• Journal of the Korea Academia-Industrial cooperation Society
• /
• v.19 no.3
• /
• pp.40-45
• /
• 2018

Intelligent monitoring and diagnosis of production processes based on multivariate statistical methods has been one of important tasks for safety and quality issues. This is due to the fact that faults and unexpected events may have serious impacts on the operation of processes. This study proposes a diagnostic scheme based on effective representation of process measurement data and is evaluated using simulation process data. The effects of utilizing a preprocessing step and nonlinear statistical methods are also tested using fifteen faults of the simulation process. Results show that the proposed scheme produced more reliable results and outperformed other tested schemes with none of the filtering step and nonlinear methods. The proposed scheme is expected to be robust to process noises and easy to develop due to the lack of required rigorous mathematical process models or expert knowledge.

• Journal of Korean Society for Quality Management
• /
• v.45 no.1
• /
• pp.25-38
• /
• 2017

Purpose: Hot strip rolling mill consists of a lot of mechanical and electrical units. In condition monitoring and diagnosis phase, various units could be failed with unknown reasons. In this study, we propose an effective method to detect early the units with abnormal status to minimize system downtime. Methods: The early warning problem with various units is defined. K-means and PAM algorithm with Euclidean and Manhattan distances were performed to detect the abnormal status. In addition, an performance of the proposed algorithm is investigated by field data analysis. Results: PAM with Manhattan distance(PAM_ManD) showed better results than K-means algorithm with Euclidean distance(K-means_ED). In addition, we could know from multivariate field data analysis that the system reliability of hot strip rolling mill can be increased by detecting early abnormal status. Conclusion: In this paper, clustering-based monitoring and fault detection algorithm using Manhattan distance is proposed. Experiments are performed to study the benefit of the PAM with Manhattan distance against the K-means with Euclidean distance.

• Journal of Korean Academy of Fundamentals of Nursing
• /
• v.17 no.4
• /
• pp.478-486
• /
• 2010

Purpose: To explore nurses' compliance with standards for critical care nursing practice in intensive care units (ICUs) and to provide basic data for high quality of critical care nursing. Method: A total of 616 participants from 61 ICUs which are graded from 1 to 7 throughout the nation were surveyed. Data were collected from February 9 to February 27, 2009 using a questionnaire consisting of 58 questions including 50 nursing activities as indicators. Results: The rate of ICU nurses' compliance with standards for critical care nursing practice was high. As for individual standards, compliance with the standard of assessment was the highest, followed by implementation, diagnosis, and planning in that order. There were differences in compliance according to nurses' ICU experience, work place (unit), and ICU grade. A shortage of manpower was considered as a main cause for noncompliance. Conclusion: The present compliance rate with standards for critical care nursing practice by ICU nurses was identified. Therefore, compliance rate can be used to promote quality of critical care nursing and development of educational programs for ICU nurses.

• Asian Pacific Journal of Cancer Prevention
• /
• v.14 no.9
• /
• pp.5477-5482
• /
• 2013

Background: Communication plays an important role for the well being of patients, families and also health care professionals in cancer care. Conversely, ineffective communication may cause depression, increased anxiety, hopelessness and decreased of quality life for patients, families and also nurses. Objective: This study aimed to explore communication difficulties of pediatric hematology/oncology nurses with patients and their families, as well as their suggestions about communication difficulties. Materials and Methods: It was conducted in a pediatric hematology/oncology hospital in Ankara, Turkey. Qualitative data were collected by focus groups, with 21 pediatric hematology/oncology nursing staff from three groups. Content analysis was used for data analysis. Results: Findings were grouped in three main categories. The first category concerned communication difficulties, assessing problems in responding to questions, ineffective communication and conflicts with the patient's families. The second was about the effects of communication difficulties on nurses and the last main category involved suggestions for empowering nurses with communication difficulties, the theme being related to institutional issues. Conclusions: Nurses experience communication difficulties with children and their families during long hospital stays. Communication difficulties particularly increase during crisis periods, like at the time of first diagnosis, relapse, the terminal stage or on days with special meaning such as holidays. The results obtained indicate that pediatric nurses and the child/family need to be supported, especially during crisis periods. Feeling of empowerment in communication will improve the quality of care by reducing the feelings of exhaustion and incompetence in nurses.

• The Korean Nurse
• /
• v.29 no.1
• /
• pp.59-71
• /
• 1990

Although the usefulness and importance of clinical application of nursing diagnosis are well recognized by the academic circle, it is not yet generally practiced. In order to provide data for establishing a policy for clinical nursing diagnosis; a study was made at a seminar, sponsored by the Department of nursing, Severance Hospital, with participation of 190 nurses from 33 hospitals. The objective of the study was to find out; 1) if the nurses agree with the academic community in recognizing the benefits and problems of clinical application of nursing diagnosis; 2) how the nurses evaluate their ability to carry out nursing diagnosis; and 3) if educational programs would help enhance ability of nursing diagnosis among nurses. The summary of findings by the study is as follows; 1. While all nurses responded positively on the question of benefits improving science and quality of nursing, thus elevating credibility and position of nurses, some expressed concern on the practicality of the system in setting up nursing objectiveness, confirming the nursing problems and utilizing patient information. For the 20 questions and the scale of 1~5, the lowest average score was 3.223 and the highest 4.066. 2. The study attempted to find out the opinion of the nurses on the problems that 'would make difficult to adopt the nursing diagnosis in clinics. The result of the study indicates the nurses believe the major problems are the fact that the subject of nursing diagnosis are not well defined and that the form sheets do not match with the ones that are currently being used. However, comparing it with the result of the previous study on the same question (inadequate manpower and insufficienf time allocated for the job were two major problems pointed out then.), it can be said that the opinion of the nurses studied this time was much more positive and it suggests that they believe the system can be adopted without increasing manpower and only by giving additional training and by adjusting the format of nursing record sheets. It suggests that the future for adopting a clinical nursing diagnosis is very bright. 3. As the most urgent problem to be solved for adopting clinical nursing diagnosis, 38. 5% responded that it was "education of nurses, "and 34.2% responded that it was "staffing adequate number of nurses". 4. For the 10 questions asked for self-evaluation of ability to adopt the system, with the scale of 1~5, average score was lower than 3. This indicate that they evaluate their ability to adopt the system is low. 5. The results of study taken before and after the educational programs for clinical nursing diagnosis were compared with overall score in order to determine if such program would cause changes in the response to the effect of clinical application of nursing diagnosis, and it was found that there was statistically significant changes suggesting that the education contributed to positive change in the response. 6. The results of study taken before and after the educational programs for clinical nursing diagnosis were compared with overall score in order to determine how the proble~ ms for adopting nursing system would be effected by such educational programs, and it was found that those problems be not soived with a short course of training. 7. The results of study taken before and after the educational programs for clinical nursing diagnosis were compared with overall score in order to determine if such programs would bring changes in the self-evaluation of nurses on the ability of nursing diagno sis, and it was found that program improve score of self-evaluation their ability of the nursing diagnosis. As seen in the above reports, it was found that the nu'rses are very positive about the clinical nursing diagnosis, that educational program for the clinical nursing diagnosis helps nurses for positively changing their attitude for ,the nursing diagnosis, for their self-confidence on their ability to perform nursing diagnosis. With improved know-how and self"confictence of nurses gained through educational and .training programs, the future of clinical application of nursing diagnosis is very bright.diagnosis is very bright.

• Quality Improvement in Health Care
• /
• v.11 no.1
• /
• pp.46-60
• /
• 2004

Background : Recently, we have experienced various changes in the healthcare environment. Healthcare organizations are facing a financial crisis due to more competitive relationships among themselves as well with low health insurance fees. The purposes of the current study were: (1) to develop a data warehouse-based system for evaluating and monitoring the case management activities, and (2) to measure and analyze its effects. Methods : In order to collect the data for the study, the database on discharged patients was utilized at a university hospital located in Seoul from June 1, 2002 through December 31, 2002. Initially, a data warehouse was built for the case management system. The case management activities were analyzed using structured methodology to establish the case management system. Results : The findings of this study were as follows: (1) A case management system was developed to make it possible to monitor of healthcare quality and resource utilization. The Case management System included monitoring functions regarding utilization reviews, critical pathways, and clinical indicators. (2) Utilizing the case management system, unplanned readmissions were documented among total discharged patients during two months from November 1, 2002 through December 31, 2002. The unplanned readmission rate was 2.3%(276 patients) in total of 11,960 discharged patients. Among them 81 patients(0.7% of total discharges, 29.3% of unplanned readmission) were readmitted to the same physician in charge under the same diagnosis. No significant differences were found in the demographic variables such as gender and age among the patients. (3) After implementing the case management system, 2.9% of average length of stay reduced. Applying cost-benefit analysis, the 2.9% reduction of length of stay represents net profit of ${\backslash}$ 279,592,000 in the year of 2004. In addition, applying value acceleration analysis, cumulative net benefit of ${\backslash}$ 1,481,000,000 was expected by the year of 2007. Also we were able to expect ${\backslash}$ 247,800,000 of cumulative benefit for the prospective 5 years in value linkage analysis. It represents average ${\backslash}$ 787,700,000 of pure net benefit a year. Conclusion : The value of present study would be not only implementing the knowledge management system into the existing case management activities, but also evaluating its effects and estimating its financial benefits. This study suggested that the case management system would be a supportive tool for monitoring and improving the quality of healthcare, and a cost-effective tool for increment of healthcare organization's financial benefit.

• Child Health Nursing Research
• /
• v.6 no.2
• /
• pp.249-261
• /
• 2000

The purpose of this study were to identify the quality of life for the mothers of hospitalized chronic pediatric patients, and to explore the factors affecting the QOL of those mothers. The subjects were 201 mothers whose children had hospitalized at one University hospital with chronic diseases. Data were collected from the December, 1997 to December, 1998. We used a revised QOL instrument consisting of 34 items, 5 point likert scale based on the Noh's QOL instrument. The revised QOL consists of six subscales, those are physical status and function, self esteem, emotional status, economic status, relationship with family members, and relationship with neighborhood. Data were analyzed by t-test, ANOVA, Pearson's correlation using SPSS-PC. The results were as follows: 1. The mean score of quality of life for the mothers of chronic pediatric patients was 100.31, and item mean was 2.95. In subscale analysis, item mean of economic status was the lowest, and that of relationship with family members was the highest. 2. Correlations between characteristics of chronic pediatric patients, their mothers and QOL of mothers were as follows; 1) Total QOL of mothers had a significant positive relationship with progressing time relapse after diagnosing and age of mothers. There was a significant negative relationship between the total QOL of mothers and number of hospitalization of their children. 2) QOL on self esteem and economic status had a significant relationship with age of pediatric patients, the time relapse after diagnosis, and age of mothers. Total number of family members and QOL on economic status showed a significant positive relationship. QOL on emotional status, economic status, and relationship with family members of mothers showed negative correlations with the number of hospitalization of their children. 3. Followings were the result of difference in QOL among different demographic cha- racteristics of the subjects. 1) QOL on economic status of mothers was significantly higher when fathers of pediatric patients had jobs. 2) Total QOL score, QOL on emotional status, and QOL on relationship with neighborhood were significantly higher when mothers of pediatric patients had spouses. 3) QOL on self esteem of mothers was significantly higher when mothers had religion. 4. Followings were the result of difference in QOL among different diagnosis of the children. 1) Total QOL score of mothers whose children had congenital heart disease was higher than that of mothers whose children had leukemia and cancer. 2) QOL on emotional status, economic status, and relationship with family members of mothers whose children had congenital heart disease were higher than those of mothers whose children had leukemia, cancer, and epilepsy.

• Journal of the Korea Academia-Industrial cooperation Society
• /
• v.14 no.12
• /
• pp.6455-6460
• /
• 2013

Learner modeling forms the foundations for intelligent tutoring systems that provide adaptive and active learning guidance for learning and education quality enhancement. The aim of this study was to develop learner modeling technologies to form the foundation of intelligent tutoring systems. Specific research tasks include learner modeling building techniques, diverse learner state diagnosis methods and educational data mining.

• Journal of the Korean Society of Industry Convergence
• /
• v.6 no.4
• /
• pp.379-386
• /
• 2003

The goal of this research is to develop a Heel/Side Laster and control GUI(Graphic User Interface) for adaptive manufacturing. For this purpose, we have analyzed the working sequences of heel/side laster, and developed a control program that will facilitate the machineries with functions that are suitable for adaptive manufacturing. We also made it possible to modify the gluing path with simple manipulation of CAD data. By providing a user-friendly GUI, we made it possible for unskilled workers use the system without difficulty. In addition, we have developed a flexible environment where the already available CAD data can be modified and saved with ease. Automatic feeding and path control algorithms for thermoplastic cement were also implemented. By using the Heel/Side Laster for adaptive manufacturing, we are able to achieve increased productivity and work efficiency while improving the quality of the product with self-diagnosis and fine adjustment function.

• International Journal of Reliability and Applications
• /
• v.10 no.1
• /
• pp.1-15
• /
• 2009

Even though the impact of manufacturing quality to reliability is not considered much as well as that of design area, a major cause of an early failure of the product is known as manufacturing problem. This research applies two different types of neural network algorithms, the Back propagation (BP) algorithm and Learning Vector Quantization (LVQ) algorithm, to identify and classify the nonrandom variation pattern on the control chart based on knowledge-based diagnosis of dimensional variation. The performance and efficiency of both algorithms are evaluated to choose the better pattern recognition system for auto body assembly process. To analyze hundred percent of the data obtained by Optical Coordinate Measurement Machine (OCMM), this research considers an application in which individual observations rather than subsample means are used. A case study for analysis of OCMM data in underbody assembly process is presented to demonstrate the proposed knowledge-based pattern recognition system.