• Korean Chemical Engineering Research
• /
• v.60 no.2
• /
• pp.202-207
• /
• 2022

The study on electrode degradation of Proton Exchange Membrane Fuel Cell (PEMFC) was mainly studied on the particle growth and active area reduction of Pt on the electrode. The degradation of the electrode catalyst Pt in contact with the membrane affects the deterioration of the polymer membrane, but there are not many studies related to this. In this study, the phenomenon of the deposition of deteriorated Pt inside the polymer membrane during the accelerated electrode catalyst degradation test and its effects were studied. The voltage change (0.6 V ↔ 0.9 V) was repeated up to 30,000 cycles to accelerate the platinum degradation rate. When the voltage change cycle was repeated while oxygen was introduced into the cathode, the amount of Pt deposited inside the film was larger than when nitrogen was introduced. As the number of voltage change cycles increased, the amount of Pt deposited inside the membrane increased, and Pt dissolved in the cathode moved toward the anode, showing a uniform distribution throughout the membrane at 20,000 cycles. In the process of the accelerated electrode catalyst degradation test, the hydrogen crossover current density of the membrane did not change, and it was confirmed that the deposited Pt did not affect the durability of the membrane.

• Korea Trade Review
• /
• v.43 no.1
• /
• pp.109-130
• /
• 2018

The cumulative standard is one of the criteria determining the origin of imported goods and is a provision that allows non-origin materials to be treated as origin goods when satisfying certain conditions. Regarding the Korea-Canada FTA, new cumulative standards were applied concerning cross accumulation of automobile products. It would benefit U.S. originating intermediate goods of HS code chapter 84, 85, 87, and 94 obtained into HS code heading from 8701 into 8706. We examine the effectiveness of crossover cumulative standards through the change in the import values of 84, 85, 87, 94, which are target items for cross cumulation. Only items designated for automobile parts were selected and analyzed. From the estimation results, significant changes appeared in 20 of the 35 items. It was found that the import amount increased significantly as of January 2015 or the rate of change in trend increases more than before. In addition, the estimation results show that Korean auto companies utilizing the cumulative standards through increased imports of auto parts form the U.S.

• Journal of Intelligence and Information Systems
• /
• v.17 no.4
• /
• pp.241-254
• /
• 2011

Financial time-series forecasting is one of the most important issues because it is essential for the risk management of financial institutions. Therefore, researchers have tried to forecast financial time-series using various data mining techniques such as regression, artificial neural networks, decision trees, k-nearest neighbor etc. Recently, support vector machines (SVMs) are popularly applied to this research area because they have advantages that they don't require huge training data and have low possibility of overfitting. However, a user must determine several design factors by heuristics in order to use SVM. For example, the selection of appropriate kernel function and its parameters and proper feature subset selection are major design factors of SVM. Other than these factors, the proper selection of instance subset may also improve the forecasting performance of SVM by eliminating irrelevant and distorting training instances. Nonetheless, there have been few studies that have applied instance selection to SVM, especially in the domain of stock market prediction. Instance selection tries to choose proper instance subsets from original training data. It may be considered as a method of knowledge refinement and it maintains the instance-base. This study proposes the novel instance selection algorithm for SVMs. The proposed technique in this study uses genetic algorithm (GA) to optimize instance selection process with parameter optimization simultaneously. We call the model as ISVM (SVM with Instance selection) in this study. Experiments on stock market data are implemented using ISVM. In this study, the GA searches for optimal or near-optimal values of kernel parameters and relevant instances for SVMs. This study needs two sets of parameters in chromosomes in GA setting : The codes for kernel parameters and for instance selection. For the controlling parameters of the GA search, the population size is set at 50 organisms and the value of the crossover rate is set at 0.7 while the mutation rate is 0.1. As the stopping condition, 50 generations are permitted. The application data used in this study consists of technical indicators and the direction of change in the daily Korea stock price index (KOSPI). The total number of samples is 2218 trading days. We separate the whole data into three subsets as training, test, hold-out data set. The number of data in each subset is 1056, 581, 581 respectively. This study compares ISVM to several comparative models including logistic regression (logit), backpropagation neural networks (ANN), nearest neighbor (1-NN), conventional SVM (SVM) and SVM with the optimized parameters (PSVM). In especial, PSVM uses optimized kernel parameters by the genetic algorithm. The experimental results show that ISVM outperforms 1-NN by 15.32%, ANN by 6.89%, Logit and SVM by 5.34%, and PSVM by 4.82% for the holdout data. For ISVM, only 556 data from 1056 original training data are used to produce the result. In addition, the two-sample test for proportions is used to examine whether ISVM significantly outperforms other comparative models. The results indicate that ISVM outperforms ANN and 1-NN at the 1% statistical significance level. In addition, ISVM performs better than Logit, SVM and PSVM at the 5% statistical significance level.

• Korean Journal of Psychosomatic Medicine
• /
• v.27 no.2
• /
• pp.147-154
• /
• 2019

Objectives : Cognitive dysfunction, including inattention, is often observed in patients with depression. Inattentive symptoms in patients with depression is similar to those among attention deficit/hyperactivity disorder (ADHD) patients. It is important to diagnose the two diseases accurately, because the treatment varies depending on the cause of inattention. This study aimed to investigate the coexistence rate of ADHD and the correlation between ADHD symptoms and depression in patients with depression. Methods : Participants in this study were 158 outpatients presenting with depression, who visited the psychiatric department from March 2015 to July 2018. Participants divided into a depression and a non-depression group according to the Korean version of the Center for Epidemiological Studies-Depression Scale (CES-D) score and were administered the following : a sociodemographic variables form (age, sex, academic background, occupation), the self-reporting test for adult ADHD (Adult Attention Deficit/Hyperactivity Disorder self-report scale-V 1.1; ASRS V1.1), and the Korean version of the Connors adult ADHD rating scale (K-CAARS). Descriptive statistical analysis, crossover analysis, t-tests, and Pearson's correlation coefficient were conducted on the data. Results : The coexistence rate of adult ADHD symptom was as high as 36.7% in patients with depression (p<0.001). In K-CAARS, the depression group (Inattention=1.80, Hyperactivity=1.92, Impulsivity=1.56, Self-concept=2.06) showed higher average scores on ADHD symptoms than the non-depressive group (Inattention=1.28, Hyperactivity=1.25, Impulsivity=1.09, Self-concept=1.42, p<0.001). Conclusions : This study confirmed that ADHD symptoms coexist in the depression group. When evaluating the symptoms of patients who complain of depression, it is suggested that they should be accurately diagnosed and appropriately treated with interest to the coexistence of ADHD symptoms and the possibility for ADHD diagnosis.