• Journal of Biomedical Engineering Research
• /
• v.31 no.3
• /
• pp.240-244
• /
• 2010

The purpose of this study is to compare finger tapping (FT) movement of patients with Parkinson's disease (PD) with normal subjects. A gyrosensor system was used for the measurement of FT movement, because it provides angular velocity free from the gravitational artifact and it can be used during clinical FT test listed in unified PD rating scale (UPDRS). Forty PD patients (age: 65.7 ${\pm}$ 11.1 yrs, H&Y stage:2.3 ${\pm}$ 0.5), 14 age-matched elderly subjects (65${\pm}$3.9 yrs) and 17 healthy young subjects (24${\pm}$2.1yrs) participated in this study. Angular velocity of finger tapping movement was measured in both right and left index finger. As quantitative measures, root-mean-squared (RMS) angular velocity, RMS angle, peak power and total power were used. ANOVA showed that all measures were significantly different among three groups (p<0.001) in all quantitative measures. Post-hoc test revealed that all quantitative measures except peak power in patients with PD were significantly smaller than in both healthy elderly and young subjects (p<0.01). This suggests that the measures developed in this study can distinguish patients with PD from normal subjects.

• Korean Journal of Biological Psychiatry
• /
• v.19 no.1
• /
• pp.45-52
• /
• 2012

Objectives : This study was designed to investigate the usability of IVA + Plus (Continuous Performance Test) and Neuro-Guide [Quantitative electroencephalography (EEG) normative database] as an auxiliary diagnostic tools for attention-deficit hyperactivity disorder (ADHD). Methods : The scores of IVA + Plus and resting EEG were obtained from 34 elementary school-aged children. Also, the Korean ADHD Rating Scale (K-ARS) and the Diagnostic Interview Schedule for Children version IV (DISC-IV) was done for the parent of them. From the result of the DISC-IV, we divided them into three groups, ADHD Not Otherwise Specified (NOS), and Normal Control (NC). Using NeuroGuide, the z-scores of relative power for delta (1-4 Hz), theta (4-8 Hz), alpha (8-12 Hz), and beta (12-25 Hz) were calculated. Then the correlation and variance analysis were done to investigate the differences between three groups. Results : The scores of IVA + Plus were negatively correlated with the K-ARS. IVA + Plus have successfully discriminated the ADHD from NC and NOS. The z-scores of relative power of delta and theta were positively correlated with the K-ARS. The z-scores of relative power of alpha and beta were negatively correlated with the K-ARS. Conclusions : The IVA + Plus and NeuroGuide QEEG test are expected to be used as the valuable tools for diagnosing ADHD accurately.

• Communications for Statistical Applications and Methods
• /
• v.18 no.6
• /
• pp.859-869
• /
• 2011

Interest has increased in academic research regarding key factors that drive box-office success as well as the ability to predict the box-office success of a movie from a commercial perspective. This study analyzed the relationship between key success factors of a movie and box office records based on movies released in 2010 in Korea. At the pre-production investment decision-making stage, the movie genre, motion picture rating, director power, and actor power were statistically significant. At the stage of distribution decision-making process after movie production, among other factors, the influence of star actors, number of screens, power of distributors, and social media turned out to be statistically significant. We verified movie success factors through the application of a Multinomial Logit Model that used the concept of choice probabilities. The Multinomial Logit Model resulted in a higher level of accuracy in predicting box-office success compared to the Artificial Neural Network and Discriminant Analysis.

• The Transactions of the Korean Institute of Power Electronics
• /
• v.15 no.6
• /
• pp.451-459
• /
• 2010

This paper describes the performance comparison results for a hybrid back-to-back converter, which is composed of a 3-level 24-pulse converter and a 3-level PWM converter, in order to interconnect a large scale wind farm with the power grid. Also it describes the performance comparison results when the 24-pulse converter operates in only firing-angle control, and both firing-angle and the zero-voltage control. For the purpose of systematic performance comparison, computer simulations with PSCAD/EMTDC software were carried out, and based on simulation results a scaled hardware model with 2 kVA rating was built and tested.

• The Transactions of the Korean Institute of Power Electronics
• /
• v.7 no.1
• /
• pp.30-40
• /
• 2002

This paper studies the electronic ballast development for 250w MH lamps. We have improved the input power factor using a PFC IC. To provide the rating voltage required In the lamps, we have used the buck type dc-dc converter By this method, the stress of switching devices in inverter can be reduced. The inverter is the Full-Bridge type. To eliminate the acoustic resonance phenomena of MH lamps, we have added the high frequency sinewave voltage to the low frequency square-wave voltage to the lamp. We hove developed the igniter circuit using the L, C devices. We could control dimming of the lamp by varying the output voltage of the buck converter. The time of illuminating lamps and luminous intensity could be adjusted by season and time band. The buck converter output voltage can be controlled and the no load and over current situation were Protected by the development of the microprocessor Program.

• Journal of Intelligence and Information Systems
• /
• v.26 no.2
• /
• pp.105-129
• /
• 2020

This study uses corporate data from 2012 to 2018 when K-IFRS was applied in earnest to predict default risks. The data used in the analysis totaled 10,545 rows, consisting of 160 columns including 38 in the statement of financial position, 26 in the statement of comprehensive income, 11 in the statement of cash flows, and 76 in the index of financial ratios. Unlike most previous prior studies used the default event as the basis for learning about default risk, this study calculated default risk using the market capitalization and stock price volatility of each company based on the Merton model. Through this, it was able to solve the problem of data imbalance due to the scarcity of default events, which had been pointed out as the limitation of the existing methodology, and the problem of reflecting the difference in default risk that exists within ordinary companies. Because learning was conducted only by using corporate information available to unlisted companies, default risks of unlisted companies without stock price information can be appropriately derived. Through this, it can provide stable default risk assessment services to unlisted companies that are difficult to determine proper default risk with traditional credit rating models such as small and medium-sized companies and startups. Although there has been an active study of predicting corporate default risks using machine learning recently, model bias issues exist because most studies are making predictions based on a single model. Stable and reliable valuation methodology is required for the calculation of default risk, given that the entity's default risk information is very widely utilized in the market and the sensitivity to the difference in default risk is high. Also, Strict standards are also required for methods of calculation. The credit rating method stipulated by the Financial Services Commission in the Financial Investment Regulations calls for the preparation of evaluation methods, including verification of the adequacy of evaluation methods, in consideration of past statistical data and experiences on credit ratings and changes in future market conditions. This study allowed the reduction of individual models' bias by utilizing stacking ensemble techniques that synthesize various machine learning models. This allows us to capture complex nonlinear relationships between default risk and various corporate information and maximize the advantages of machine learning-based default risk prediction models that take less time to calculate. To calculate forecasts by sub model to be used as input data for the Stacking Ensemble model, training data were divided into seven pieces, and sub-models were trained in a divided set to produce forecasts. To compare the predictive power of the Stacking Ensemble model, Random Forest, MLP, and CNN models were trained with full training data, then the predictive power of each model was verified on the test set. The analysis showed that the Stacking Ensemble model exceeded the predictive power of the Random Forest model, which had the best performance on a single model. Next, to check for statistically significant differences between the Stacking Ensemble model and the forecasts for each individual model, the Pair between the Stacking Ensemble model and each individual model was constructed. Because the results of the Shapiro-wilk normality test also showed that all Pair did not follow normality, Using the nonparametric method wilcoxon rank sum test, we checked whether the two model forecasts that make up the Pair showed statistically significant differences. The analysis showed that the forecasts of the Staging Ensemble model showed statistically significant differences from those of the MLP model and CNN model. In addition, this study can provide a methodology that allows existing credit rating agencies to apply machine learning-based bankruptcy risk prediction methodologies, given that traditional credit rating models can also be reflected as sub-models to calculate the final default probability. Also, the Stacking Ensemble techniques proposed in this study can help design to meet the requirements of the Financial Investment Business Regulations through the combination of various sub-models. We hope that this research will be used as a resource to increase practical use by overcoming and improving the limitations of existing machine learning-based models.

• The Transactions of the Korean Institute of Power Electronics
• /
• v.11 no.5
• /
• pp.463-470
• /
• 2006

This paper deals with a new 3-phase power quality disturbance generator. The proposed generator can provide phase jump as well as voltage sag, swell, outage, unbalance, and over and under voltage. The operating principle of the generator is described in each mode of disturbance. The magnitude of the phase jump is analysed and it is found that the magnitude is the function of the turn-ratios of the transformers consisting the generator. The scheme has simple structure compared with the conventional one, and the major components of the proposed scheme are SCR thyristor and transformer, which guarantees high reliability and cost-effective implementation of the generator. Furthermore, high efficiency can be obtained because there is no PWM switching of the semiconductor devices, and it is easy to control the system. Simulations are carried out to confirm the operation in each disturbance mode, and experiments has been done with 5kVA power rating. The usefulness of the proposed scheme is verified through simulation and experimental results. It is expected that the scheme can be applied to the performance test of the custom power devices such as UPS, DVR, DSTATCOM, and SSTS with cost-effective system.

• Journal of Distribution Science
• /
• v.12 no.11
• /
• pp.77-83
• /
• 2014

Purpose - The National Agricultural Cooperative Federation of Korea and National Fisheries Cooperative Federation of Korea have prosecuted both financial and retail businesses. As cooperatives are public institutions and receive government support, their sound management is required by the Financial Supervisory Service in Korea. This is mainly managed by CAEL, which is changed by CAMEL. However, NFFC's business section, managing the finance and retail businesses, is unified and evaluated; the CAEL model has an insufficient classification to evaluate the retail industry. First, there is discrimination power as regards CAEL. Although the retail business sector union can receive a higher rating on a CAEL model, defaults have often been reported. Therefore, a default prediction model is needed to support a CAEL model. As we have the default prediction model using a subdivision of indexes and statistical methods, it can be useful to have a prevention function through the estimation of the retail sector's default probability. Second, separating the difference between the finance and retail business sectors is necessary. Their businesses have different characteristics. Based on various management indexes that have been systematically managed by the National Fisheries Cooperative Federation of Korea, our model predicts retail default, and is better than the CAEL model in its failure prediction because it has various discriminative financial ratios reflecting the retail industry situation. Research design, data, and methodology - The model to predict retail default was presented using logistic analysis. To develop the predictive model, we use the retail financial statements of the NFCF. We consider 93 unions each year from 2006 to 2012 to select confident management indexes. We also adapted the statistical power analysis that is a t-test, logit analysis, AR (accuracy ratio), and AUROC (Area Under Receiver Operating Characteristic) analysis. Finally, through the multivariate logistic model, we show that it is excellent in its discrimination power and higher in its hit ratio for default prediction. We also evaluate its usefulness. Results - The statistical power analysis using the AR (AUROC) method on the short term model shows that the logistic model has excellent discrimination power, with 84.6%. Further, it is higher in its hit ratio for failure (prediction) of total model, at 94%, indicating that it is temporally stable and useful for evaluating the management status of retail institutions. Conclusions - This model is useful for evaluating the management status of retail union institutions. First, subdividing CAEL evaluation is required. The existing CAEL evaluation is underdeveloped, and discrimination power falls. Second, efforts to develop a varied and rational management index are continuously required. An index reflecting retail industry characteristics needs to be developed. However, extending this study will need the following. First, it will require a complementary default model reflecting size differences. Second, in the case of small and medium retail, it will need non-financial information. Therefore, it will be a hybrid default model reflecting financial and non-financial information.

• The Journal of Korean Institute of Electromagnetic Engineering and Science
• /
• v.28 no.5
• /
• pp.400-409
• /
• 2017

We have studied a combiner that can withstand high power while minimizing insertion loss in high frequency band. In particularly, because the output power that can be output per unit elements is much lower in the Ku band and above than in the low frequency band, it is necessary to combine many semiconductor elements in order to make a high power SSPA. A planar combiner such as a microstrip, as the number of elements to be combined increases, the insertion loss increases proportionally, resulting in a reduction in the overall system efficiency and an increase heating value also. The planar combiner also have some problems due to the low power handling rate. To improve these problems, we proposed a Cavity Radial Combiner. A Ku band 16-way Cavity Radial Combiner was fabricated and measured. As a result, it was tested 14dB return loss and over 94.5 % output combining efficiency in design band.

• Journal of the Korea Academia-Industrial cooperation Society
• /
• v.19 no.6
• /
• pp.80-87
• /
• 2018

In recent years, due to the spread of various renewable energy power sources and the pursuit of high efficiency and low-power consumption, not only trends in the electric power industry but also the consumption, control methods, and characteristics are diversified. However, in this diversified electric power industry, the fuse (which is the core part responsible for safety) has not developed significantly in classical operation mode, and thus, fires continue to occur. In this paper, the effects of low melting-point metal plating and high melting-point metal plating on operating characteristics and IT curve movement of the fuse are investigated in a cartridge fuse, which is a classic fuse manufacturing method. The effects of plating on the thickness of the fuse are investigated, and various operating characteristics of the fuse are implemented. In addition, it is suggested that the plating of the low melting-point metal moves the rated current line of the fuse to a low rating, and moves operating characteristics to characteristics of delay operation. It is possible to design various operating characteristics using this characteristic.