• International journal of advanced smart convergence
• /
• v.10 no.1
• /
• pp.1-11
• /
• 2021

Document page segmentation is an important step in building a quality optical character recognition module. The study examined already existing work on the topic of page segmentation and focused on the development of a segmentation model that has greater functional significance for application in an organization, as well as broad capabilities for managing the quality of the model. The main problems of document segmentation were highlighted, which include a complex background of intersecting objects. As classes for detection, not only classic text, table and figure were selected, but also additional types, such as signature, logo and table without borders (or with partially missing borders). This made it possible to pose a non-trivial task of detecting non-standard document elements. The authors compared existing neural network architectures for object detection based on published research data. The most suitable architecture was RetinaNet. To ensure the possibility of quality control of the model, a method based on neural network modeling using the RetinaNet architecture is proposed. During the study, several models were built, the quality of which was assessed on the test sample using the Mean average Precision metric. The best result among the constructed algorithms was shown by a model that includes four neural networks: the focus of the first neural network on detecting tables and tables without borders, the second - seals and signatures, the third - pictures and logos, and the fourth - text. As a result of the analysis, it was revealed that the approach based on four neural networks showed the best results in accordance with the objectives of the study on the test sample in the context of most classes of detection. The method proposed in the article can be used to recognize other objects. A promising direction in which the analysis can be continued is the segmentation of tables; the areas of the table that differ in function will act as classes: heading, cell with a name, cell with data, empty cell.

• Journal of Preventive Medicine and Public Health
• /
• v.47 no.1
• /
• pp.64-71
• /
• 2014

Objectives: Physical activity behavior begins to decline during adolescence and continues to decrease throughout young adulthood. This study aims to explain factors that influence physical activity behavior in a sample of female adolescents using a health promotion model framework. Methods: This cross-sectional survey was used to explore physical activity behavior among a sample of female adolescents. Participants completed measures of physical activity, perceived self-efficacy, self-esteem, social support, perceived barriers, and perceived affect. Interactions among the variables were examined using path analysis within a covariance modeling framework. Results: The final model accounted for an $R^2$ value of 0.52 for physical activity and offered a good model-data fit. The results indicated that physical activity was predicted by self-esteem (${\beta}$=0.46, p<0.001), perceived self-efficacy (${\beta}$=0.40, p<0.001), social support (${\beta}$=0.24, p<0.001), perceived barriers (${\beta}$=-0.19, p<0.001), and perceived affect (${\beta}$=0.17, p<0.001). Conclusions: The findings of this study showed that the health promotion model was useful to predict physical activity behavior among the Iranian female adolescents. Information related to the predictors of physical activity behavior will help researchers plan more tailored culturally relevant health promotion interventions for this population.

• Korean Journal of Health Education and Promotion
• /
• v.27 no.4
• /
• pp.123-129
• /
• 2010

Objectives: The aim of this study is to seek an effective way to support smoking cessation by analyzing any change to the pattern of nicotine dependence according to the change in time. Methods: The study was conducted with 800 male smokers who had participated in smoking cessation programs at public health centers from July 16, 2005 to July 15, 2008. Latent growth curve modeling approach was used for data analysis. Results: From the developmental trajectory of individual nicotine dependence, while nicotine dependence of smokers with high nicotine dependence in the first year was slightly decreased in the third year, smokers with low nicotine dependence in the year showed dramatically lower nicotine dependence in the third year. Compared with those who did not successfully quit smoking, the initial value of nicotine dependence of those who successfully quit smoking in the first and the second year was low. Over the years, nicotine dependence was decreased. Conclusion: From this study it was demonstrated that nicotine dependence was reduced through the practice of smoking cessation and reduced nicotine dependence was a factor which affects successful smoking cessation. These results indicate that multiple attempts to quit smoking finally reduces nicotine dependence. Reduced nicotine dependence is likely to increase the possibility of successful smoking cessation.

• The Korean Journal of Health Service Management
• /
• v.10 no.1
• /
• pp.143-154
• /
• 2016

Objectives : The aim of this study was to validated the effectiveness of the information gap in work and daliy life satisfaction. Additionally, this study attempted to verify the mediating effect of self-esteem. Methods : The study examined 327 students who participated in a study on the PSWCI 1st Wave by KCOMWEL. Data were analyzed through descriptive statistics using the reliability test in SPSS 22.0 Ver. Moreover, hypothesis testing was analyzed with covariance based on structure equation modeling (CB-SEM) using Amos 21.0 Ver. Results : The low information gap has a positive effect on satisfaction with work and daily life. Additionally, self-esteem also has a positive effect on each satisfaction measure. However, self-esteem does not have a mediating effect between information gap and each satisfaction measure. Conclusions : The results of the study found the factor of effect on effect factor on beneficiary's satisfaction of industrial accident compensation insurance. Therefore, new ways need to be found that reduce the information gap and increase self-esteem.

• Journal of Preventive Medicine and Public Health
• /
• v.40 no.6
• /
• pp.454-460
• /
• 2007

Objectives : Obesity is currently an epidemic in Korea, and sleep duration is thought to be one of the risk factors for obesity. The objective of this study was to test the hypothesis that short sleep duration is associated with obesity in Korean adults. Methods : The data from the 2001 Korean National Health and Nutrition Survey were used, and 6,174 subjects aged $18{\sim}80$ years were included in the analysis. Sleep duration was measured using information obtained from self-reported questionnaires. Obesity, the main outcome variable, was measured according to body mass index. Multiple regression modeling was used to adjust for potential confounding variables. Results : The study results revealed a negative association between sleep duration and body mass index among Korean adults. These associations persisted after controlling for the potential confounding variables. Conclusions : These findings support the hypothesis that sleep duration is associated with obesity in Korean adults. In addition, these observations support earlier experimental sleep studies and provide a basis for future studies on weight control intervention by increasing the amount of sleep.

• The Korean Journal of Health Service Management
• /
• v.13 no.4
• /
• pp.163-177
• /
• 2019

Objectives: The purpose of this study was to identify the predictors of quality of life (QOL) for terminal cancer patients admitted into the community health center, and to establish a hypothetical model to explain and verify causative relationships among the variables. Methods: Data were collected from January 2015 to June 2016. Participants were 237 registered patients in Busan Metropolitan City hospice & palliative care center. The descriptive and correlation statistics were analyzed using the SPSS/WIN 24.0, and the structural equation modeling procedure was performed using the AMOS 24.0 program. Results: The results of this study showed that the physical symptoms of terminal cancer patients were the most direct factors affecting the QOL, and satisfaction with health care services has a direct effect on the QOL. Conclusions: The study contributes to drawing up measures to improve QOL for terminally ill cancer patients who are living in the end-of-life section of the community by revealing the causal relationship to the QOL for terminal cancer patients.

• Korean Journal of Community Nutrition
• /
• v.29 no.3
• /
• pp.199-211
• /
• 2024

Objectives: Online grocery shopping has gained traction with the digital transformation of retail. This study constructs a behavioral model combining values, attitudes, and reasons for behavior-specifically, facilitators and resistance-to provide a more novel discussion and further understand the relative influences of the various factors affecting continuance intention in online grocery shopping. Methods: Data were collected through an online questionnaire from consumers who had engaged in online grocery shopping during the past month in Seoul, Korea. All collected data were analyzed using descriptive analysis, and model validation was performed using partial least squares structural equation modeling. Results: Continuance intention is primarily driven by facilitative factors (compatibility, relative advantage, and ubiquity). Attitude can also positively influence continuance intention. Although resistance factors (price, tradition, and risk) do not significantly affect continuance intention, they negatively affect attitude. Values significantly influence consumers' reasoning processes but not their attitude. Conclusions: These findings explain the key influences on consumers' online grocery shopping behavior in Seoul and provide additional discussion and literature on consumer behavior and market management. To expand the online grocery market, consumers should be made aware of the potential benefits of the online channel; the barriers they encounter should be reduced. This will help sustain online grocery shopping behavior. Furthermore, its positive impact on attitude will further strengthen consumers' continuance intention.

• Journal of the Korean Society of Surveying, Geodesy, Photogrammetry and Cartography
• /
• v.25 no.2
• /
• pp.117-131
• /
• 2007

Representation of building internal space is an active research area as the need for more geometrically accurate and visually realistic increases. 3 dimensional representation is common ground of research for disciplines such as computer graphics, architectural design and engineering and Geographic Information System (GIS). In many cases CAD plans are the starting point of reconstruction of 3D building models. The main objectives of building reconstruction in GIS applications are visualization and spatial analysis. Hence, CAD plans need to be preprocessed and edited to adapt to the data models of GIS SW and then georeferenced to enable spatial analysis. This study automated the preprocessing of CAD data using AutoCAD VBA (Visual Basic Application), and the processed data was topologically restructured for further analysis in GIS environment. Accuracy of georeferencing CAD data was also examined by comparing the results of coordinate transformation by using digital maps and GPS measurements as the sources of ground control points. The reconstructed buildings were then applied to visualization and network modeling.

• Health Policy and Management
• /
• v.22 no.4
• /
• pp.497-521
• /
• 2012

Objectives This study aimed to investigate the effect of social capital, health risk behavior and health status on medical care utilization by the elderly. The data and Research method Data were obtained from the 4th wave survey of the Korea Welfare Panel Study. 4,087 household members aged 65 years and over were subject to analysis. Descriptive statistics are used to describe the basic features of the data in a study. we performed a structural equation modeling(SEM) analysis to evaluate the effect of social capital and mediating effect of health risk behavior and health status. Results Results showed that factors related to medical care utilization of the elderly were different depending on types of service (inpatient and outpatient service) except health status. Age, higher social capital, more health-risk behavior and poorer health status were associated with increased use of inpatient service. Social capital was found to have a positive direct effect on it. Also, social capital had an indirect effect on reducing use of inpatient services by improving health status. On the other hand, lower age and higher household income tended to increase use of outpatient service, while higher social capital and higher health status were inversely related. Social capital had a direct effect and an indirect effect on reducing use of outpatient service and, at that time, health status played a mediating role. Conclusions Social capital may contribute to improve health status and indirectly reduce medical care utilization of the elderly by enhancing their health status. These results provide evidence that more policy and strategy considerations should be needed for the elderly to strengthen their social capital in order to enhance their levels of health and more efficient utilization of medical care.

• Journal of Environmental Health Sciences
• /
• v.43 no.4
• /
• pp.307-313
• /
• 2017

Objectives: Chemicals derived from various environment media contaminates food across the food supply chain. In Korea, levels of contaminants in food have been sporadically measured by monitoring programs of different government agencies. There is difficulty with data compilation and integrated analysis across media. Therefore, the aim of this study was to propose an overall integrated database and analytical platform design for the 'ECO-FOOD NET (Environmental COntaminant reduction platform for FOOD through an interagency collaboration NETwork)', a tool to support the reduction of environmental contaminants in food. Methods: We developed a new data structure and standardized protocols for the compilation of integrated data. In addition, we conducted subject-oriented logical and physical relational database modeling and created the architecture design of the platform. Results: We established a standardized code system related to exposure media and route, analysis method and food matrix. In addition, we designed the seven software modules of 'About the System', 'Introduction to Interagency Work', 'Media-Chemicals Profiles', 'Method Bank', 'Monitoring Data Base', 'Integrated Media Analysis', and 'Risk-Benefit Analysis'. Conclusions: This study will contribute to decision-making as a tool for executing risk management, such as sustainable reduction policies of contaminants in food.