• Journal of Intelligence and Information Systems
• /
• v.10 no.2
• /
• pp.133-145
• /
• 2004

Combining multiple classifiers to obtain improved performance over the individual classifier has been a widely used technique. The task of constructing a multiple classifier system(MCS) contains two different issues : how to generate a diverse set of base-level classifiers and how to combine their predictions. In this paper, we review the characteristics of the existing multiple classifier systems: bagging, boosting, and stacking. And then we propose new MCSs: stacked bagging, stacked boosting, bagged stacking, and boasted stacking. These MCSs are a sort of hybrid MCSs that combine advantageous characteristics of the existing ones. In order to evaluate the performance of the proposed schemes, we conducted experiments with nine different real-world datasets from UCI KDD archive. The result of experiments showed the superiority of our hybrid MCSs, especially bagged stacking and boosted stacking, over the existing ones.

• Journal of Microbiology and Biotechnology
• /
• v.28 no.2
• /
• pp.227-235
• /
• 2018

Foodborne illness represents a major threat to public health and is frequently attributed to pathogenic microorganisms on fresh produce. Recurrent outbreaks often come from vegetables that are grown close to or within the ground. Therefore, the first step to understanding the public health risk of microorganisms on fresh vegetables is to identify and describe microbial communities. We investigated the phyllospheres on Chinese cabbage (Brassica rapa subsp. pekinensis, N = 54). 16S rRNA gene amplicon sequencing targeting the V5-V6 region of 16S rRNA genes was conducted by employing the Illumina MiSeq system. Sequence quality was assessed, and phylogenetic assessments were performed using the RDP classifier implemented in QIIME with a bootstrap cutoff of 80%. Principal coordinate analysis was performed using a weighted Fast UniFrac matrix. The average number of sequence reads generated per sample was 34,584. At the phylum level, bacterial communities were composed primarily of Proteobacteria and Bacteroidetes. The most abundant genera on Chinese cabbages were Chryseobacterium, Aurantimonadaceae_g, Sphingomonas, and Pseudomonas. Diverse potential pathogens, such as Pantoea, Erwinia, Klebsiella, Yersinia, Bacillus, Staphylococcus, Salmonella, and Clostridium were also detected from the samples. Although further epidemiological studies will be required to determine whether the detected potential pathogens are associated with foodborne illness, our results imply that a metagenomic approach can be used to detect pathogenic bacteria on fresh vegetables.

• Korean Journal of Fisheries and Aquatic Sciences
• /
• v.42 no.6
• /
• pp.642-649
• /
• 2009

Line transect data from sighting surveys conducted in the East Sea, Korea in 2000, 2002, 2003, 2005 and 2006 were analysed to estimate densities and numbers of minke whale. The half-normal model was fit to the survey in 2000 and the uniform model was the most fitable to the survey in 2002 and 2006, and the surveys in 2003 and 2005 were fit by the hazard-rate model. The estimated density of minke whale in the survey in 2000 was estimated as 0.026 individuals/$km^2$ (CV=0.409; 95% CI 0.011-0.065) and was higher than the survey in 2002 estimated as 0.018 individuals/$km^2$ (CV=0.329; 95% CI: 0.009-0.034). The estimated density of minke whale in the survey in 2003 was estimated as 0.033 individuals/$km^2$ (95% CI: 0.008-0.139) with the highest CV 0.760. The highest density was estimated in the survey in 2005 with 0.053 individuals/$km^2$ (95% CI: 0.020-0.141). The Lowest CV (0.306) was estimated in the survey in 2006 with 0.025 individuals/$km^2$ (95% CI: 0.014-0.046). A total of 500 bootstrap samples were generated within each stratum. Density, CV and 95% CI of each surveys were increased than analytic results except the survey in 2003. There were no increasing or decreasing annual trends in the density of minke whales observed during the study period. A long-term monitor and survey is needed to assess project minke whale abundance in the East Sea.

• Quality Improvement in Health Care
• /
• v.10 no.2
• /
• pp.216-231
• /
• 2003

Objectives: To develop a model that predicts a death probability of acute myocardial infarction(AMI) patient, and to evaluate a performance of hospital services using the developed model. Methods: Medical records of 861 AMI patients in 7 general hospitals during 1996 and 1997 were reviewed by two trained nurses. Variables studied were risk factors which were measured in terms of severity measures. A risk model was developed by using the logistic regression, and its performance was evaluated using cross-validation and bootstrap techniques. The statistical prediction capability of the model was assessed by using c-statistic, $R^2$ as well as Hosmer-Lemeshow statistic. The model performance was also evaluated using severity-adjusted mortalities of hospitals. Results: Variables included in the model building are age, sex, ejection fraction, systolic BP, congestive heart failure at admission, cardiac arrest, EKG ischemia, arrhythmia, left anterior descending artery occlusion, verbal response within 48 hours after admission, acute neurological change within 48 hours after admission, and 3 interaction terms. The c statistics and $R^2$ were 0.887 and 0.2676. The Hosmer-Lemeshow statistic was 6.3355 (p-value=0.6067). Among 7 hospitals evaluated by the model, two hospitals showed significantly higher mortality rates, while other two hospitals had significantly lower mortality rates, than the average mortality rate of all hospitals. The remaining hospitals did not show any significant difference. Conclusion: The comparison of the qualities of hospital service using risk-adjusted mortality rates indicated significant difference among them. We therefore conclude that risk-adjusted mortality rate of AMI patients can be used as an indicator for evaluating hospital performance in Korea.

• The Journal of the Korea Contents Association
• /
• v.18 no.5
• /
• pp.592-599
• /
• 2018

The purpose of this study is to examine whether the participation of lifelong learning activities of the elderly is a part of the self - The questionnaire consisted of 12 items of general characteristics, 5 items of lifelong education, 6 items of volunteer activity, 15 items of life satisfaction, and 10 items of self - integration. The subjects of this study were 300 elderly people aged 60 or older living in Seoul, Gyeonggi - do, and Incheon, and participated in lifelong educational institutions such as the elderly welfare center, elderly university, and ward. As a method of analysis, the structural equation model of AMOS 22.0 was applied. The results obtained by applying the structural equation analysis are as follows. First, general characteristics were tested and the reliability of the items was tested. The reliability of the items, predictability, accuracy, and validity were analyzed by principal component analysis. Second, the research hypothesis was verified by verifying the fit of measurement variables through participation factor of lifelong education, self - integration, life satisfaction, and voluntary service. Statistical analysis was performed using the SPSS WIN 22.0 and Amos 22.0 programs.

• YAKHAK HOEJI
• /
• v.59 no.3
• /
• pp.92-97
• /
• 2015

KIOM-MA128 is a novel Korean herbal medicine with anti-atopic, anti-inflammatory and anti-asthmatic effects. This article presents the first pharmacokinetic study on KIOM-MA128. The purpose of this study was to characterize a pharmacokinetic characteristic of matrine, a potential marker of KIOM-MA128, in rats using population pharmacokinetic model. 1, 2 and 8 g/kg of KIOM-MA128 were administered to rats orally and plasma concentrations of matrine was determined by HPLC-MS/MS. Non-compartmental analysis (NCA) was performed using Phoenix$^{(R)}$ and pharmacokinetic model was built using NONMEM$^{(R)}$. This model was validated with internal validation which is visual predictive check (VPC) and bootstrap. The NCA result of matrine showed that $C_{max}$ was 294.24, 552.22 and 868.65 ng/ml, $AUC_{inf}$ was 1273.05, 2724.76 and $9743.25ng{\cdot}hr/ml$ and $T_{max}$ was 1, 1.3 and 2.3 hr for the doses of 1, 2, and 8 g/kg, respectively. The rat plasma concentrations were described very well with one-compartment model. Pharmacokinetic model for matrine was successfully developed and evaluated. Finally, our model is helpful to understand pharmacokinetic characteristic of KIOM-MA128.

• Journal of Convergence for Information Technology
• /
• v.10 no.10
• /
• pp.150-160
• /
• 2020

The purpose of this study was to test the effect of socially-perfectionism on depression by mediating ambivalence over emotional expressiveness and experiential avoidance. For this purpose, 201 participants across the country conducted the survey, a measure of MPS, AEQ-K, AAQ-II, CES-D. The descriptive statistics, Pearson correlation, path coefficient were conducted using SPSS 23.0. The indirect effect was examined using bootstrap in PROCESS Macro. The results of the study are as follows. First, all the variables had meaningful positive correlations. Secondly, When socially-perfectionism affects depression, ambivalence over emotional expressiveness, and experiential avoidance were mediated. As a result, the implications and limitations of the study were discussed.

• The Bulletin of The Korean Astronomical Society
• /
• v.39 no.2
• /
• pp.52-52
• /
• 2014

It is widely accepted that the evolution of galaxies is accelerated in dense environments. According to recent studies, however, the evolution by direct interactions between galaxies is known to be most active in a galaxy group rather than in a galaxy cluster. In particular, the central galaxy in a group is closely related to its satellites in the properties such as morphology, color and star formation rate, because those galaxies evolve together in a small-scale environment. Currently, however, it is not yet studied well whether such conformity between bright galaxies and their faint companions remains after a galaxy group falls into a galaxy cluster. Recently, Lee et al. (2014) have found that the colors of bright galaxies show a measurable correlation with the mean colors of faint companions around them in WHL J085910.0+294957, a galaxy cluster at z = 0.3, which may be the vestige of infallen groups in the cluster. As a follow-up study, we study Abell 2744, an ongoing cluster-cluster merger at z = 0.308, using the HST Frontier Fields Survey data. The cluster members are selected based on the distributions of color, size and concentration along magnitude. The correlation in color between bright galaxies and their companions is not found in the full area of Abell 2744. However, when the area is limited to the southeastern part of the Abell 2744 image, the mean color of faint companions shows marginal dependence (> $2{\sigma}$ to Bootstrap uncertainties) on the color of their adjacent bright galaxy. We discuss the implication of these results, focusing on their dependence on local environments.

• Korean Journal of Clinical Pharmacy
• /
• v.26 no.4
• /
• pp.312-317
• /
• 2016

Objective: Midazolam is mainly metabolized by cytochrome P450 (CYP) 3A. Inhibition or induction of CYP3A can affect the pharmacological activity of midazolam. The aims of this study were to develop a population pharmacokinetic (PK) model and evaluate the effect of CYP3A-mediated interactions among ketoconazole, rifampicin, and midazolam. Methods: Three-treatment, three-period, crossover study was conducted in 24 healthy male subjects. Each subject received 1 mg midazolam (control), 1 mg midazolam after pretreatment with 400 mg ketoconazole once daily for 4 days (CYP3A inhibition phase), and 2.5 mg midazolam after pretreatment with 600 mg rifampicin once daily for 10 days (CYP3A induction phase). The population PK analysis was performed using a nonlinear mixed effect model ($NONMEM^{(R)}$ 7.2) based on plasma midazolam concentrations. The PK model was developed, and the first-order conditional estimation with interaction was applied for the model run. A three-compartment model with first-order elimination described the PK. The influence of ketoconazole and rifampicin, CYP3A5 genotype, and demographic characteristics on PK parameters was examined. Goodness-of-fit (GOF) diagnostics and visual predictive checks, as well as bootstrap were used to evaluate the adequacy of the model fit and predictions. Results: Twenty-four subjects contributed to 900 midazolam concentrations. The final parameter estimates (% relative standard error, RSE) were as follows; clearance (CL), 31.8 L/h (6.0%); inter-compartmental clearance (Q) 2, 36.4 L/h (9.7%); Q3, 7.37 L/h (12.0%), volume of distribution (V) 1, 70.7 L (3.6%), V2, 32.9 L (8.8%); and V3, 44.4 L (6.7%). The midazolam CL decreased and increased to 32.5 and 199.9% in the inhibition and induction phases, respectively, compared to that in control phase. Conclusion: A PK model for midazolam co-treatment with ketoconazole and rifampicin was developed using data of healthy volunteers, and the subject's CYP3A status influenced the midazolam PK parameters. Therefore, a population PK model with enzyme-mediated drug interactions may be useful for quantitatively predicting PK alterations.

• Research in Community and Public Health Nursing
• /
• v.29 no.3
• /
• pp.371-381
• /
• 2018

Purpose: The purpose of this study is to identify the mediating effects of self-esteem between social comparison orientation and social network service (SNS) addiction in university students. Methods: Descriptive cross-sectional survey design was employed. The data were statistically analyzed by using the descriptive and inferential statistics. Sobel test and Bootstrap method, and Kappa squared mediation effect size measure were used to identify the mediator's significance. A convenience sample of 195 subjects was recruited from two universities in Korea. Results: The mean age of the subjects was $22.58{\pm}1.81$. The subjects showed relatively high levels of SNS addiction with a mean score of $14.33{\pm}4.80$. The overall model significantly explained 37.0% of variances in the subjects' SNS addiction after controlling gender, age, grade, major, period of SNS using, time spent on SNS per day, and times accessed SNS per day. Of the predictors, time spent on SNS per day, social comparison orientation, and self-esteem were significantly associated with SNS addiction. Self-esteem was the mediator between social comparison orientation and SNS addiction. Conclusion: When developing strategies for preventing SNS addiction, interventions for reducing time spent on SNS per day, not having upward social comparison orientation, and improving the self-esteem should be considered. These findings might provide a theoretical basis for developing effective strategies for preventing SNS addiction in university students.