• Journal of Korea Water Resources Association
• /
• v.45 no.8
• /
• pp.815-826
• /
• 2012

The underestimating trend using existing ordinary regression (OR) based trend analysis has been a well-known problem. The existing OR method based on least squares approximate the conditional mean of the response variable given certain values of the time t, and the usual assumption of the OR method is normality, that is the distribution of data are not dissimilar form a normal distribution. In this regard, this study proposed a quantile regression that aims at estimating either the conditional median or other quantiles of the response variable. This study assess trend in annual daily maximum rainfall series over 64 weather stations through both in OR and QR approach. The QR method indicates that 47 stations out of 67 weather stations are a strong upward trend at 5% significance level while OR method identifies a significant trend only at 13 stations. This is mainly because the OR method is estimating the condition mean of the response variable. Unlike the OR method, the QR method allows us flexibly to detect the trends since the OR is designed to estimate conditional quantiles of the response variable. The proposed QR method can be effectively applied to estimate hydrologic trend for either non-normal data or skewed data.

• The Journal of the Korea Contents Association
• /
• v.18 no.8
• /
• pp.525-535
• /
• 2018

If the frequency of a particular class is excessively higher than the frequency of other classes in the classification problem, data imbalance problems occur, which make machine learning distorted. Corporate bankruptcy prediction often suffers from data imbalance problems since the ratio of insolvent companies is generally very low, whereas the ratio of solvent companies is very high. To mitigate these problems, it is required to apply a proper sampling technique. Until now, oversampling techniques which adjust the class distribution of a data set by sampling minor class with replacement have popularly been used. However, they are a risk of overfitting. Under this background, this study proposes ROSE(Random Over Sampling Examples) technique which is proposed by Menardi and Torelli in 2014 for the effective corporate bankruptcy prediction. The ROSE technique creates new learning samples by synthesizing the samples for learning, so it leads to better prediction accuracy of the classifiers while avoiding the risk of overfitting. Specifically, our study proposes to combine the ROSE method with SVM(support vector machine), which is known as the best binary classifier. We applied the proposed method to a real-world bankruptcy prediction case of a Korean major bank, and compared its performance with other sampling techniques. Experimental results showed that ROSE contributed to the improvement of the prediction accuracy of SVM in bankruptcy prediction compared to other techniques, with statistical significance. These results shed a light on the fact that ROSE can be a good alternative for resolving data imbalance problems of the prediction problems in social science area other than bankruptcy prediction.

• Korean Journal of Ichthyology
• /
• v.20 no.4
• /
• pp.248-254
• /
• 2008

Olive flounder (Paralichthys olivaceus) is one of the most popular farmed fish in Korea. Genetic variability of the fish was investigated by means of microsatellite DNA markers. All of the 8 microsatellite loci were analyzed in this study. For the confirmation of genetic variation during a shift in generation, microsatellite variability was compared within the same hatchery strains but produced in different spawning years. When genetic variability of farmed flounders produced in 2006 and 2007 was compared with that of 2003, a marked reduction of genetic variability was observed in the 2006 and 2007 populations. Mean number of alleles per locus and expected mean heterozygosity decreased from 9.75 and 0.796 (in 2003 population) to 7.78 and 0.785 (in 2006 population), respectively. Moreover, we have observed the distortion of allele frequency. These results show that reduced genetic variability of farmed olive flounder in processed generation has lower numbers of alleles and genetic variability than these of wild fish. Our results suggest that to have a sustainable aquaculture of this species, there is need for scientific broodstock management based on genetic variation and more intensive breeding practices to improve genetic diversity and to avoid detrimental inbreeding effects.

• Journal of the Korean Society of Food Science and Nutrition
• /
• v.39 no.9
• /
• pp.1295-1304
• /
• 2010

The purpose of this study was to investigate the BMI, dietary behaviors, body satisfaction and factors affecting the weight control interest according to gender of middle school students (195 boys and 251 girls) in Wonju area. The average height and weight of the boys were $164.8{\pm}8.3\;cm$ and $55.5{\pm}12.3\;kg$ respectively. Those of the girls were $158.8{\pm}5.0\;cm$ and $48.7{\pm}7.4\;kg$ respectively. The average body mass index (BMI) of the boys and girls was 20.3 and 19.3 respectively. In both boys and girls, 69.7% of them had regular meals and the main reason for skipping meals was insufficient time to eat due to oversleeping (33.6%). Most of the subjects consumed snacks more than once a day (95.5%). The dietary intake attitude score of the girls ($35.08{\pm}5.91$) was higher than that of the boys ($33.81{\pm}5.45$) (p<0.01). The eating disorders score of the girls ($12.92{\pm}6.22$) was higher than that of the boys ($10.70{\pm}9.82$) (p<0.01). Also, 87.2% of the subjects showed normal behavior and 12.8% of the subjects had eating disorders, but there was no significant difference according to gender. The body satisfaction score of the boys ($30.16{\pm}5.08$) was higher than that of the girls ($28.00{\pm}5.52$) (p<0.001). In general, body satisfaction score correlated positively with dietary intake attitude score, but correlated negatively with eating disorders score (p<0.05). Multiple regression analysis revealed that body satisfaction score was the most significant variable which affected the weight control interest. Therefore, development of the nutrition education program for adolescents will be effective not only for the improvement of dietary behaviors but also for the positive change in the misleading perception about the ideal body shape.