• Journal of the Korea Society of Computer and Information
• /
• v.28 no.7
• /
• pp.57-65
• /
• 2023

Various studies to enhance the accuracy of rice production forecasting are focused on improving the accuracy of the models. In contrast, there is a relative lack of research regarding the data itself, which the prediction models are applied to. When applying the same dependent variable and prediction model to two different sets of rice production data composed of distinct features, discrepancies in results can occur. It is challenging to determine which dataset yields superior results under such circumstances. To address this issue, by identifying potential influential features within the data before applying the prediction model and centering the modeling around these, it is possible to achieve stable prediction results regardless of the composition of the data. In this study, we propose a method to adjust the composition of the data's features in order to select optimal base variables, aiding in achieving stable and consistent predictions for rice production. This method makes use of the Korea Meteorological Administration's ASOS data. The findings of this study are expected to make a substantial contribution towards enhancing the utility of performance evaluations in future research endeavors.

• The Journal of Bigdata
• /
• v.6 no.2
• /
• pp.85-98
• /
• 2021

The pandemic of COVID-19 further promoted the imbalance in the volume of imports and exports among countries using containers, which worsened the shortage of empty containers. Since it is important to secure as many empty containers as the appropriate demand for stable and efficient port operation, measures to predict demand for empty containers using various techniques have been studied so far. However, it was based on long-term forecasts on a monthly or annual basis rather than demand forecasts that could be used directly by ports and shipping companies. In this study, a daily and weekly prediction method using an actual artificial neural network is presented. In details, the demand forecasting model has been developed using multi-layer perceptron and multiple linear regression model. In order to overcome the limitation from the lack of data, it was manipulated considering the business process between the loaded container and empty container, which the fully-loaded container is converted to the empty container. From the result of numerical experiment, it has been developed the practically applicable forecasting model, even though it could not show the perfect accuracy.

• Exercise Science
• /
• v.28 no.1
• /
• pp.82-90
• /
• 2019

PURPOSE: The purpose of this study was to examine the association of waist to height ratio (WHtR) and resting heart rate (RHR) with cardio-metabolic risk factors among Korean postmenopausal women. METHODS: A cross-sectional analysis was performed using the 2015 Korea National Health and Nutrition Examination Survey. The analysis included a total of 1,540 postmenopausal women. RESULTS: Individuals with higher WHtR (>0.56) showed significantly higher glucose, triglyceride, insulin, Homeostatic Model Assessment for Insulin resistance (HOMA-IR), total cholesterol, systolic and diastolic blood pressure compared with ones with lower WHtR (≤0.51). Similar findings were found in those with higher RHR (≥90 bpm) compared with ones with lower RHR (<60 bpm) for glucose and HOMA-IR. When determining the combined effects of WHtR and RHR on the prevalence of metabolic syndrome, individual with WHtR above 0.5 and RHR above 80 bpm showed 10.39 times higher prevalence of metabolic syndrome compared with those with WHtR below 0.5 and RHR below 70 bpm. We further performed multiple linear regression analysis to understand how WHtR and RHR contribute to fasting glucose, and found that both WHtR and RHR contribute to fasting glucose levels independent of age, education level, marital status and income level. CONCLUSIONS: The current study showed that the WHtR and RHR are associated with cardio-metabolic risk factor and prevalence of metabolic syndrome in Korean postmenopausal women.

• Korea Journal of Hospital Management
• /
• v.28 no.3
• /
• pp.58-67
• /
• 2023

Purpose: The purpose of this study was to analyze the factors associated with long-term hospitalized patients in long-term care hospitals using the quality assessment data for long-term care hospitals by the Health Insurance Review. Methods: Among 1,376 long-term care hospitals, frequency analysis and descriptive statistics were used to analyze the characteristics of these hospitals. Multiple linear regression was conducted to examine the associations between infrastructure characteristics, medical personnel characteristics, health outcomes and the proportion of long-term hospitalized patients. Results: The research findings indicate that the number of patients per doctor, the number of patients per nurse, and the number of patients per nursing staff were positively associated with the proportion of long-term hospitalized patients. Among health outcomes, a higher proportion of patients with more than a 5% weight loss compared to the previous month and the proportion of patients showing improvement in ADL, were more likely to have a lower proportion of long-term hospitalized patients. However the proportion of diabetic patients with HbA1c test results within the appropriate range was positively associated with the proportion of long-term hospitalized patients. Conclusion: The present study results provide fundamental data for the establishment of policies for long-term care hospitals. Based on this study, it is important to suggest screening methods for unnecessary long-term hospitalizations, such as sufficient medical personnel to improve the quality of care in long-term care hospitals. It is also necessary to clearly separate the roles of medical institutions and long-term care facilities and implement policies to support patients' social reintegration.

• Korea Journal of Hospital Management
• /
• v.28 no.3
• /
• pp.27-38
• /
• 2023

Objectives: This study explores the impact of age groups on social presence and trust among users of medical artificial intelligence chatbots. Furthermore, we investigate the existence of gender differences within these relationships. Method: We collected data through a survey from people who had interacted with general hospital chatbot services, either by making reservations or seeking consultations. Multiple linear regression analysis was conducted to examine the relationship between general characteristics of study population and social presence and trust of artificial intelligence chatbots. Additionally, we conducted stratified analysis to confirm the presence of gender differences within these relationship. Results: Among 300 participants, those aged 50 and older had higher social presence of artificial intelligence chatbots and greater trust of artificial intelligence chatbots (social presence, 𝛽=0.543, p=0.003; trust, 𝛽=0.787, p=0.000). In stratified by sex, women aged 50 and older had higher social presence and trust of artificial intelligence chatbots compared to those in their 30s age group (social presence, 𝛽 = 0.925, p=0.002; trust, 𝛽=0.645, p=:0.007). However, there was no statistically significant relationship between age and chatbot social presence and trust in men. Conclusion: This study demonstrates that advanced age plays a significant roles in users' social presence and trust in medical artificial intelligence chatbots. Futhermore, our findings reveal gender differences with women aged 50 and older showing the most substantial levels of social presence and trust. Therefore, it is expected that this finding can serve as valuable evidence to enhance the satisfaction of medical institution service users, offering crucial insights into the effective utilization of chatbot services.

• Journal of radiological science and technology
• /
• v.46 no.5
• /
• pp.401-408
• /
• 2023

Thyroid uptake measurements can be subject to measurement errors due to the scoping and positioning of the thyroid gland. To compensate for these limitations, the clinical utility of the thyroid simultaneous counting method as an alternative to thyroid uptake measurement was analyzed and evaluated experimentally through quantitative analysis of images acquired after thyroid scanning. Experimental data were obtained using a Gamma camera (GE infinia), a thyroid uptake system (KOROID 1), and a thyroid neck phantom. Based on the thyroid uptake rate of 1-5% according to the protocol of thyroid scan test (^99mTcO₄ - , 370 MBq) in normal results, ^99mTcO₄ - was set in the range of 3.7-18.5 MBq (Matrix: 256×256, Scan time: 1 min, collimator: pin hole, phantom-collimator distances: 7 cm). The acquired images were corrected for the attenuation of isotopes due to the set-up time and half-life by applying the Auto Region of interest (ROI) drawing system, and the significance of the experimental results was evaluated by Multiple linear regression analysis (SPSS, ver. 22, IBM). The thyroid uptake rate showed a significant correlation between the dose and the measured counts when using the thyroid uptake system equipment. Meanwhile, the quantitative analysis counts of phantom images using Gamma camera also showed a significant correlation. Thus confirmed that the correlation between these two experiments was statistically significant (P<0.05). The simultaneous counting protocol, which indirectly measures thyroid uptake from thyroid scans, is likely to be clinically relevant if complemented by additional studies with different variables in patients with thyroid disease.

• Journal of Korean Critical Care Nursing
• /
• v.16 no.3
• /
• pp.11-23
• /
• 2023

Purpose : This study investigates the experiences of patients in intensive care units (ICUs), and the factors influencing these experiences. Method : We used a cross-sectional survey design to analyze previously collected cohort data from 891 patients who spent over 24 hours in 19 ICUs across four university hospitals in Busan, South Korea between June 2019 and July 2020. Within a week of ICU discharge, participants completed the Korean version of the Intensive Care Experience Questionnaire, covering four areas: "awareness of surroundings," "frightening experiences," "satisfaction with care," and "recall of experiences." We used multiple linear regression to identify factors associated with the ICU experience. Results : Low income (𝛽 = -.08, p = .016), unplanned hospitalization (𝛽 = -.09, p = .006), sedation (𝛽 = -.16, p < .001), and delirium (𝛽 = -.15, p < .001) reduce patients' awareness of their surroundings. Frightening experiences are associated with being female (𝛽 = -.07, p = .027), experiencing delirium(𝛽= -.15, p<.001), and longer stays in the ICU (𝛽= -.14, p <.001). Using sedatives decreases satisfaction with care (𝛽 = -.08, p = .048). Living alone (𝛽 = -.08, p = .013) and using painkillers (𝛽 = -.08, p = .020) reduces recall of experiences. Conclusion : Negative ICU experiences are significantly associated with being female, living alone, lower income, unplanned admission, using sedatives and painkillers, delirium, and longer stays in the ICU. Thus, improving ICU experiences requires interventions that address modifiable factors, such as delirium, medication, and length of ICU stays.

• Korean Journal of Culture and Social Issue
• /
• v.14 no.1_spc
• /
• pp.153-166
• /
• 2008

The purpose of this study was to investigate middle school student's self-directed learning(SDL) using a hierarchical linear modeling. By considering variances of SDL at individual and school level, the student's SDL was explained in terms of school quality as well as individual efforts. For the HLM analysis, participation in private tutoring, teacher's support for SDL, caring students' individual needs, and participation in extra curriculum activities were explored at individual level. At school level, school SES, quality of national curriculum implementation, and parental support for school were utilized. The results of analysis showed that more than 95% of variance of SDL was explained by variables at individual level. Among the variables at individual level, private tutoring was not a significant variable explaining the SDL. Based upon the results, multiple regression analyses by background variables were also conducted. By interpreting the results of analyses, the impact of school quality and individual efforts on the SDL was discussed.

• Nutrition Research and Practice
• /
• v.17 no.5
• /
• pp.969-983
• /
• 2023

BACKGROUND/OBJECTIVES: We investigated the association of plant and animal protein intake with grip strength in Koreans aged ≥ 50 yrs. SUBJECTS/METHODS: The data was collected from 3,610 men and 4,691 women (≥ 50 yrs) from the 2016-2018 Korea National Health and Nutrition Examination Survey. We calculated the total energy intake, and the intake of animal and plant protein and collected dietary data using 1-day 24-h dietary recalls. Low grip strength (LGS) was defined as the lowest quintile (men: up to 26.8 kg, women: up to 15.7 kg). The association of protein intake with grip strength was examined using Pearson's correlation and multiple linear regression analysis. RESULTS: The results proved that participants with LGS had lower daily energy, protein and fat intake, and percent energy from protein than those with normal or high grip strength (P < 0.0001). Total energy intake, animal protein, and plant protein were positively associated with grip strength. A higher intake of total plant protein (P for trend = 0.004 for men, 0.05 for women) and legumes, nuts, and seeds (LNS) protein (P for trend = 0.01 for men, 0.02 for women) was significantly associated with a lower prevalence of LGS. However, non-LNS plant protein intake was not associated with LGS (P for trend = 0.10 for men, 0.15 for women). In women, a higher total animal protein intake was significantly associated with decreased LGS (P for trend = 0.03). CONCLUSIONS: Higher total plant protein and LNS protein intake are negatively associated with LGS.

• The Journal of Korean Academic Society of Nursing Education
• /
• v.30 no.1
• /
• pp.49-60
• /
• 2024

Purpose: The coronavirus disease 2019 (COVID-19) pandemic has had significant physical and psychological impacts on registered nurses (RNs). This study aimed to identify long COVID symptoms and their associated factors specifically among RNs. Methods: This descriptive correlational study's sample comprised 189 nurses (31.57±5.98 years, 93.7% female) in Korea. Self-reported long COVID symptoms were assessed using the COVID-19 Yorkshire Rehabilitation Scale. Data were collected from December 31, 2022, to January 13, 2023, using the online survey method and were analyzed using independent t-test, Wilcoxon signed-rank test, one-way ANOVA, Pearson's correlation, and a multiple linear regression analysis with the IBM SPSS Statistics 26.0 program. Results: A total of 179 participants (94.7%) experienced one or more long COVID symptoms. The most prevalent symptoms were weakness (77.8%), fatigue (68.3%), breathlessness (67.7%), cough/throat sensitivity/voice change (50.3%), and sleep problems (50.3%). The factors related to long COVID symptoms were marital status, type of institution, working time, acute COVID-19 symptoms, and vaccination status. The quarantine period (β=.26, p<.001) and the nursing workforce after COVID-19 (β=-.17, p=.018) were significantly associated with long COVID symptoms (Adjusted R² =.33). Conclusion: Providing comprehensive recognition is necessary for the understanding of long COVID symptoms and their associated factors among nurses and could promote a long COVID symptom management education program targeted at nurses. Moreover, it could facilitate effective nursing care and education plans for long COVID patients.