• Journal of Korean Public Health Nursing
• /
• v.35 no.1
• /
• pp.60-71
• /
• 2021

Purpose: This study examined the socio-demographic and health factors affecting the quit-smoking plan in smoking seniors. Methods: Data were obtained from the Seventh Korean National Health and Nutrition Examination Survey (VII-1, VII-2, VII-3). The sample consisted of 369 smoking seniors. The complex sample was analyzed thought an independent t-test, Chi-square test, and multiple logistic regression. Results: The influential factors on the quit-smoking plan were daily smoking (OR=0.30, CI=0.11-0.78), age of start smoking (OR=1.06, CI=1.01-1.11), daily smoking amount (OR=0.95, CI=0.90-1.00), quit-smoking trial (OR=2.63, CI=1.32-5.23), and cognitive stress (OR=2.13, CI=1.01-4.54). Conclusion: This study revealed the variables that should be considered when setting up a smoking cessation plan for smoking seniors. Based on this, an elderly cessation intervention program can be developed.

• International Journal of Internet, Broadcasting and Communication
• /
• v.11 no.1
• /
• pp.47-53
• /
• 2019

The idea of ensemble learning is to train multiple models, each with the objective to predict or classify a set of results. Most of the errors from a model's learning are from three main factors: variance, noise, and bias. By using ensemble methods, we're able to increase the stability of the final model and reduce the errors mentioned previously. By combining many models, we're able to reduce the variance, even when they are individually not great. In this paper we propose an ensemble model and applied it to classification problem. In iris, Pima indian diabeit and semiconductor fault detection problem, proposed model classifies well compared to traditional single classifier that is logistic regression, SVM and random forest.

• Journal of Korean society of Dental Hygiene
• /
• v.22 no.5
• /
• pp.341-346
• /
• 2022

Objectives: This study was conducted to analyze the relationship between smoking and denture wear in the elderly individuals aged 65 years and older, and a total of 3,112 people were included. Methods: A complex sample chi-square test was performed for denture wear according to general, smoking, and smoking-related characteristics. Factors related to denture wear were assessed using multiple logistic regression analysis. Results: Among non-smokers, present smokers were 4.192 times more likely to wear dentures, and former smokers were 2.195 times more likely to wear dentures. The average number of daily past smokers was 0.564 times less likely to wear dentures if they smoked 15 cigarettes or less per day. Conclusions: Smoking among the elderly and wearing dentures are related, and it is necessary to develop and utilize a smoking cessation education program considers socioeconomic characteristics.

• International Journal of Advanced Culture Technology
• /
• v.11 no.3
• /
• pp.131-141
• /
• 2023

This study aimed to identify the determinants of physical frailty among the old-old adults in rural Korean communities. A total of 191 individuals aged 75 and older were included in the study, with the majority being female. Participants were classified into healthy (n=47), pre-frail (n=54), and frail (n=90) groups. Significant differences were found across these groups in terms of age, gender, education level, depression, and nutritional status. Multiple logistic regression analysis revealed that age (OR=1.16), depression (OR=0.21), malnourishment (OR=10.85), and short physical performance ability (OR=0.70) were significant predictors of physical frailty. These findings underscore the multifaceted nature of physical frailty among old-old adults in urban-rural complex communities and highlight the need for comprehensive and integrated interventions. Such interventions should consider not only physical factors but also broader health conditions and socio-demographic influences impacting the elderly. Further research is needed to develop and evaluate interventions that address these determinants and promote health equity among the elderly population in urban-rural complex communities

• International Journal of Internet, Broadcasting and Communication
• /
• v.16 no.4
• /
• pp.290-300
• /
• 2024

This study presents a comprehensive evaluation of various machine learning models for predicting heart failure outcomes. Leveraging a data set of clinical records, the performance of Logistic Regression, Support Vector Machine (SVM), Random Forest, Soft Voting ensemble, and XGBoost models are rigorously assessed using multiple evaluation metrics, including accuracy, precision, recall, F1-score, and area under the receiver operating characteristic curve (AUC). The analysis reveals that the XGBoost model outperforms the other techniques across all metrics, exhibiting the highest AUC score, indicating superior discriminative ability in distinguishing between patients with and without heart failure. Furthermore, the study highlights the importance of feature importance analysis provided by XGBoost, offering valuable insights into the most influential predictors of heart failure, which can inform clinical decision-making and patient management strategies. The research also underscores the significance of balancing precision and recall, as reflected by the F1-score, in medical applications to minimize the consequences of false negatives.

• Proceedings of the Korean Institute of Navigation and Port Research Conference
• /
• v.29 no.1
• /
• pp.441-449
• /
• 2005

The purpose of this research is to present the improvement measure of lagging behind coastal shipping system to be a logistic hub-nation with a competitive edge. For this purpose, this research tries to find out major northeast asia environment factors and accordingly the effects of its. The effects of coastal shipping system's development strategy is analysed by structural equation model and multiple regression model. Research results show that three types of coastal shipping developing strategy(connected transportation system, structure of coastal shipping system, governmental support policy) will contribute much to be logistic hub-nation. The contribution effects is increasing cargo from strengthened feeder transport system and maximizing logistic service &minimizing logistic costs. From the result, some implications are derived as follow. First, familiar environmental balanced ocean-coastal transport system is required. Second the one-stop logistic service system is necessary to build excusive feeder port, and to establish Ro-Ro ship & high-speed ship, etc.. Third, governmental support policy and subsidy(tax exempted oil & various tax benefits) are required to bring up lagging behind coastal shipping system to be a logistic hub-nation with a competitive edge.

• Journal of Korean Academy of Nursing
• /
• v.39 no.4
• /
• pp.549-561
• /
• 2009

Purpose: Work-related stress and risk factors among Korean employees were identified in this study. Methods: Data were obtained from employees aged 20 to 64 using the Korean Working Conditions Survey 2006 (KWCS). Multiple logistic regression analysis using SAS version 9.1 was performed to examine risk factors of work-related stress by gender. Results: The age-adjusted prevalence of work-related stress among male and female employees was 18.4% and 15.1% respectively. After adjustments for multiple variables among both male and female employees, there was a significant relationship between work-related stress and risk factors including education, company size, work time, ergonomic risks, biological chemical risks, and job demands. The significant variables for male employees were housework load, occupational class, and shift work, and for female employees, type of employment. Conclusion: There is a need to develop and support intensive stress management programs nationally giving consideration to work-related stress associated with working time, physical working environment, and job demands. Based on gender specific approaches, for male employes, stress management programs should be developed with consideration being given to occupational class and shift work. For stress management programs for female employees, consideration needs to be given to permanent employment status, specifically those in small companies.

• Korean Parent-Child Health Journal
• /
• v.21 no.1
• /
• pp.1-10
• /
• 2018

Purpose: This study was to identify factors associated with premenstrual syndromes based on women's subjective assessment and investigate problems related to menstruation in female college students. Methods: The data was collected by questionnaires from 558 nursing students in a university in Gyeonggi, Korea. The data were analyzed with the IBM SPSS 21.0 program, using descriptive statistics, independent t-test, one-way ANOVA, multiple response and multiple logistic regression. Results: The problems related to menstruation included irregular menstrual cycle, severe dysmenorrhea, no menstruation, abnormal uterine bleeding, and menorrhagia. Influential factors on premenstrual syndrome revealed dysmenorrhea (${\beta}=.467$, p<.001), perceived stress status (very high) (${\beta}=.155$, p<.001), perceived stress status (high) (${\beta}=.119$. p=.002), perceived health status (very poor) (${\beta}=.102$, p=.006), and smoking (${\beta}=.087$, p=.016) in female college students. Conclusion: The findings suggest that active management and intervention regarding menstruation disorders and premenstrual syndrome are required.

• Research in Community and Public Health Nursing
• /
• v.28 no.3
• /
• pp.271-279
• /
• 2017

Purpose: Non-Suicidal Self-Injury (NSSI), a highly prevalent behavior in adolescents, refers to the direct destruction of one's body tissue without suicidal intent. To date, the prevalence of adolescent self-injury in South Korea and its associated factors remain unknown. This study aims to determine the prevalence of self-injury in Korean adolescents as well as its associated factors. Methods: We assessed 717 middle school students by means of an anonymous self-report survey. Information about demographic characteristics, lifestyle, anxiety and depression, self-esteem, and parenting behavior was obtained. Data were analyzed using $x^2$ test, t-test and multiple logistic regression. Results: NSSI was reported by 8.8% of respondents. Univariate analyses showed associations of exposure to alcohol use, anxiety, depression, self-esteem, and parenting methods with self-injury. In multiple analyses, alcohol use, anxiety, and parental abuse were associated with lifetime self-injury. Conclusion: The rate of NSSI in the South Korea was found to be lower than those of other countries. As our study suggests that alcohol use, anxiety, and parental abuse are associated with lifetime self-injury, health care providers at school should take these factors into account when developing prevention and intervention programs for adolescents.

• Women's Health Nursing
• /
• v.24 no.3
• /
• pp.233-242
• /
• 2018

Purpose: To identify risk factors for premature birth among premature obstetric labor women. Methods: Participants were 129 hospitalized women who were diagnosed with potential premature obstetric labor with 20 weeks to 37 weeks of gestation. Data were analyzed using descriptive statistics, $x^2$ test, t-test, and binary logistic regression. Results: Of 129 women, 78(60.5%) gave premature birth and 51 (39.5%) gave full-term birth. Risk factors for premature birth were education level (${\leq}$bachelor's degree), abnormal bowel condition (constipation or diarrhea), time firstly diagnosed with a premature obstetric labor (below 28 weeks of pregnancy), and multiple pregnancy. There were also increased risks of premature birth for participants with high level of anxiety and high level of prenatal stress. In social support, there was an increased risk of premature birth for participants with low level of social support. Conclusion: Prenatal nursing programs should consider not only psychosocial factors such as anxiety, prenatal stress, and social support, but also some general and obstetric factors such as education level, abnormal bowel condition, time firstly diagnosed with a premature obstetric labor, and multiple pregnancy to increase maternal and child health.