest in winter (3.72). The results from a linear regression analysis for examining the relationship among AWS, LST, and auxiliary data show that the coefficient of determination was the highest in winter (0.818) but the lowest in summer (0.078), thereby indicating a significant level of seasonal variation. Based on these results, we utilized a variety of Kriging techniques to estimate the surface temperature. The results of cross-validation in each Kriging model show that the measure of model accuracy was 1.71, 1.71, 1.848, and 1.630 for universal Kriging, ordinary Kriging, cokriging, and regression Kriging, respectively. The estimates from regression Kriging thus proved to be the most accurate among the Kriging methods compared.

• Journal of Chest Surgery
• /
• v.35 no.3
• /
• pp.177-181
• /
• 2002

Background: Follow-up studies have shown that although outcomes have improved substantially over time, results of the Fontan operation and its modifications remain suboptimal. In this study, we reviewed our experience with the extracardiac conduit Fontan operation, with a focus early and midterm change of internal diameter of PTFE conduit. Material and Method: Between April 1997 and July 2000 were reviewed. Twelve patients (M:6, F:6, mean age 42.04 $\pm$ 12.43months, mean body weight 13.80$\pm$ 1.94kg) underwent extracardiac conduit Fontan operation with expanded PTFE graft. Mean cardiopulmonary bypass time was 109.7$\pm$26.99minute and mean operation time was 455$\pm$89.51minute. Intraoperative fenestration was performed in 10 patients. The aortic cross clamping was not performed in all patients. Result: There was no early deaths and no postoperative dysrhythmia. Postoperative protein losing enteropathy and prolonged pleural effusion occurred in 1(8.3%) and 4 patients(33.3%). Conduit patency was evaluated by magnetic resonance imaging studies. A 9.84$\pm$3.84% mean reduction in conduit internal diameter and there was no statistical correlation between the change of internal diameter of conduit and the postoperative duration after partial correlation analysis(r=0.019, p=0.955). Conclusion: These results demonstrate that the extracardiac conduit Fontan operation provies good early and midterm results and may reduce the prevalence of late arrhythmia. And there is no correlation between the change of internal diameter of conduit and the postoperative duration after extracardiac conduit Fontan operation with the expanded PTFE graft conduit.

• Asia Marketing Journal
• /
• v.7 no.3
• /
• pp.53-76
• /
• 2005

With rapid technological and market change, new product development (NPD) complexity is a significant issue that organizations continually face in their development projects. There are numerous factors, which cause development projects to become increasingly costly & complex. A product is more likely to be successfully developed and marketed when the complexity inherent in NPD projects is clearly understood and carefully managed. Based upon the previous studies, this study examines the nature and importance of complexity in developing new products and then identifies several issues in managing complexity. Issues considered include: definition of complexity : consequences of complexity; and methods for managing complexity in NPD projects. To achieve high performance in managing complexity in development projects, these issues need to be addressed, for example: A. Complexity inherent in NPD projects is multi-faceted and multidimensional. What factors need to be considered in defining and/or measuring complexity in a development project? For example, is it sufficient if complexity is defined only from a technological perspective, or is it more desirable to consider the entire array of complexity sources which NPD teams with different functions (e.g., marketing, R&D, manufacturing, etc.) face in the development process? Moreover, is it sufficient if complexity is measured only once during a development project, or is it more effective and useful to trace complexity changes over the entire development life cycle? B. Complexity inherent in a project can have negative as well as positive influences on NPD performance. Thus, which complexity impacts are usually considered negative and which are positive? Project complexity also can affect the entire organization. Any complexity could be better assessed in broader and longer perspective. What are some ways in which the long-term impact of complexity on an organization can be assessed and managed? C. Based upon previous studies, several approaches for managing complexity are derived. What are the weaknesses & strengths of each approach? Is there a desirable hierarchy or order among these approaches when more than one approach is used? Are there differences in the outcomes according to industry and product types (incremental or radical)? Answers to these and other questions can help organizations effectively manage the complexity inherent in most development projects. Complexity is worthy of additional attention from researchers and practitioners alike. Large-scale empirical investigations, jointly conducted by researchers and practitioners, will help gain useful insights into understanding and managing complexity. Those organizations that can accurately identify, assess, and manage the complexity inherent in projects are likely to gain important competitive advantages.

• KOREAN JOURNAL OF CROP SCIENCE
• /
• v.28 no.2
• /
• pp.216-226
• /
• 1983

Genetic studies on the $F_2$ generation of a set of half diallel crosses involving six cowpea varieties were conducted. by the randomized block design with three replications to determine combining ability, gene action and the relationships between parents and their $F_2$ hybrids. The 12 agronomic characters namely, days to flowering, days from flowering to maturity, days to maturity, diameter of stem, length of internode, number of branches per plant, length of pod, number of pods per plant, number of grains per pod, number of grains per plant, 100 grain weight and grain weight per plot were observed, and the $F_2$ generation of this diallel set of crosses was analysed for each character according to the method by Jinks and Hayman. The results obtained are summarized as follows: 1. Vr-Wr graphical analyses; The following seven characters, days to flowering, number of branches per plant, length of pod, number of pods per plant, number of grains per plant, 100 grain weight and grain weight per plot appeared to be partially dominant, and over dominance was found for days from flowering to maturity, days to maturity, length of internode and number of grains per pod. But diameter of stem indicated partial dominance near complete dominance. 2. Estimates of genetic variance components; In the degree of dominance,. eight characters, that is, days to flowering, days from flowering to maturity, days to maturity, length of internode, number of pods per plant, number of grains per pod, number of grains per plant and grain weight per plot were expressed larger than 1. And the characters, days from flowering to maturity, number of branches per plant and number of grains per plant as the degree of mean dominance ($H_1$/D) were found to be negative value over other characters. On the other hand, apprent asymmetry of dominance-recessive allele ($H_2$ /$4H_1$) produced comparatively estimates with lower value on days from flowering to maturity, length of internode, number of branches per plant and number of grains per pod. 3. Analyses of combining ability; Mean square value of GCA(general combining ability) appeared to be more important than those of SCA (specific combining ability) for most characters, and among them, grain weight per plot showed the highest mean square value in GCA and SCA. 4. Effect of combining ability; Variety 178 was expressed as the highest GCA effects in five characters (days to flowering days to maturity, number of pods per plant, number of grains per plant and grain weight per plot). SCA effects were differed from parents, characters and crosses, but crosses between TVu 1857 $\times$ TVu 2885 and TVu 2702 $\times$ J78 were shown to be highly with SCA effects on yield.

• Journal of Intelligence and Information Systems
• /
• v.21 no.4
• /
• pp.93-110
• /
• 2015

The recommender system is a system which recommends products to the customers who are likely to be interested in. Based on automated information filtering technology, various recommender systems have been developed. Collaborative filtering (CF), one of the most successful recommendation algorithms, has been applied in a number of different domains such as recommending Web pages, books, movies, music and products. But, it has been known that CF has a critical shortcoming. CF finds neighbors whose preferences are like those of the target customer and recommends products those customers have most liked. Thus, CF works properly only when there's a sufficient number of ratings on common product from customers. When there's a shortage of customer ratings, CF makes the formation of a neighborhood inaccurate, thereby resulting in poor recommendations. To improve the performance of CF based recommender systems, most of the related studies have been focused on the development of novel algorithms under the assumption of using a single profile, which is created from user's rating information for items, purchase transactions, or Web access logs. With the advent of big data, companies got to collect more data and to use a variety of information with big size. So, many companies recognize it very importantly to utilize big data because it makes companies to improve their competitiveness and to create new value. In particular, on the rise is the issue of utilizing personal big data in the recommender system. It is why personal big data facilitate more accurate identification of the preferences or behaviors of users. The proposed recommendation methodology is as follows: First, multimodal user profiles are created from personal big data in order to grasp the preferences and behavior of users from various viewpoints. We derive five user profiles based on the personal information such as rating, site preference, demographic, Internet usage, and topic in text. Next, the similarity between users is calculated based on the profiles and then neighbors of users are found from the results. One of three ensemble approaches is applied to calculate the similarity. Each ensemble approach uses the similarity of combined profile, the average similarity of each profile, and the weighted average similarity of each profile, respectively. Finally, the products that people among the neighborhood prefer most to are recommended to the target users. For the experiments, we used the demographic data and a very large volume of Web log transaction for 5,000 panel users of a company that is specialized to analyzing ranks of Web sites. R and SAS E-miner was used to implement the proposed recommender system and to conduct the topic analysis using the keyword search, respectively. To evaluate the recommendation performance, we used 60% of data for training and 40% of data for test. The 5-fold cross validation was also conducted to enhance the reliability of our experiments. A widely used combination metric called F1 metric that gives equal weight to both recall and precision was employed for our evaluation. As the results of evaluation, the proposed methodology achieved the significant improvement over the single profile based CF algorithm. In particular, the ensemble approach using weighted average similarity shows the highest performance. That is, the rate of improvement in F1 is 16.9 percent for the ensemble approach using weighted average similarity and 8.1 percent for the ensemble approach using average similarity of each profile. From these results, we conclude that the multimodal profile ensemble approach is a viable solution to the problems encountered when there's a shortage of customer ratings. This study has significance in suggesting what kind of information could we use to create profile in the environment of big data and how could we combine and utilize them effectively. However, our methodology should be further studied to consider for its real-world application. We need to compare the differences in recommendation accuracy by applying the proposed method to different recommendation algorithms and then to identify which combination of them would show the best performance.

• Korean Journal of Biological Psychiatry
• /
• v.3 no.2
• /
• pp.222-239
• /
• 1996

The purpose of this study was to evaluate the effects of alcohol on the psychomotor performance and subjective assessment in healthy Korean adults with acetaldehyde dehydrogenase I(ALDH-I) isozyme variance. A total of 20 male subjects, half with active ALDH-I and the other half with inactive ALDH-I, were selected through both a self-reporting questionnaire examining alcohol sensitivity and the Higuchi's ethanol patch test detecting ALDH-I deficiency. In a doule-blind, placebo-controlled cross-over design, each subject consumed four doses of alcohol(0.25, 0.5, 0.75, 1.0g/kg) and placebo on five separate occasions at weekly intervals, Treatment order was fully balanced using a $5{\times}5$ Latin square, Psychomotor performance tests[coritical flicker fusion threshold(CFF) and choice reaction time(CRT)] and self-estimate questionnaires were conducted at baseline and at time points of 20, 40, 60, 90, 120, 150, 180 minutes after consuming the test drug for 20 minutes, Blood alcohol concentrations(BACs) using breath analyzer were measured at baseline and at time points of 10, 20, 30, 40, 50, 60, 75, 90, 105, 120, 150, 180 minutes after drinking, The BACs and the mean changes in the psychomotor performances and subjective assessments from pre-alcohol baseline, were compared between the two groups. The findings were summarized as follows : 1) BACs were tended to be higher in the inactive group than the active in all of the four alcohol doses. However significant group differences were only after the 0.5g/kg dose of alcohol. 2) The inactive group showed significant impairment in CFFT at most time points alter 0.75 and 1.0g/kg doses of alcohol. 3) In CRT, total reaction time(TRT) significantly prolonged in the inactive group than the active group at 20 minutes after 0.25 and 1.0g/kg doses of alcohol and at 40, 60, 90 minutes alter 0.75g/kg dose of alcohol. In the inactive group, recognition time component significantly increased at 20, 60, 90 minutes after 1.0g/kg dose of alcohol, while movement time component significantly increased at 40, 60 minutes after 0.75g/kg dose of alcohol. 4) Subjective evaluation of the effect of alcohol revealed that physical and mental conditions as well as a self-estimate of the effects of alcohol on performance were significantly worse in the inactive group than the active at some time points alter all of the lour alcohol doses, wihch were more pronounced after 0.75 and 1.0g/kg doses of alcohol. 5) Most of the group differences mentioned above, still remained statistically significant after BAC was entered as a covariate, These findings demonstrated that the alcohol sensitivity is higher in individuals with inactive ALDH-I than those with active ALDH-I both on the subjective assessments and the objective psychomotor performances. Furthermore, these results suggest thai the alcohol sensitivity may be determined by acetaldehyde concentration rather than BAC per se. In future studies, after more accurate genotyping for ALDH-I, the relationships between BAC, acetaldehyde concentration and alcohol sensitivities should be clearly defined.

• Asian-Australasian Journal of Animal Sciences
• /
• v.13 no.4
• /
• pp.464-469
• /
• 2000

Experiments were conducted to determine the effects of soybean meal (SBM) as a source of protein and sago meal (SM) as a source of carbohydrate on in situ and in vivo digestibility of dietary components in four male goats (Kambing Katjang) and four male sheep (Malin) weighing 25-35 kg. Rumen volume, as well as rumen fluid dilution rate were also determined. The animals were housed in single pens with individual feeding and drinking troughs and each animal was fitted with a rumen fistula. They were fed two diets : chopped rice straw+200 g soybean meal (SBM), and chopped rice straw+190 g soybean meal+300 g sago meal (SBM+SM). Rice straw was offered ad libitum. The supplements were isonitrogenous (80 g crude protein/animal/d), but the proportions of dry matter (DM), organic matter (OM), crude fibre (CF), neutral detergent fibre (NDF) and acid detergent fibre (ADF) were lower in the SBM supplement (191, 165, 11, 40, 15 g/animal/d for DM, OM, CF, NDF and ADF, respectively) than in the SBM+SM supplement (445, 423, 25, 102, 38 g/animal/d for DM, OM, CF, NDF and ADF, respectively). Two animals from each species were fed either supplement in a cross-over design in two periods. Each period lasted for four weeks. In situ and in vivo digestibility studies were carried out, followed by the determination of rumen volume and rumen fluid dilution rate. The results showed that straw DM and total DM intakes of goats (average of $48.7g/kg\;W^{0.75}$, $72.7g/kg\;W^{0.75}$, respectively) were significantly (p<0.01) higher than sheep (average of $3.56g/kg\;W^{0.75}$, $61.6g/kg\;W^{0.75}$, respectively), but OM, N and GE intakes were not significantly different between the two animal species. When the effect of supplements was compared, animals fed SBM+SM supplement had significantly (p<0.001) higher DM, OM and GE intakes than animals fed SBM supplement. Potential degradabilities of rice straw DM were significantly (p<0.01) higher in goats (average of 48.8%) than in sheep (average of 46.1 %). The supplements had no significant effect on the potential degradabilities of DM, OM and NDF, but they had a significant (p<0.05) effect on the degradation rates of DM and NDF. The addition of sago meal in the diet reduced the degradation rates of DM and NDF of rice straw in the rumen. Potential degradability of DM of soybean meal was not significantly different between animal species as well as between supplements. Sago meal was highly degradable. At 24 h of incubation in the rumen, 90-95% of DM loss was observed. There was a significant interaction between animal species and supplements in the in vivo digestibility of ADF and GE. In animals fed SBM supplement, the in vivo digestibility of ADF was significantly (p<0.05) higher in goats ($50.6{\pm}4.22%$) than in sheep ($44.4{\pm}3.21%$), but digestibility of GE was significantly (p<0.05) higher in sheep ($70.2{\pm}1.93%$) than in goats ($63.0{\pm}3.07%$). The digestibility values of CP and OM were significantly (p<0.05) higher in sheep when compared to goats. Animals fed SBM+SM supplement showed significantly (p<0.05) higher DM and OM digestibility values than animals fed SBM supplement, but digestibility values of CP were significantly (p<0.05) higher in animals fed SBM supplement. Differences in in vivo digestibility values of CF and NDF were not significantly different between animal species or supplements. Water intake, rumen volume ($1/kg\;W^{0.75}$), rumen fluid dilution rate and mean retention time were similar between the two animal species. However, rumen fluid dilution rate and mean retention time was significantly (p<0.01) affected by supplements. Animals fed SBM+SM had faster rumen fluid dilution rate and consequently shorter mean retention time.

• Journal of Hospice and Palliative Care
• /
• v.22 no.4
• /
• pp.145-155
• /
• 2019

Purpose: Amendment to the Act on Decisions on Life-sustaining Treatment was recently enacted to designate long-term care hospitals as providers of hospice and palliative care. Despite its benefit of providing improved accessibility to end-of-life care, the amendment has raised concerns about its effect on quality of service. This study aimed to use information obtained from an expert group interview and previous studies to compare how cancer patients, family caregivers, physicians, and the general Korean population perceive the potential benefits and risks of this amendment. Methods: We conducted a multicenter cross-sectional study from July to October 2016. The included participants answered a structured questionnaire regarding the extent to which they agree or disagree with the questionnaire items indicating the potential benefits and risks of the amendment. Chi-square tests and univariate and multivariate logistic regression analyses were performed. Results: Compared with the general population, physicians agreed more that long-term care hospitals are currently not adequately equipped to provide quality hospice and palliative care. Family caregivers found improved access to long-term care hospitals more favorable but were more likely to agree that these hospitals might prioritize profits, thereby threatening the philosophy of hospice care, and that families might cease to fulfill filial responsibilities. Compared with the general population, cancer patients were more concerned about the potentially decreased service quality in this setting. Conclusion: Although potential service beneficiaries and providers expected improved accessibility of hospice and palliative care services, they were also concerned whether the system can provide adequate quality of end-of-life care.