• International Journal of Human Ecology
• /
• v.16 no.2
• /
• pp.21-31
• /
• 2015

This study explored determinants of family support that young renter households received to afford their housing costs. Microdata set of the 2014 Korea Housing Survey was used as secondary data for the study. Total 1,752,899 households headed by persons between 20 and 34 years of age and whose rental type was either Jeon-se or monthly rental with deposit in private rental units were selected as study subjects. For the data analysis, a series of discriminant analysis was conducted using IBM SPSS 21.0. Major findings were as follows. (1) Among the subjects, 28.2% were found to receive financial support from parents or other relatives. (2) To see the discriminant analysis results, a linear combination of seven household and housing characteristics (householder's gender, whether or not the householder worked in the previous week, whether or not the householders have a spouse, tenure type, structure type, location and deposit amount) could explain 44.6% of variance in young renter households' receipt of family support with a prediction accuracy of 77.2%. (3) To summarize the final discriminant model, Jeon-se renter households in location other than Incheon or Gyeonggi Province living in a unit in structure other than multifamily structure headed by younger householders that did not worked previous week or without spouse; with a greater deposit had the maximum tendency to receive family support to pay rental costs.

• The Journal of Korean Academic Society of Nursing Education
• /
• v.23 no.4
• /
• pp.389-397
• /
• 2017

Purpose: This study was conducted to examine awareness of biomedical ethics, and to identify affecting factors of the awareness of biomedical ethics in nursing students. Methods: The subjects consisted of 266 nursing students their third and fourth years of study. The data were collected from October to December, 2015 by self-report using questionnaires. Data analysis was performed using SPSS/WIN 18.0, descriptive statistics, t-test, ANOVA, $Scheff{\acute{e}}$ test, Pearson correlation coefficient, and multiple regression analysis. Results: The mean score of the awareness of biomedical ethics was $2.81{\pm}0.22$, perception of death was $3.15{\pm}0.36$, and knowledge of brain death, organ donation, and organ transplant was $12.12{\pm}3.02$. The prediction factors of awareness of biomedical ethics were gender (${\beta}=.29$, p<.001), participation in religious activity (${\beta}=.23$, p=.015), and perception of death (${\beta}=.20$, p=.016). The explanation power was 17.1%. Conclusion: These results showed that education about biomedical ethics is necessary for nursing students, and the development of biomedical ethics educational programs should reflect affecting factors.

• IE interfaces
• /
• v.16 no.spc
• /
• pp.144-148
• /
• 2003

A group of digital human models with various sizes which properly represents a population under consideration is needed in the design process of an ergonomic product in virtual environment. The present study proposes a two-step method which produces a representative group of human models in terms of stature and weight. The proposed method first generates a designated number of pairs of stature and weight within an accommodation range from the bivariate normal distribution of stature and weight of the target population. Then, from each pair of stature and weight, the method determines the sizes of body segments by using 'hierarchical' regression models and corresponding prediction distributions of individual values. The suggested method was applied to the 1988 US Army anthropometric survey data and implemented to a web-based system which generates a representative group of human models for the following parameters: nationality, gender, accommodation percentage, and number of human models.

• Proceedings of the Korea Information Processing Society Conference
• /
• 2016.04a
• /
• pp.588-590
• /
• 2016

사용자의 성별은 기본적이면서도 중요한 마케팅 데이터다. 그러나 최근에는 개인정보보호 강화 추세로, 회원가입 시 성별이나 나이 등의 세부 정보를 입력하지 않는 간편 가입이 많아졌다. 이러한 입력되지 않은 정보 추출을 위해 성별 예측 연구의 필요성이 증가되었다. 성별이 입력된 사용자의 정보를 바탕으로 성별이 입력되지 않은 사용자의 성별을 예측하는 기존 연구가 다양한 방법으로 진행되어왔고, 우수한 식별이 가능한 기법들은 이진분류기인 SVM을 기반으로 한 연구가 다수 존재한다. 그러나 SVM 알고리즘은 이진 분류만 가능하기 때문에 성별예측에 대한 정확률은 알 수가 없다. 성별예측의 정확률을 활용하면 부정확한 분류를 예방할 수 있으며 상품추천의 가중치로 사용 될 수 있다. 본 연구는 확률을 기반으로 하여 정확률을 추론 가능한 나이브 베이지안을 응용한다. 그리고 데이터 집합 사례를 균형있게 늘려주는 SMOTE기법을 이용해 클래스 불균형 문제를 개선했으며 또한 성별 예측의 특성에 맞게 노이즈를 제거하고, 성별 분류에 확정적인 아이템에 가중치를 적용했다. 더불어 제안 방법을 실제 데이터에 적용시켜 우수성을 입증하였다.

• Journal of Broadcast Engineering
• /
• v.26 no.5
• /
• pp.583-591
• /
• 2021

This paper explores variables that influence the prediction of OTT service experience and free(AVOD)/ paid(SVOD) service use. Research results showed that five variables such as gender, age, personal income, household composition, and e-commerce use experience had a significant impact on identifying OTT service experience and whether to use free or paid services. Also, it was found that the probability of using SVOD increases as they prefer news and drama genres and use OTT services for more time. In summary, those who are relatively young, have a high personal income, and are more adapted to digital environments such as e-commerce are more likely to use SVOD.

• International Journal of Advanced Culture Technology
• /
• v.10 no.2
• /
• pp.28-33
• /
• 2022

This study aims to investigate factors that affect elderly poverty based on a comprehensive and universal perspective, suggesting some alternatives for improving the poverty rate of the elderly. The comprehensive and universal approach to the poverty of the aged that this study attempts can give a better understanding of the elderly poverty beyond the contribution of the existing literature, with the research model including individual, family, labor, and income factors as the causes of old-age poverty from the comprehensive and universal perspective on the causes of poverty of the elderly. In addition, the study attempts to input variants of variables into the equation for the causes of elderly poverty by using panel data from the 8th Korean Retirement and Income Study. This study employs decision tree analysis to determine the cause of the poverty of the elderly using CHAID. The decision tree analysis shows that the most vital variable affecting elderly poverty is making income. For the poor elderly without earned income, public pensions, educational careers, and residential areas influence elderly poverty, but for the poor elderly with earned income, wage earners and gender are variables that affect poverty. This study suggests some alternatives to improve the poverty rate of the aged. The government should create a better working environment such as senior re-employment for old people to be able to participate in economic activities, improve public pension or social security for workers with unfavorable conditions for public security of old age, and give companies that create employment of the aged diverse incentives.

• Journal of Navigation and Port Research
• /
• v.40 no.6
• /
• pp.375-384
• /
• 2016

This study aimed to specify Vessel Traffic System(VTS) operators' situational awareness(SA) tasks and examine differences in subjective ratings for three levels of SA. Data for relative frequencies of SA tasks were collected by using direct in field observation. Subjective rating scores were obtained using a questionnaire method and compared in terms of VTS operator's gender and length of service career. The results are as follows. First, it was found that the VTS operators perform information perception task elements more frequently than those for information integration and prediction. Second, VTS operators tended to show subjectively lower evaluation scores for prediction than information perception or integration. Third, male VTS operators rated their SA ability higher than females. Fourth, the male VTS operators more than 15 years of career service showed higher subjective rating scores than those with under 5 years of service. Female VTS operators with different levels of career service showed a similar level of subjective rating scores. These results suggest that the frequency of SA related tasks and subjective SA evaluation can differ in terms of SA levels and individual differences.

• Journal of the Korea Academia-Industrial cooperation Society
• /
• v.19 no.11
• /
• pp.126-136
• /
• 2018

The purpose of this study was to develop a severity-adjustment model for predicting mortality in acute stroke patients using machine learning. Using the Korean National Hospital Discharge In-depth Injury Survey from 2006 to 2015, the study population with disease code I60-I63 (KCD 7) were extracted for further analysis. Three tools were used for the severity-adjustment of comorbidity: the Charlson Comorbidity Index (CCI), the Elixhauser comorbidity index (ECI), and the Clinical Classification Software (CCS). The severity-adjustment models for mortality prediction in patients with acute stroke were developed using logistic regression, decision tree, neural network, and support vector machine methods. The most common comorbid disease in stroke patients were hypertension, uncomplicated (43.8%) in the ECI, and essential hypertension (43.9%) in the CCS. Among the CCI, ECI, and CCS, CCS had the highest AUC value. CCS was confirmed as the best severity correction tool. In addition, the AUC values for variables of CCS including main diagnosis, gender, age, hospitalization route, and existence of surgery were 0.808 for the logistic regression analysis, 0.785 for the decision tree, 0.809 for the neural network and 0.830 for the support vector machine. Therefore, the best predictive power was achieved by the support vector machine technique. The results of this study can be used in the establishment of health policy in the future.

• The Korean Journal of Applied Statistics
• /
• v.37 no.3
• /
• pp.323-338
• /
• 2024

This study analyzes the Korean professional volleyball league and predict match outcomes using popular machine learning classification methods. Match data from the 2012/2013 to 2022/2023 seasons for both male and female leagues were collected, including match details. Two different data structures were applied to the models: Separating matches results into two teams and performance differentials between the home and away teams. These two data structures were applied to construct a total of four predictive models, encompassing both male and female leagues. As specific variable values used in the models are unavailable before the end of matches, the results of the most recent 3 to 4 matches, up until just before today's match, were preprocessed and utilized as variables. Logistc Regrssion, Decision Tree, Bagging, Random Forest, Xgboost, Adaboost, and Light GBM, were employed for classification, and the model employing Random Forest showed the highest predictive performance. The results indicated that while significant variables varied by gender and data structure, set success rate, blocking points scored, and the number of faults were consistently crucial. Notably, our win-loss prediction model's distinctiveness lies in its ability to provide pre-match forecasts rather than post-event predictions.

• Physical Therapy Korea
• /
• v.12 no.3
• /
• pp.74-83
• /
• 2005

The purpose of this study was to produce the regression equation from non-exercise $VO_{2max}$ of healthy young adults and to develop a maximal oxygen consumption ($VO_{2max}$) regression model. This model was based on heart rate non-exercise predictor variables (rest heart rate, maximal heart rate/rest heart rate), as an extra addition to the general regression which can reflect an individual's inherent or acquired cardiorespiratory fitness. The subjects were 101 healthy young adults aged 19 to 35 years. Exercise testing was measured by using a Balke protocol for treadmill and indirect calorimetry. The prediction equation was analyzed by using stepwise multiple regression procedures. The mean of $VO_{2max}$ was $39.02{\pm}6.72\;m{\ell}/kg/min$ (mean${\pm}$SD). The greatest variable correlated to $VO_{2max}$ was %fat. The predictor variable used in the non-exercise $VO_{2max}$ included %fat, gender, habitual physical activity and $HR_{max}/HR_{rest}$. The non-exercise $VO_{2max}$ estimation was as follows: $VO_{2max}$($m{\ell}/kg/min$)=55.58-.41(%fat)+.59(physical activity rating)-2.69($HR_{max}/HR_{rest}$)-5.36 (male=0, female=1); (R=.85, SEE=3.64, R2=.72: including heart rate variable); $VO_{2max}$($m{\ell}/kg/min$)=48.47-.41(%fat)+.45(physical activity rating)-5.12 (male=0, female=1); (R=.84, SEE=3.74, R2=.70: with the exception of heart rate variable). As an added heart rate variable, there was only a 2% coefficient of determination improved. Therefore, these results demonstrated that heart rate variable correlation with a non-exercise regression model was very low. In conclusion, for healthy young korean adults, those variables that can affect non-exercise $VO_{2max}$ estimation turned out to be only % fat, gender, and physical activity. We suggest that further research of predictor variables for non-exercise $VO_{2max}$ is necessary for different patient groups who cannot perform maximal exercise or submaximal exercise.