• Journal of The Korean Association of Information Education
• /
• v.22 no.3
• /
• pp.367-374
• /
• 2018

In order to cultivate the human resources needed in the 4th industrial revolution era, it is necessary to select the gifted students and educate them systematically. Although excellent gifted students are important in a specific field, more convergent talents in the fields of mathematics, science, and information are required. The purpose of this study is to investigate how evaluation factors reflecting the characteristics of information gifted students affect the selection of science gifted students of a university gifted education center. In the characteristics of information gifted students, the cognitive factors such as Rule creation ability, Reasoning ability, Efficiency ability, Generalization ability, Structuring ability and Abstraction ability were highly correlated in selecting the science gifted students. Correlations in the applicants group of students for science gifted education center are higher than those in the first passers group and higher than those in the final successful candidates group. This means that the factors that shows the characteristics of the information gifted have a great influence on the selection of the science gifted.

• The Journal of Korean Institute of Communications and Information Sciences
• /
• v.34 no.2A
• /
• pp.147-154
• /
• 2009

Antenna grouping algorithm is hybrid of beamforming and spatial multiplexing. In antenna grouping system, we partition $N_t$ transmit antennas into $N_r$ groups and use beamforming in a group, spatial multiplexing between groups. We can transmit $N_r$ data streams in the $N_t{\times}N_r$ antenna grouping system. With antenna grouping, we can achieve diversity gain through beamforming, and high spectral efficiency through spatial multiplexing. But if channel is ill-conditioned or there are some correlations between antennas, the performance of antenna grouping is seriously degraded and in that case, beamforming is the best transmit strategy. By selecting the antenna grouping mode when channel is well-conditioned and by selecting the beamforming mode when channel is ill-conditioned, we can prevent serious fluctuation of BER performance caused by varying channel condition and achieve the best BER performance. In this paper, we investigate mode selection algorithm which can select antenna grouping mode or beamforming mode. we also propose a simple mode selection criterion.

• Journal of Climate Change Research
• /
• v.9 no.1
• /
• pp.47-58
• /
• 2018

In this study, we evaluated the uncertainty in the process of selecting GCM and downscaling method for assessing the impact of climate change, and influence of user-centered climate change information on reproducibility of Chungju Dam inflow was analyzed. First, we selected the top 16 GCMs through the evaluation of spatio-temporal reproducibility of 29 raw GCMs using 30-year average of 10-day precipitation without any bias-correction. The climate extreme indices including annual total precipitation and annual maximum 1-day precipitation were selected as the relevant indices to the dam inflow. The Simple Quantile Mapping (SQM) downscaling method was selected through the evaluation of reproducibility of selected indices and spatial correlation among weather stations. SWAT simulation results for the past 30 years period by considering limitations in weather input showed the satisfactory results with monthly model efficiency of 0.92. The error in average dam inflow according to selection of GCMs and downscaling method showed the bests result when 16 GCMs selected raw GCM analysi were used. It was found that selection of downscaling method rather than selection of GCM is more is important in overall uncertainties. The average inflow for the future period increased in all RCP scenarios as time goes on from near-future to far-future periods. Also, it was predicted that the inflow volume will be higher in the RCP 8.5 scenario than in the RCP 4.5 scenario in all future periods. Maximum daily inflow, which is important for flood control, showed a high changing rate more than twice as much as the average inflow amount. It is also important to understand the seasonal fluctuation of the inflow for the dam management purpose. Both average inflow and maximum inflow showed a tendency to increase mainly in July and August during near-future period while average and maximum inflows increased through the whole period of months in both mid-future and far-future periods.

• The Korean Journal of Applied Statistics
• /
• v.31 no.6
• /
• pp.721-732
• /
• 2018

Latent class analysis (LCA) is an important tool to explore unseen latent groups in multivariate categorical data. In practice, it is important to select a suitable set of variables because the inclusion of too many variables in the model makes the model complicated and reduces the accuracy of the parameter estimates. Dean and Raftery (Annals of the Institute of Statistical Mathematics, 62, 11-35, 2010) proposed a headlong search algorithm based on Bayesian information criteria values to choose meaningful variables for LCA. In this paper, we propose a new variable selection procedure for LCA by utilizing posterior probabilities obtained from each fitted model. We propose a new statistic to measure the adequacy of LCA and develop a variable selection procedure. The effectiveness of the proposed method is also presented through some numerical studies.

• Korea Journal of Hospital Management
• /
• v.23 no.4
• /
• pp.40-52
• /
• 2018

The purpose of this study is to identify medical consumers' hospital selection factors in response to the rapidly changing environment of medical industry. For that purpose this study classified consumers' hospital selection factors into three categories such that human factors including expertise, reliability, empathy; system factor including, convenience, differentiation, efficiency; and facility factor including tangibility, accessibility, and location, based on the previous studies and the results of a preliminary survey of the patients of a small private hospital. The nine factors were further divided into 23 more specific attributes. Then, an online survey was conducted to measure the perceptions of the 23 attributes by the medical consumers over the age of 20. The analysis of the survey data using Kano model and Timko model indicated that 14 of the 23 attributes were classified as attractive factors, eight attributes were or classified as, one-dimensional factors, and one attribute, doctors' educational background, was classified as indifference factor. Of the 14 attractive factors, "unique and differentiated services related to medical treatment" and "distance from home to hospital" had the highest customer satisfaction coefficients. Of the eight one-dimensional factors, "kind treatment," "providing adequate explanations," "accuracy of diagnosis," and "cleanness of facilities" had the highest customer satisfaction coefficients as well as the highest dissatisfaction coefficients. The findings indicate that these six attributes are the most basic and most impactful attributes that hospitals must manage strategically to improve their service quality and attract more medical consumers to their hospitals.

• Journal of Korean Society on Water Environment
• /
• v.35 no.5
• /
• pp.425-431
• /
• 2019

Recently, people have been attracting attention to the good quality of water resources as well as water welfare. to improve the quality of life. This study is a papers on the prediction of benthic macroinvertebrate index (BMI), which is a aquatic ecological health, using the machine learning based CFS (Correlation-based Feature Selection) method and the random forest model to compare the measured and predicted values of the BMI. The data collected from the Han River's branch for 10 years are extracted and utilized in 1312 data. Through the utilized data, Pearson correlation analysis showed a lack of correlation between single factor and BMI. The CFS method for multiple regression analysis was introduced. This study calculated 10 factors(water temperature, DO, electrical conductivity, turbidity, BOD, $NH_3-N$, T-N, $PO_4-P$, T-P, Average flow rate) that are considered to be related to the BMI. The random forest model was used based on the ten factors. In order to prove the validity of the model, $R^2$, %Difference, NSE (Nash-Sutcliffe Efficiency) and RMSE (Root Mean Square Error) were used. Each factor was 0.9438, -0.997, and 0,992, and accuracy rate was 71.6% level. As a result, These results can suggest the future direction of water resource management and Pre-review function for water ecological prediction.

• Journal of Korean Society on Water Environment
• /
• v.35 no.5
• /
• pp.432-438
• /
• 2019

The purpose of this study is to predict Trophic Diatom Index (TDI) in tributaries of the Han River watershed using the random forest algorithm. The one year (2017) and supplied aquatic ecology health data were used. The data includes water quality(BOD, T-N, $NH_3-N$, T-P, $PO_4-P$, water temperature, DO, pH, conductivity, turbidity), hydraulic factors(water width, average water depth, average velocity of water), and TDI score. Seven factors including water temperature, BOD, T-N, $NH_3-N$, T-P, $PO_4-P$, and average water depth are selected by the Correlation Feature Selection. A TDI prediction model was generated by random forest using the seven factors. To evaluate this model, 2017 data set was used first. As a result of the evaluation, $R^2$, % Difference, NSE(Nash-Sutcliffe Efficiency), RMSE(Root Mean Square Error) and accuracy rate show that this model is compatible with predicting TDI. To be more concrete, $R^2$ is 0.93, % Difference is -0.37, NSE is 0.89, RMSE is 8.22 and accuracy rate is 70.4%. Also, additional evaluation using data set more than 17 times the measured point was performed. The results were similar when the 2017 data set were used. The Wilcoxon Signed Ranks Test shows there was no statistically significant difference between actual and predicted data for the 2017 data set. These results can specify the elements which probably affect aquatic ecology health. Also, these will provide direction relative to water quality management for a watershed that must be continuously preserved.

• The Korean Journal of Applied Statistics
• /
• v.35 no.4
• /
• pp.469-484
• /
• 2022

Since a large text corpus contains hundred-thousand unique words, text data is one of the typical large-dimensional data. Therefore, various feature selection methods have been proposed for dimension reduction. Feature selection methods can improve the prediction accuracy. In addition, with reduced data size, computational efficiency also can be achieved. The chi-square statistic and the information gain are two of the most popular measures for identifying interesting terms from text data. In this paper, we investigate the theoretical properties of the chi-square statistic and the information gain. We show that the two filtering metrics share theoretical properties such as non-negativity and convexity. However, they are different from each other in the sense that the information gain is prone to select more negative features than the chi-square statistic in imbalanced text data.

• The Journal of the Institute of Internet, Broadcasting and Communication
• /
• v.22 no.6
• /
• pp.107-112
• /
• 2022

In an embedded system such as a drone, it is difficult to store, transfer and analyze the entire hyper-spectral image to a server in real time because it takes a lot of power and time. Therefore, the hyper-spectral image data is transmitted to the server through dimension reduction or compression pre-processing. Feature selection method are used to send only the bands for analysis purpose, and these algorithms usually take a lot of processing time depending on the size of the image, even though the efficiency is high. In this paper, by improving the temporal disadvantage of the band selection algorithm, the time taken 24 hours was reduced to around 60-180 seconds based on the 40000*682 image resolution of 8GB data, and the use of 7.6GB RAM was significantly reduced to 2.3GB using 45 out of 150 bands. However, in terms of pixel classification performance, more than 98% of analysis results were derived similarly to the previous one.

• The Transactions of the Korean Institute of Power Electronics
• /
• v.23 no.4
• /
• pp.247-255
• /
• 2018

This paper proposes a transformer design of a direct cell-to-cell active cell balancing circuit with a multi-winding transformer for battery management system (BMS) applications. The coupling coefficient of the multi-winding transformer and the output capacitance of MOSFETs significantly affect the balancing current transfer efficiency of the cell balancing operation. During the operation, the multi-winding transformer stores the energy charged in a specific source cell and subsequently transfers this energy to the target cell. However, the leakage inductance of the multi-winding transformer and the output capacitance of the MOSFET induce an abnormal energy transfer to the non-target cells, thereby degrading the transfer efficiency of the balancing current in each cell balancing operation. The impacts of the balancing current transfer efficiency deterioration are analyzed and a transformer design methodology that considers the coupling coefficient is proposed to enhance the transfer efficiency of the balancing current. The efficiency improvements resulting from the selection of an appropriate coupling coefficient are verified by conducting a simulation and experiment with a 1 W prototype cell balancing circuit.