• Korean Medical Education Review
• /
• v.22 no.2
• /
• pp.99-114
• /
• 2020

The rapid development of artificial intelligence (AI), including deep learning, has led to the development of technologies that may assist in the diagnosis and treatment of diseases, prediction of disease risk and prognosis, health index monitoring, drug development, and healthcare management and administration. However, in order for AI technology to improve the quality of medical care, technical problems and the efficacy of algorithms should be evaluated in real clinical environments rather than the environment in which algorithms are developed. Further consideration should be given to whether these models can improve the quality of medical care and clinical outcomes of patients. In addition, the development of regulatory systems to secure the safety of AI medical technology, the ethical and legal issues related to the proliferation of AI technology, and the impacts on the relationship with patients also need to be addressed. Systematic training of healthcare personnel is needed to enable adaption to the rapid changes in the healthcare environment. An overall review and revision of undergraduate medical curriculum is required to enable extraction of significant information from rapidly expanding medical information, data science literacy, empathy/compassion for patients, and communication among various healthcare providers. Specialized postgraduate AI education programs for each medical specialty are needed to develop proper utilization of AI models in clinical practice.

• Journal of Korean Society for Quality Management
• /
• v.19 no.1
• /
• pp.115-128
• /
• 1991

In korea, since November 1982 these two small group actvity convension (QC circle convension and Factory Saemaul activity small group convension) has been united, many problem have been disclosed that are against the basic principle more or less. Worker's small group activity is essentially, a trouble shooting oriented voluntary small group within their working place to improve the surroundings creatively. In practice. however, many group are so typical and so impetuous of the material effect that it is worried to be inclined to outform rather than contents. Effective small group activities are presumed to be successful only with labor management cooperation on the basis of human-orient management philosophy. The small group activities are also prevalent in service sector. More derivative methods have been developed and more members are willingly participating in training programs. The small group which is basically a horizontal organization unit, promptes communication within the whole organization. In consideration of the social circumstances and traditions, the flexible model of the small group activities suitable to the corporate environment, will contribute industrial development.

• Journal of Community Nutrition
• /
• v.6 no.1
• /
• pp.42-47
• /
• 2004

The purpose of the study was to investigate assisted living residents' perception of foodservice experience using a qualitative approach. A total of 14 residents who lived in assisted living units of a continuing care retirement community participated in interview sessions. The interviews were semi-structured with open-ended questions. The interviews were transcribed and coded to identify themes from the responses. The residents perceived the availability of choices, variety of foods, and service positively, but expressed concerns about food preparation, food quality, and repetitive menus. They were particularly concerned with tough and dry meats. The foodservice department should consider the older residents' ability to chew and their changing taste buds when determining quality of food purchased and preparation methods. The residents considered the service pleasing and described it as satisfactory. They stated that the service staff was friendly but needed more training in proper service techniques. Communication between the foodservice department and the residents was an area to be improved. The foodservice department should increase the residents' involvement in the menu planning and evaluation of the foodservice on a routine basis. Foodservice managers and dietitians working for the older adults can utilize the findings of the study to identify strategies to improve foodservice at their facilities

• Journal of Community Nutrition
• /
• v.6 no.1
• /
• pp.41-47
• /
• 2004

The purpose of the study was to investigate assisted living residents' perception of foodservice experience using a qualitative approach. A total of 14 residents who lived in assisted living units of a continuing care retirement community participated in interview sessions. The interviews were semi-structured with open-ended questions. The interviews were transcribed and coded to identify themes from the responses. The residents perceived the availability of choices, variety of foods, and service positively, but expressed concerns about food preparation, food quality, and repetitive menus. They were particularly concerned with tough and dry meats. The foodservice department should consider the older residents' ability to chew and their changing taste buds when determining quality of food purchased and preparation methods. The residents considered the service pleasing and described it as satisfactory. They stated that the service staff was friendly but needed more training in proper service techniques. Communication between the foodservice department and the residents was an area to be improved. The foodservice department should increase the residents' involvement in the menu planning and evaluation of the foodservice on a routine basis. Foodservice managers and dietitians working for the older adults can utilize the findings of the study to identify strategies to improve foodservice at their facilities.

• International Journal of Control, Automation, and Systems
• /
• v.4 no.5
• /
• pp.637-644
• /
• 2006

Biomedical image is often complex. An applied image analysis system should deal with the images which are of quite low quality and are challenging to segment. This paper presents a framework for color cell image segmentation by learning and classification online. It is a robust two-stage scheme using kernel method and watershed transform. In first stage, a two-class SVM is employed to discriminate the pixels of object from background; where the SVM is trained on the data which has been analyzed using the mean shift procedure. A real-time training strategy is also developed for SVM. In second stage, as the post-processing, local watershed transform is used to separate clustering cells. Comparison with the SSF (Scale space filter) and classical watershed-based algorithm (those are often employed for cell image segmentation) is given. Experimental results demonstrate that the new method is more accurate and robust than compared methods.

• Journal of Korean Academy of Fundamentals of Nursing
• /
• v.11 no.3
• /
• pp.309-316
• /
• 2004

Purpose: The purpose of this study was to identify the perceptions and attitudes of nurses toward euthanasia. Method: In this descriptive study, data were collected from 485 nurses using a self-report questionnaire. The attitudes toward euthanasia scales were composed of four sub dimensions; quality of life, client's right, respect for life and medical ethics. The data were analyzed with descriptive and parametric statistics using SPSS WIN program. Results: Of the nurses, 84.7% were in agreement with constituting a law for euthanasia and 57.6% accepted passive euthanasia. Further, 80.1% would accept euthanasia for their own end-of-life situation. The most frequent reason for pro euthanasia was pain relief, and for con, respect for lift. The mean attitude score was 54.64 and that of sub dimensions, were 2.81 for quality of life, 3.21 for client's right, 2.87 for respect for life, and 2.84 for medical ethics. The nurses who were positive in their thinking about euthanasia had higher attitude scores. Among general characteristics of the nurses, attitudes scores were significantly different according to religion. Conclusion: Although many nurses had a positive concept of euthanasia, they still have ethical dilemmas in lift-sustaining care. Therefore training programs on moral rights are necessary to provide guidelines for end-of-life care.

• Journal of the Korea Society of Computer and Information
• /
• v.20 no.5
• /
• pp.73-81
• /
• 2015

Most of the software fault prediction studies focused on the binary classification model that predicts whether an input entity has faults or not. However the ability to predict entity fault-proneness in various severity categories is more useful because not all faults have the same severity. In this paper, we propose fault prediction models at different severity levels of faults using traditional size and complexity metrics. They are ternary classification models and use four machine learning algorithms for their training. Empirical analysis is performed using two NASA public data sets and a performance measure, accuracy. The evaluation results show that backpropagation neural network model outperforms other models on both data sets, with about 81% and 88% in terms of accuracy score respectively.

• Journal of Fashion Business
• /
• v.18 no.5
• /
• pp.144-158
• /
• 2014

National Competency Standards(NCS) is to systemize the competency that is necessary for performing duties in industrial fields and to utilize synthetically duty, vocational education training, and qualification at the national level. The purpose of this study is to analyze the process of NCS development and verification, which systemizes competency units and competency unit elements through the analysis of duty in pattern field. It is to cultivate competent people to be able to promote the development of pattern industry ultimately through being a complementary to educational circles and industry then to give them practical knowledge that is demanded in the field. Furthermore, it is to be utilized as a fundamental data for reforming the system of duty competency evaluation so as to manage personnel career systematically and to improve their competency. Focus Group Interview(FGI) was adapted as the method of this study, which was proceeded 3 times, and validity of the drawn result is verified through expert questionnaire survey. Research result, which is competency units, is 10 as follows; Fit trend analysis, Analysis of sample garment Specification sheet, Pattern making for sample garment, Pattern making for manufacturing garment, Creation of sewing specification, Instruction of manufacturing technique, Sample garment Inspection for quality control, Grading, Calculation of the required material quantities, Quality control.

• Korean Journal of Health Education and Promotion
• /
• v.29 no.4
• /
• pp.83-99
• /
• 2012

Objectives: The purpose of this review is to introduce reporting guidelines for health promotion research in an effort to enhance systematic structure and quality of health promotion research reported in academic papers. Methods: Widely accepted guidelines were selected for description, which focus on 4 distinct types of research design. Checklists and flow diagrams are described and compared. Results: CONSORT Statement is reporting guidelines for randomized controlled trials with a 25-item checklist and a flow diagram. TREND Statement with a 22-item checklist is to guide reporting of health research in nonrandomized design. STROBE Statement is a compiled guidelines for observational health research, accompanied by a 22-item checklist in a combined edition. PRISMA Statement consists of a 27-item checklist and a flow diagram, providing guidelines for reporting systematic reviews and meta-analyses. All items on the checklists and flow diagrams were introduced and discussed. Conclusion: Solid understanding of research designs and adoption of reporting guidelines will enhance the quality of research with information on internal and external validity. Education and training of researchers on the research reporting is required along with systems level adoption of efforts for research enhancement.

• Proceedings of the Korean Institute of Electrical and Electronic Material Engineers Conference
• /
• 2006.06a
• /
• pp.163-164
• /
• 2006

ZnO deposition parameters are not independent and have a nonlinear and complex properties respectively. Therefore, finding optimal process conditions are very difficult and need to do many experiments. To predict ZnO deposition result, neural network was used. To gather training data, Si, GaAs, and Glass were used for substrates, and substrate temperature, work pressure, RF power were $50-500^{\circ}C$, 15 mTorr, and 180-210 W respectively, and the purity of target was ZnO 4N. For predicting the result of ZnO deposition process exactly, sensitivity analysis and drawing a response surface was added. The temperature of substrate was evaluated as a most important variable. As a result, neural network could verify the nonlinear and complex relations of variables and find the optimal process condition for good quality ZnO thin films.