• The Journal of the Korea Contents Association
• /
• v.20 no.1
• /
• pp.519-529
• /
• 2020

The purpose of this study is to establish a model for predicting academic achievement of college students and to reveal the interrelationship and relative influence of each factor. For this, we surveyed the personal factors and learning strategy factors of 1,310 learners at J University, and analyzed the discriminant factors and patterns of the predictors of academic achievement through the decision tree analysis, a data mining method, and examined the relative effects of each factor. Binary logistic regression analysis was performed for viewing. As a result, the most important factor for predicting academic achievement was efficacy, and other factors such as motivation, time management, and depression were predictive of academic achievement. The patterns of factors predicting academic achievement were found to be high in efficacy and time management, and high in motivation for learning even if the efficacy was moderate. Low efficacy and learning motivation, and high depression have been shown to decrease academic achievement. Based on these results, the study suggested the efficacy and motivation to improve academic achievement of college students, strengthening time management education, and managing negative emotions.

• Journal of Information Processing Systems
• /
• v.15 no.6
• /
• pp.1306-1325
• /
• 2019

As the world is moving towards digitization, data is generated from various sources at a faster rate. It is getting humungous and is termed as big data. The financial sector is one domain which needs to leverage the big data being generated to identify financial risks, fraudulent activities, and so on. The design of predictive models for such financial big data is imperative for maintaining the health of the country's economics. Financial data has many features such as transaction history, repayment data, purchase data, investment data, and so on. The main problem in predictive algorithm is finding the right subset of representative features from which the predictive model can be constructed for a particular task. This paper proposes a correlation-based method using submodular optimization for selecting the optimum number of features and thereby, reducing the dimensions of the data for faster and better prediction. The important proposition is that the optimal feature subset should contain features having high correlation with the class label, but should not correlate with each other in the subset. Experiments are conducted to understand the effect of the various subsets on different classification algorithms for loan data. The IBM Bluemix BigData platform is used for experimentation along with the Spark notebook. The results indicate that the proposed approach achieves considerable accuracy with optimal subsets in significantly less execution time. The algorithm is also compared with the existing feature selection and extraction algorithms.

• The Journal of The Korea Institute of Intelligent Transport Systems
• /
• v.16 no.3
• /
• pp.28-38
• /
• 2017

The study is to analyze the aggressive driving behavior in the protected/permissive left turn(PPLT) intersections in Gunsan City. As a result of the logistic regression model, increasing of driver's age and driving experience, non-peak time, no company, sedan and male have a tendency to behave aggressive driving to the opposite vehicles. When the vehicles try to turn the unprotected left in the PPLT intersection, the opposite vehicle drivers recognize them at the aggressive driving behavior if the distance to opposite vehicles is not enough. The relationship between driver characteristics and the distance to the opposite vehicles is analyzed under aggressive driving behavior. increasing of age and company, peak time tend to influence the short distance opposite vehicles while male and higher driving experience the middle and long distance. Sedan has the aggressive possibility to shorter distance opposite vehicles rather than others.

• Journal of Digital Convergence
• /
• v.14 no.12
• /
• pp.13-25
• /
• 2016

This paper analyses the impacts of the characteristics of policyholder and contract on the lapse of Voluntarily Insured Person in National Pension, using the recent lapse data from National Pension Service. The logistic regression model is used in examining lapse odds with several independent variables. The result demonstrates several hypotheses of the lapse behaviors. First, the lapse odds of men is lower than that of women. Second, the effect of age on lapse odds shows concave shave with the peak at 37. Third, insured period has a negative effect on lapse odds in entrants sample. Fourth, standard monthly income has little effect on lapse in either sample. Fifth, the lapse odds decreases as the expected benefit ratio increases. Sixth, 2013 pension bill resulted in the sharp increase of lapse odds and the effect was greater for entrants. Last but not least, spatial environment such as residence also affects the lapse behavior.

• Research in Community and Public Health Nursing
• /
• v.13 no.3
• /
• pp.456-470
• /
• 2002

Objectives: The purpose of this study was to test the Theory of Planned Behavior (TPB) in the prediction of smoking cessation intention and smoking cessation behavior among adolescent smokers, in order to provide basic data to develop a future smoking cessation program as a nursing intervention. Method: The study subjects were 80 adolescent smokers who had smoked one cigarette and attended a five-day school smoking cessation program. The data were collected from October 24 to December 21, 1999. The instruments used in this study were the tools developed by Jee (1994) to measure TPB variables such as attitude toward smoking cessation behavior, subjective norm, perceived behavioral control, smoking cessation intention, and smoking cessation behavior. The data were analyzed with the SAS/PC program using descriptive statistics, hierarchical multiple regression, and logistic multiple regression. Results: 1. Attitude toward smoking cessation behavior, subjective norm, and perceived behavioral control were partially significant in predicting smoking cessation intention. 2. Smoking cessation intention and perceived behavioral control toward smoking cessation behavior did not significantly predict smoking cessation behavior. 3. There were partial interaction effects among the attitude toward smoking cessation behavior, subjective norm, and perceived behavioral control in the prediction of smoking cessation intention. 4. There were partial interaction effects between smoking cessation intention and perceiver behavioral control toward smoking cessation behavior in the prediction of smoking cessation behavior. Conclusion: This study partially demonstrated support for the TPB model that was partially useful in predicting smoking cessation intention and smoking cessation behavior among adolescent smokers. Therefore, it is recommended that attitude toward smoking cessation behavior and perceived behavioral control should be considered in developing smoking cessation programs and implementing nursing interventions to change the smoking behavior of adolescent smokers.

• Korean Journal of Health Education and Promotion
• /
• v.19 no.1
• /
• pp.17-30
• /
• 2002

BACKGROUND: Back pain is a popular disease in general population as well as in workers. School students handle heavy bag and keep awkward postures during class long time. However, the prevalence of back pain among students and the risk factors associated with back pain are not well known. METHODS: In this study, we assess the frequency of risk factors for back pain among 2,717 high school students. From April 2001 to May 2001, using a self-reported questionnaire, we collected data on occurrence of back pain and potential risk factors for back pain. RESULTS: Fifteen percent of high school students reported having daily back pain for a week or more during the past 12 months. Female students had a higher prevalence of back pain than males(OR=2.22, 95% CI 1.69-2.91). Using a multiple logistic regression model, we found six factors associated with back pain for females; alcohol(OR=1.75, 95% CI 1.26-2.45), depression(OR=1.75, 95% CI 1.84-2.28), poor physical health(OR=2.57, 95% CI 1.84-8.58), obesity(OR=0.29, 95% CI 0.12-0.68), exercise(OR=l.50, 95% CI=1.07-2.16), and good performance(OR=l.50, 95% CI 1.05-2.18). Only alcohol, however, associated with back pain for males(OR=1.70, 95% CI 1.05-2.77) CONCLUSIONS: High school students had a relatively high prevalence of back pain. Students with alcohol consumption had the higher risk for back pain.

• Korean Journal of Health Education and Promotion
• /
• v.26 no.2
• /
• pp.1-13
• /
• 2009

Objectives: This study identified how personal characteristics, family environment, governmental policy for the prevention and cessation of smoking might influence on adolescent smoking. Methods: This study used data from the 2006 Korea Youth Risk Behavior Web-based Survey of 71,404 middle school and high school students, giving a response rate of 90.9%. We selected 61,508 adolescents subjects of the final analysis without missing data on independent variables and dependent variables which are used in this study. This study used $\chi^2$ tests and logistic regression models. Variables were added to the regression model in three groups using a hierarchical approach.Results: Adolescents were significantly more likely to become current smokers if they were boys, were in a higher grade, and had lower academic achievement. Adolescents experiencing stress and depression were associated with increased risk of current smoking. Adolescents with single parents or students of non-living with parents comparing with students of living with parents showed the high possibility of smoking. Lower father's education was associated with increased likelihood of current smoking. Adolescents who were exposed to smoking at home were more likely to smoke. Adolescents without contacting with the antismoking media campaign was associated with increased likelihood of current smoking. Conclusion: Promoting antismoking media campaigns targeted at adolescent is required, and the smoking prevention education which are proper for subjects are required. Proper plans which could decrease the exposure of secondhand smoking should be established.

• Journal of the Korean Institute of Navigation
• /
• v.18 no.2
• /
• pp.91-109
• /
• 1994

Technological and organisational changes in transport system have introduced new dimension into port system development and inter-port competition. The quality of service now required by the customer is costly and not easily provided by small shipping companies and small ports. It has been suggested that in the future container shipping may be concentrated by space-sharing arrangements or actual mergers into the hands of a few mega-operators with the investment potential to provide total logistics networks. In order to compete effectively, high load factors will be essential and port concentration inevitable. A fa-voured few ports will become the load centres and other ports will assume a secondary feeder role. In this study, three questions are raised and attempts are made to answer them : (a) what is the new role of ports today ; (b) why should ports be engaged in this new role ; and (c) how can ports play this new role. In short, a modern port should be a service centre and a logistic platform for international trade and transport-a third generation port. Ports, in particular, have to make every effort to be competitive in the cost and quality of services and to make the port a transport and distribution service centre. For most ports, this is not an option but a must ; an essential requirement for survival in this win or lose situation. The best way to win is to maintain a close contact with port users, listen to them, discuss with them, help them and satisfy them. That is port marketing. Starting from the findings of port marketing, it is es-sential to work out appropriate development plans and marketing targets and to improve port competitive-ness. As an alternative method, a port competitiveness model is suggested, which may help port managers to make appropriate improvements.

• Korean Journal of Biological Psychiatry
• /
• v.17 no.4
• /
• pp.218-225
• /
• 2010

Objectives : The potential association between choline acetyltransferase(CHAT) polymorphism and the risk of mild cognitive impairment(MCI) has not been investigated in Korea. We examined the main effect of CHAT polymorphism and its interaction with apolipoprotein E(APOE) polymorphism in the development of MCI in elderly Korean sample. Methods : We analyzed CHAT 2384G > A polymorphism and APOE polymorphism among 149 MCI subjects with MCI and 298 normal controls. We tested the association between MCI and CHAT A allele status using a logistic regression model. In addition, we employed generalized multifactor dimensionality reduction(GMDR) to investigate the interaction between CHAT and APOE with regard to the risk of MCI. Results : The CHAT A allele was associated with AD risk(OR = 1.59, 95% CI = 1.02-2.48, p = 0.042). No significant gene-gene interaction between CHAT and APOE was found in GMDR method(testing balanced accuracy = 0.540, p = 0.055). Conclusion : The CHAT A allele was associated with MCI risk in the Korean elderly. Its interaction with the APOE ${\varepsilon}4$ allele was not significant with regard to the development of MCI.

• Journal of the Korean Dietetic Association
• /
• v.26 no.2
• /
• pp.85-100
• /
• 2020

Eating alone has recently become a very common dietary pattern in modern society. This study investigated the relationship between the frequency of eating alone and health related issues including chronic diseases, depression, and the quality of life (QOL). The 2016 Korea National Health and Nutrition Examination Survey provided the basic data for this study. According to the general analysis of 4,910 adults aged over 19 years or older, the average age in the 'eating alone' group was significantly higher (P<0.001), and the ratio of single-person households was significantly higher as the number of times of eating alone increased (P<0.001). Analysis of the relationship between the risk factors of metabolic syndrome according to the number of times eating alone, using logistic regression analysis, showed that the odds ratio of metabolic syndrome in the 'two times eating alone a day' group was approximately 1.3 times higher (OR=1.275) after being corrected for gender, age and energy intake. For the 'three times eating alone a day' group, the metabolic syndrome odds ratio was higher in all models except for model 1 and 5 (P for trend<0.05). The prevalence of depression using patient health questionnaire-9 (PHQ-9) was higher as the number of eating alone increased, and the QOL was inversly related with the number of meals eating alone (P for trend<0.01). We hope the results of this study will raise awareness of the health of those people who eat alone and lay the groundwork for individuals who eat alone and gain social attention.