• Journal of Intelligence and Information Systems
• /
• v.20 no.4
• /
• pp.121-139
• /
• 2014

Predicting corporate failure has been an important topic in accounting and finance. The costs associated with bankruptcy are high, so the accuracy of bankruptcy prediction is greatly important for financial institutions. Lots of researchers have dealt with the topic associated with bankruptcy prediction in the past three decades. The current research attempts to use ensemble models for improving the performance of bankruptcy prediction. Ensemble classification is to combine individually trained classifiers in order to gain more accurate prediction than individual models. Ensemble techniques are shown to be very useful for improving the generalization ability of the classifier. Bagging is the most commonly used methods for constructing ensemble classifiers. In bagging, the different training data subsets are randomly drawn with replacement from the original training dataset. Base classifiers are trained on the different bootstrap samples. Instance selection is to select critical instances while deleting and removing irrelevant and harmful instances from the original set. Instance selection and bagging are quite well known in data mining. However, few studies have dealt with the integration of instance selection and bagging. This study proposes an improved bagging ensemble based on instance selection using genetic algorithms (GA) for improving the performance of SVM. GA is an efficient optimization procedure based on the theory of natural selection and evolution. GA uses the idea of survival of the fittest by progressively accepting better solutions to the problems. GA searches by maintaining a population of solutions from which better solutions are created rather than making incremental changes to a single solution to the problem. The initial solution population is generated randomly and evolves into the next generation by genetic operators such as selection, crossover and mutation. The solutions coded by strings are evaluated by the fitness function. The proposed model consists of two phases: GA based Instance Selection and Instance based Bagging. In the first phase, GA is used to select optimal instance subset that is used as input data of bagging model. In this study, the chromosome is encoded as a form of binary string for the instance subset. In this phase, the population size was set to 100 while maximum number of generations was set to 150. We set the crossover rate and mutation rate to 0.7 and 0.1 respectively. We used the prediction accuracy of model as the fitness function of GA. SVM model is trained on training data set using the selected instance subset. The prediction accuracy of SVM model over test data set is used as fitness value in order to avoid overfitting. In the second phase, we used the optimal instance subset selected in the first phase as input data of bagging model. We used SVM model as base classifier for bagging ensemble. The majority voting scheme was used as a combining method in this study. This study applies the proposed model to the bankruptcy prediction problem using a real data set from Korean companies. The research data used in this study contains 1832 externally non-audited firms which filed for bankruptcy (916 cases) and non-bankruptcy (916 cases). Financial ratios categorized as stability, profitability, growth, activity and cash flow were investigated through literature review and basic statistical methods and we selected 8 financial ratios as the final input variables. We separated the whole data into three subsets as training, test and validation data set. In this study, we compared the proposed model with several comparative models including the simple individual SVM model, the simple bagging model and the instance selection based SVM model. The McNemar tests were used to examine whether the proposed model significantly outperforms the other models. The experimental results show that the proposed model outperforms the other models.

• Journal of Pharmaceutical Investigation
• /
• v.39 no.1
• /
• pp.65-71
• /
• 2009

The aim of the present study was to evaluate the bioequivalence of two domperidone maleate tablets, Motilium-$M^{(R)}$ Tablet (Janssen Korea Ltd., reference product) and $Toriem^{(R)}$ Tablet (Daewon Pharm. Co., Ltd., test product). Domperidone was extracted by liquid-liquid extraction using tert-butyl methyl ether and separated in less than 3 min on $C_{18}$ reverse-phase column using an isocratic elution. A tandem mass spectrometer, as detector, was used for quantitative analysis in positive mode by a multiple reaction monitoring mode to monitor the m/z $426.1{\rightarrow}119.1$ and the m/z $837.4{\rightarrow}158.2$ transitions for domperidone and the internal standard (roxithromycin), respectively. Calibration curves, from $0.05{\sim}50$ ng/mL of domperidone, showed correlation coefficients (r) higher than 0.9941. Intra day and inter day precision (C.V. %) for quality control were ranged from 10.04 to 16.09% and from 10.87 to 18.69%, respectively. The lower limit of quantification (LLOQ) of domperidone was 0.05 ng/mL. The method described is precise and sensitive and has been successfully applied to the study of bioequivalence of domperidone in 24 healthy Korean volunteers. Twenty-four healthy male Korean volunteers received a single dose of each medicine ($2{\times}12.72\;mg$ domperidone maleate) in a $2{\times}2$ crossover study. There was a one-week washout period between the doses. Plasma concentrations of domperidone were monitored for over a period of 24 hr after the administration. $AUC_{0-t}$ (the area under the plasma concentration-time curve) was calculated by the linear trapezoidal rule. $C_{max}$ (maximum plasma drug concentration) and $T_{max}$ (time to reach $C_{max}$) were compiled from the plasma concentration-time data. The 90% confidence intervals for the log transformed data were within acceptable range of log 0.8 to log 1.25 (e.g., $log\;0.92{\sim}log\;1.05$ for $AUC_{0-t}$, $log\;0.81{\sim}log\;1.05$ for $C_{max}$). The major parameters, $AUC_{0-t}$ and $C_{max}$ met the criteria of KFDA for bioequivalence indicating that $Toriem^{(R)}$ tablet is bioequivalent to Motilium-$M^{(R)}$ tablet.

• The Journal of Korean Medicine
• /
• v.43 no.2
• /
• pp.61-74
• /
• 2022

Objectives: This study aimed to explore the short-term effects of bilateral masticatory training using an intraoral device on memory and concentration, which is an advanced form of Gochi, compared to the unilateral form with gum. Methods: Thirty young healthy participants (age, 16-30 years) were screened and randomly assigned to one of two sequences in a crossover design. The participants assigned to sequence A (n=15) performed bilateral mastication using an intraoral device with a total of 300 taps, followed by unilateral mastication using gum with the same number of repetitions and frequency, separated by a 7-day washout period. A reverse order was used for sequence B. The primary and secondary outcomes were the digit span test result and the symbol digit modality test and the word list recall results, respectively, which were conducted before and after each intervention. Results: Symbol digit modality test scores increased by 12.03±8.33 with bilateral mastication, which was significantly higher than that obtained with chewing gum (5.17 points;95% confidence interval: 0.99, 9.34; p<0.05). Changes in the digit span test and word list recall scores were not significantly different between the two groups. In the digit span test forward, symbol digit modality test, and word list recall test, bilateral mastication was not inferior to unilateral mastication in improving memory and concentration. Conclusions: Bilateral masticatory exercises using an intraoral device are not inferior to unilateral mastication with gum for improving memory in healthy young individuals. Further research is needed to determine the efficacy of bilateral masticatory training on cognitive function.