• Journal of the Korean Society of Food Culture
• /
• v.38 no.5
• /
• pp.293-303
• /
• 2023

This study aimed to determine the association between household types and healthy dietary practices among Korean adults. A cross-sectional analysis was performed using nationwide data on 23,488 participants from the 2017-2021 Korea National Health and Nutrition Examination Survey (KNHANES). Based on self-reported data, the participant household types were classified into single- and multi-person households. The adjusted odds ratios (AORs) and 95% confidence intervals (CIs) for healthy dietary practices according to household types were calculated by applying multivariable logistic regression analysis after adjusting for confounders. Of total, 11.21% and 88.79% were single- and multi-person households, respectively. Compared with individuals living in multi-person households, those in single-person households had lower odds of adhering to healthy dietary practices (AOR: 0.88, 95% CI: 0.79-0.98) and consuming adequate saturated fatty acids (<7% of energy) (AOR: 0.78, 95% CI: 0.69-0.88). In addition, men and individuals aged ≥65 years living in single-person households exhibited lower odds of consuming adequate saturated fatty acids and ≥500 g of fruit and vegetables per day than those in multi-person households. Single-person households often find it a challenge to practice a healthy diet. Hence, nutritional policies and educational support that help individuals living alone consume healthier diets are warranted.

• Journal of the Korean Regional Science Association
• /
• v.40 no.1
• /
• pp.69-88
• /
• 2024

The study examines the effects of local environmental factors on stress among young and senior single-person households. We analyzed the '2019 Community Health Survey' by employing logistic regression analysis. The empirical results are as follows: First, there are greater differences in stress factors between young single-and multi-person households than senior single-and multi-person households; Second, stress among young single-person households was mainly influenced by physical environmental factors while stress among senior single-person households was influenced by both physical and social environmental factors. The results suggest that customized support at the local level is necessary in consideration of age-specific characteristics and stress vulnerabilities when promoting policies for the promotion of mental health among single-person households.

• Journal of Practical Engineering Education
• /
• v.16 no.2
• /
• pp.203-214
• /
• 2024

The purpose of this study was to identify the factors influencing vocational training participation among individuals aged 65 and older in order to enhance their employability. According to the research findings, the educational background and economic activity status of the elderly significantly impact their participation in vocational training. It was confirmed that economic activity and vocational training are closely related to the capacity development and increased employability of the elderly. Moreover, a considerable number of elderly individuals express a continued desire to work, and this group tends to participate more in vocational training. This underscores the importance of promoting vocational training among the elderly and developing suitable models, which holds significant policy implications. Logistic regression analysis revealed that gender, education, economic activity, desire to work, and pension income affect participation in vocational training. This highlights the necessity of formulating specific strategies in government support policies, particularly for those with lower educational backgrounds. Additionally, the study emphasizes the importance of approaches that encourage vocational training participation, especially among those with lower pension income.

• KSII Transactions on Internet and Information Systems (TIIS)
• /
• v.18 no.2
• /
• pp.370-396
• /
• 2024

COVID-19 was declared a pandemic by the World Health Organization (WHO) on 30 January 2020. The lifestyle of people all over the world has changed since. In most cases, the pandemic has appeared to create severe mental disorders, anxieties, and depression among people. Mostly, the researchers have been conducting surveys to identify the impacts of the pandemic on the mental health of people. Despite the better quality, tailored, and more specific data that can be generated by surveys,social media offers great insights into revealing the impact of the pandemic on mental health. Since people feel connected on social media, thus, this study aims to get the people's sentiments about the pandemic related to mental issues. Word Cloud was used to visualize and identify the most frequent keywords related to COVID-19 and mental health disorders. This study employs Majority Voting Ensemble (MVE) classification and individual classifiers such as Naïve Bayes (NB), Support Vector Machine (SVM), and Logistic Regression (LR) to classify the sentiment through tweets. The tweets were classified into either positive, neutral, or negative using the Valence Aware Dictionary or sEntiment Reasoner (VADER). Confusion matrix and classification reports bestow the precision, recall, and F1-score in identifying the best algorithm for classifying the sentiments.

• Land and Housing Review
• /
• v.15 no.1
• /
• pp.23-38
• /
• 2024

This study examined the residential environment of public rental housing by type at a microscale, using ANOVA and multinominal logistic models, based on the minimum and specific housing standards. The key findings are as follows. First, it was confirmed that each type of public rental housing, as well as resident characteristics, varied in meeting the minimum and specific housing standards. Second, Happy House turned out to have the worst residential environments, as a high proportion of this type did not meet the minimum housing standard and the remaining specific standards, excluding facility standards. Third, among permanent rental, national rental, and purchase/jeonse rental housing types, permanent rental housing was poor by the minimum housing standards, and area and room standards, while purchase and jeonse rental housing types showed a high proportion of failure to meet structural, performance, and environmental standards. Fourth, it was confirmed that purchase/jeonse rentals had higher rental anxiety than other types of public rental housing. In particular, anxiety about rent increases and the loss of deposits was high. These findings suggest that public efforts are called for to improve the residential environment through tailored support, depending on the type of public rental housing.

• Annals of Occupational and Environmental Medicine
• /
• v.35
• /
• pp.32.1-32.10
• /
• 2023

Background: Although many studies have been conducted on worker fatigue and sickness absence, the association between fatigue and sickness absence is unclear in Korean workers. This study was conducted to investigate the effect of worker fatigue on future sickness absence. Methods: The study was conducted on workers who received medical check-ups at a university hospital for two consecutive years (2014-2015). During check-ups in the first year, the Fatigue Severity Scale (FSS) was used to assess fatigue levels, and during check-ups in the second year, sickness absence was surveyed to determine whether they had been absent from work due to physical or mental illness during previous 12 months. The χ² test was used to analyze relationships between sociodemographic and occupational characteristics, fatigue levels, and sickness absence. Odds ratios (ORs) were calculated by logistic regression analysis controlled for confounding factors. Results: A total of 12,250 workers were included in the study, and 396 (3.2%) workers experienced more than one day of sickness absence during the study period. Adjusted ORs for sickness absence were 3.35 (95% confidence interval [CI]: 2.64-4.28) in the moderate-fatigue group and 6.87 (95% CI: 4.93-9.57) in the high-fatigue group versus the low-fatigue group. For men in the moderate- and high-fatigue groups, adjusted ORs for sickness absence were 3.40 (95% CI: 2.58-4.48) and 8.94 (95% CI: 6.12-13.07), and for women in the moderate- and high-fatigue groups, adjusted ORs for sickness absence were 2.93 (95% CI: 1.68-5.10) and 3.71 (95% CI: 1.84-7.49), respectively. Conclusions: Worker fatigue is associated with sickness absence during the following 12 months, and this association appears to be stronger for men than women. These results support the notion that sickness absence can be reduced by evaluating and managing work-related fatigue.

• The Journal of Engineering Geology
• /
• v.34 no.1
• /
• pp.107-115
• /
• 2024

This study assesses forest fire susceptibility in Gangwon-do, South Korea, which hosts the largest forested area in the nation and constitutes ~21% of the country's forested land. With 81% of its terrain forested, Gangwon-do is particularly susceptible to wildfires, as evidenced by the fact that seven out of the ten most extensive wildfires in Korea have occurred in this region, with significant ecological and economic implications. Here, we analyze 480 historical wildfire occurrences in Gangwon-do between 2003 and 2019 using 17 predictor variables of wildfire occurrence. We utilized three machine learning algorithms—random forest, logistic regression, and support vector machine—to construct wildfire susceptibility prediction models and identify the best-performing model for Gangwon-do. Forest and soil map data were integrated as important indicators of wildfire susceptibility and enhanced the precision of the three models in identifying areas at high risk of wildfires. Of the three models examined, the random forest model showed the best predictive performance, with an area-under-the-curve value of 0.936. The findings of this study, especially the maps generated by the models, are expected to offer important guidance to local governments in formulating effective management and conservation strategies. These strategies aim to ensure the sustainable preservation of forest resources and to enhance the well-being of communities situated in areas adjacent to forests. Furthermore, the outcomes of this study are anticipated to contribute to the safeguarding of forest resources and biodiversity and to the development of comprehensive plans for forest resource protection, biodiversity conservation, and environmental management.

• Korean Journal of Community Nutrition
• /
• v.29 no.3
• /
• pp.173-188
• /
• 2024

Objectives: The study aim was to analyze the regional differences in dietary protein intake and protein sources of Korean older adults and their association with metabolic syndrome. Methods: Study participants were 1,721 older adults aged 65 and over who participated in 2016-2019 Korea National Health and Nutrition Examination Survey. Using 24-hour recall dietary intake data, protein intake and their food sources were examined. The association between protein intake and metabolic syndrome, obesity, and abdominal obesity were analyzed by multiple logistic regression. Results: Total protein and animal protein intakes were higher in urban area (60.0 g, 24.4 g, respectively) than in rural area (54.6 g, 19.6 g, respectively). With increase of protein intake level, animal to total protein proportion was increased in both areas. Total protein and plant protein intake was negatively associated with the risk of obesity, abdominal obesity in both areas. Animal protein intake was negatively associated with the risk of obesity in both areas, and with abdominal obesity only in urban area. In urban area, plant protein intake was also negatively associated with the risks of metabolic syndrome, elevated triglyceride, and reduced high density lipoprotein-cholesterol. In urban area, the risk of metabolic syndrome was decreased when their protein intake was more than 0.91 g/kg and was lowest when their protein intake was more than 1.5 g/kg (P for trend < 0.001). Conclusions: Korean older adults showed inadequate protein intake and those in rural area showed lower animal protein intake than in urban area. The risk of obesity and metabolic syndrome was decreased with the increase of protein intake level. These findings may help develop effective nutrition support strategy for older adults to reduce regional health disparity.

• Annals of Hepato-Biliary-Pancreatic Surgery
• /
• v.28 no.1
• /
• pp.14-24
• /
• 2024

This study aims to assess the quality and performance of predictive models for colorectal cancer liver metastasis (CRCLM). A systematic review was performed to identify relevant studies from various databases. Studies that described or validated predictive models for CRCLM were included. The methodological quality of the predictive models was assessed. Model performance was evaluated by the reported area under the receiver operating characteristic curve (AUC). Of the 117 articles screened, seven studies comprising 14 predictive models were included. The distribution of included predictive models was as follows: radiomics (n = 3), logistic regression (n = 3), Cox regression (n = 2), nomogram (n = 3), support vector machine (SVM, n = 2), random forest (n = 2), and convolutional neural network (CNN, n = 2). Age, sex, carcinoembryonic antigen, and tumor staging (T and N stage) were the most frequently used clinicopathological predictors for CRCLM. The mean AUCs ranged from 0.697 to 0.870, with 86% of the models demonstrating clear discriminative ability (AUC > 0.70). A hybrid approach combining clinical and radiomic features with SVM provided the best performance, achieving an AUC of 0.870. The overall risk of bias was identified as high in 71% of the included studies. This review highlights the potential of predictive modeling to accurately predict the occurrence of CRCLM. Integrating clinicopathological and radiomic features with machine learning algorithms demonstrates superior predictive capabilities.

• International Journal of Computer Science & Network Security
• /
• v.24 no.7
• /
• pp.108-117
• /
• 2024

The selection and recommendation of a suitable job applicant from the pool of thousands of applications are often daunting jobs for an employer. The recommendation and selection process significantly increases the workload of the concerned department of an employer. Thus, Resume Classification System using the Natural Language Processing (NLP) and Machine Learning (ML) techniques could automate this tedious process and ease the job of an employer. Moreover, the automation of this process can significantly expedite and transparent the applicants' selection process with mere human involvement. Nevertheless, various Machine Learning approaches have been proposed to develop Resume Classification Systems. However, this study presents an automated NLP and ML-based system that classifies the Resumes according to job categories with performance guarantees. This study employs various ML algorithms and NLP techniques to measure the accuracy of Resume Classification Systems and proposes a solution with better accuracy and reliability in different settings. To demonstrate the significance of NLP & ML techniques for processing & classification of Resumes, the extracted features were tested on nine machine learning models Support Vector Machine - SVM (Linear, SGD, SVC & NuSVC), Naïve Bayes (Bernoulli, Multinomial & Gaussian), K-Nearest Neighbor (KNN) and Logistic Regression (LR). The Term-Frequency Inverse Document (TF-IDF) feature representation scheme proven suitable for Resume Classification Task. The developed models were evaluated using F-Score_M, Recall_M, Precission_M, and overall Accuracy. The experimental results indicate that using the One-Vs-Rest-Classification strategy for this multi-class Resume Classification task, the SVM class of Machine Learning algorithms performed better on the study dataset with over 96% overall accuracy. The promising results suggest that NLP & ML techniques employed in this study could be used for the Resume Classification task.