• Journal of the Korea Academia-Industrial cooperation Society
• /
• v.19 no.12
• /
• pp.507-514
• /
• 2018

This study utilized latent growth curve modeling to investigate the trajectories of adolescent life satisfaction changes in middle and high school students. The effects of self-esteem, career identity, school learning activity, gender, and household earnings on life satisfaction changes were examined. Data was obtained from the Korea Child Youth Panel Survey (KYCPS), a longitudinal study following students for 7 years. Year 3-6 data was utilized. Results found that the life satisfaction trajectory resulted as a quadratic model in which individual differences were significant. Second, school learning activity used as a time variant variable had a positive significant effect on life satisfaction each year. Third, gender and self-esteem as time invariant variables had significant effects on initial levels while self-esteem had effects on the slope and quadratic change. Further implications and research issues are discussed.

• Proceedings of the Korean Institute of Information and Commucation Sciences Conference
• /
• 2022.05a
• /
• pp.587-588
• /
• 2022

In this paper, we propose a rigid body tracking method in 3D space using 2D passive marker images from multiple motion capture cameras. First, a calibration process using a chess board is performed to obtain the internal variables of individual cameras, and in the second calibration process, the triangular structure with three markers is moved so that all cameras can observe it, and then the accumulated data for each frame is calculated. Correction and update of relative position information between cameras. After that, the three-dimensional coordinates of the three markers were restored through the process of converting the coordinate system of each camera into the 3D world coordinate system, the distance between each marker was calculated, and the difference with the actual distance was compared. As a result, an error within an average of 2mm was measured.

• Journal of the Korea Society of Computer and Information
• /
• v.29 no.2
• /
• pp.51-59
• /
• 2024

This study examines the relationship between the release of the news and the individual stock returns. Investors utilize a variety of information sources to maximize stock returns when establishing investment strategies. News companies publish their articles based on stock recommendation reports of analysts, enhancing the reliability of the information. Defining release of a stock-recommendation news article as an event, we examine its economic impacts and propose a binary classification model that predicts the stock return 10 days after the event. XGBoost and LightGBM models are applied for the study with accuracy of 75%, 71% respectively. In addition, after categorizing the recommended stocks based on the listed market(KOSPI/KOSDAQ) and market capitalization(Big/Small), this study verifies difference in the accuracy of models across four sub-datasets. Finally, by conducting SHAP(Shapley Additive exPlanations) analysis, we identify the key variables in each model, reinforcing the interpretability of models.

• The Korean Journal of Applied Statistics
• /
• v.37 no.3
• /
• pp.381-393
• /
• 2024

This study investigates the impact of pseudonymization of personal information and its effect on the accuracy of data analysis. We quantitatively evaluated the relationship between the degree of pseudonymization and the accuracy of data analysis using logistic regression models, decision trees, and random forests. Through this, we confirmed that pseudonymizing sensitive information can realize personal information protection without significantly damaging data quality. However, we recognized limitations such as single sample data and consistent application of pseudonymization ratios. To overcome these limitations, additional research on diverse datasets is necessary to strengthen the generalizability of results. Moreover, we propose developing and applying methodologies to find optimal pseudonymization ratios for individual variables. The results from this study provide new insights into maintaining usability of data while achieving regulatory compliance and personal information protection.

• Korean Journal of Health Education and Promotion
• /
• v.13 no.1
• /
• pp.1-27
• /
• 1996

Recently diseases related to personal health habit and lifestyle have become common in modern industrial society. These kinds of diseases can be prevented simply by changing one's lifestyle to be more healthy. As a result of realization our interest in general health has become stronger. The most basic environment for human-being in society is the home. Humans secure their livelihood, physically. mentally, and socially at home. Therefore health care at home is very important. In modern society the responsibility for this task is traditionally given to housewives. The purpose of this study was to measure the degree of the health knowledge, health concern, health behavior and family health care of the married women and to analyze its related factors. The subjects for this study. 1,100 married women who studied at social education institutes and who had children attending an elementary school or a kindergarten, were surveyed with questionnaires. The preliminary survey was carried out from Aug. 7, to Aug. 19, 1995. With complement of questions, the main survey was carried out from Sep. 11, to Sep. 30, 1995. The data was analysed by using the SAS program. The results were as follows. 1. General Characteristics (1) In the individual characteristics of the respondents, the married women aged 30-39 were 54.8%, the average age was 39.8 years old. 33.8% of respondents had 6-10 years of marriage period, and the average marriage period was 14.9 years. Most of them(96.5%) lived with their husband. Those who graduated from college and graduate school were 53.4%. And 68.3% of respondents had no job. (2) In the family characteristics, 69.3% of the married women had 3 or 4 family members and the average family size was 4.1 person. 60.0% of the respondents had 2 children. Most of the respondents(90.9%) had no married children. 84.8% of the respondents lived with their parents. Those who reported that the total family income was more than 2,500,000 won a month were 32.3%. When making the decisions, 68.5% of the married women discussed the family matter with their husband. (3) In the individual characteristics of the respondents, 51.5% answered they were in good health. 61.7% of the married women answered they obtained the health knowledge through mass media. 24.3% of the women answered they had patients in their family in these days. 67.5% of the respondents answered they could generally control their health by themselves. 2. The Health Knowledge, Concern and Behavior. (1) For the health knowledge, the average score was 11.8. The lowest percent of correct answer(27.8%) was in the item about the skin tests for tuberculosis. And the highest percent(97.%) was in the item about taking a rest. (2) For the health concern, the married women had the highest concern about washing hands. But they were indifferent to smoking. (3) For the health behavior, the highest score was in "changing socks and underwear everyday", and the lowest one was in "taking a regular dental examination". 3. The Family Health Care (1) For the family health care, the item of "using a drug with the order of doctor or pharmacist" had the highest grade(4.78), and "consulting with the family physician about the health problem" had the lowest grade(2.03). (2) Older women and the women with a longer period of marriage had the highest level of the family health care(p<0.001). The married women who had 3 children had the highest level of the family health care(p<0.001). Those who had 5 or 6 family member and higher income had the highest level had the high level of the family health care(p<0.01). Women in good health and those who had the health knowledge from health experts had a high level of the family health care. (3) For the correlation of the family health care and other variables, the health behavior showed the highest correlation with family heath care practice(r=0.74) and the second was health concern(r=0.43). The variables which could explain the family health care were health behavior, the health concern and married women's health status(r²=55.87). The most closely associated with family health care was health behavior(r²=54.93)

• The Journal of Korean Association of Computer Education
• /
• v.16 no.2
• /
• pp.39-48
• /
• 2013

This study investigates the predictive model of the adolescents' computer entertainment behavior using neural network with the KYPS data (3449 in the junior high school; 1725 boys and 1724 girls). This study compares the results of neural network(model 1) to the logistic regression model and neural network(model 2) with the exact same variables used in logistic regression. The results reveal that the prediction of neural network model 1 is the highest among three models and with gender, computer use time, family income, the number of close friends, the number of misdeed friends, individual study time, self-control, private education time, leisure time, self-belief, stress, adaptation to school, and study related worries, the neural network model 1 predicts the computer entertainment behavior more efficiently. These results suggest that the neural network could be used for diagnosing and adjusting the adolescents' computer entertainment behavior.

• The Journal of The Korea Institute of Intelligent Transport Systems
• /
• v.15 no.3
• /
• pp.23-33
• /
• 2016

This study identified the factors that affect travel time budget by mode for traveler in Seoul using the SUR model. Individual, household and TAZ characteristics were selected as the explanatory variables. Transportation modes are summarized from 18 types to 6 types(walking, personal car, bus, subway, rail and bicycle). The results showed a distinct difference between personal transportation and public transportation. First of all, People who owned a car and driver's licence tend to prefer personal transportation. In addition, we can confirm the relationship between the bus and the subway which are most typical public transportation. Passengers who can available a personal mode preferred the subway than the bus. It is expected to suggest various implications related to the public transportation policy for Seoul metropolitan area.

• Korean Journal of Social Welfare
• /
• v.63 no.2
• /
• pp.233-260
• /
• 2011

This study intends to analyze the trend of employment rate of men aged 55~64 in 15 OECD countries from 1980 to 2005. Furthermore, this study means to examine the determinants of men aged 55~64 in 15 OECD countries to support the labor force participation among them. The analysis is based on the data of OECD, ILO and LIS. The analysis method is Arellano and Bond(1981)'s difference GMM which used instrumental variables by dynamic panel model which estimates state dependency of labor market participation and individual panel's heterogeneity. The main results from this analysis are summarized in three points. First, the employment rates of men aged 55~64 had decreased until the middle of the 1990s, while that has been increasing since 1995. Second, the sate dependency strongly worked in the employment rates of 55~64 men and positive period effect was observed for 1980~2005. This study cannot find the pull effect of public pension, while labor market push effect have negatively affected. Third, temporary work rates had contributed to increase the employment rate of men aged 55~64 for 1996~2005. The poverty has become the mechanism of the labor.

• Journal of the Institute of Electronics Engineers of Korea CI
• /
• v.40 no.3
• /
• pp.144-154
• /
• 2003

In this paper we present Logical Evolution method which is a new teaming algorithm for the concepts expressed as binary logic function. We try to solve some problems of Inductive Learning algorithms through Logical Evolution. First, to be less affected from limited prior knowledge, it generates features using the gained informations during learning process and learns the concepts with these features. Second, the teaming is done using not the whole example set but the individual example, so even if new problem or new input-output variables are given, it can use the previously generated features. In some cases these old features can make the teaming process more efficient. Logical Evolution method consists of 5 operations which are selected and performed by the logical evaluation procedure for feature generation and learning process. To evaluate the performance of the present algorithm, we make experiments on MONK data set and a newly defined problem.

• Journal of Korean Society of Transportation
• /
• v.26 no.6
• /
• pp.29-38
• /
• 2008

In Seoul, the volume of office market has been expanding rapidly and the currency will be maintained. Many researches have looked at determinants of the office rent, we still cannot have adequate and accurate information of the impacts of traffic congestions around office buildings on the office rents. To gauge the effect of traffic conditions surrounding an office building on the office rent, a hedonic price model was estimated. The regression analysis estimates the values or implicit prices of the individual rent determinants; these parameters in turn allow for a detailed examination of the variables that impact office rents. The result shows that traffic conditions of office buildings play an important role in determining the office rental rate. Since a number of adjacent streets provided excellent opportunities to connect with the neighborhood, it pulls up the rental rate. Similarly, traffic congestions depreciates the value of an office buildings restricting the accessibility to the office building. We also provide evidence of the existence of spatial submarkets and find that market takes different spatial forms depending on the local context.