• Journal of the Korean Data and Information Science Society
• /
• v.24 no.1
• /
• pp.189-200
• /
• 2013

In this paper, it will be assumed that there are two distinct populations which are multivariate normal with equal covariance matrix. We also assume that the two populations are equally likely and the costs of misclassification are equal. The classification rule depends on the situation whether the training samples include missing values or not. We consider the conditional bootstrap confidence intervals for classification error rate when a block of observation is missing.

• Journal of radiological science and technology
• /
• v.32 no.2
• /
• pp.147-151
• /
• 2009

In general, the discrete confidence judgments that use five-step assessment method have been used to assess the medical images by ROC. TPF or FPF can be computed easily with this independent reading test. However, during experiments, it happens frequently that adequate distribution for observers is required to smoothly estimate the ROC curve. In addition, data becomes invalid for distribution of the created categories. To solve such problems or to apply the ROC interpretation to data that is not obtained from the experimental observation, the continuous confidence judgements (CCJ) has been proposed, which implements ROC interpretation using continuously-distributed experimental results without category classification has been used. As the use of CCJ to assess medical images was barely reported in Korea, we applied it to the assessment of chest digital images in this study. The results showed that a smooth ROC curve was obtained conveniently by the commercialized program and the characteristic value was measured easily. Therefore, it is recommended that this method can be applied to the assessment of digital medical images.

• Journal of muscle and joint health
• /
• v.29 no.1
• /
• pp.41-49
• /
• 2022

Purpose: The purpose of this study was to assess the influence of nurses staffing level on patient health outcomes in intensive care units (ICUs) in Korea. Methods: The study was retrospective in nature. Information on patients and their outcomes, as well as nurse cohort data, were obtained from Korea's National Health Insurance Service Database. The observation period was from January 1, 2008 to December 31, 2018, and data for 2,964,991 patients were analyzed. Independent variables included patient' age and sex and hospital type, intensivist, and nurses staffing level. Results: The mortality rate in ICUs was significantly higher at tertiary hospitals with a level 3~4 (HR, 1.21; 95% confidence interval, 1.19~1.22) or level 5~9 nurse staffing (HR, 1.31; 95% confidence interval, 1.27~1.34) compare to that of tertiary hospitals with a 1~2 level. 28-day mortality rate was also higher at general hospitals with a level 3~4 (HR, 1.13; 95% confidence interval, 1.12~1.14), level 5~6 (HR. 1.34; 95% confidence interval, 1.32~1.36), level 7~9 nurse staffing (HR, 1.38; 95% confidence interval, 1.38~1.42), using level 1~2 as reference. Conclusion: Nurses staffing level is a key determinant of healthcare-associated mortality in critically ICUs patients. Policies to achieve adequate nurse staffing levels are therefore required to enhance patient outcomes.

• The Journal of the Acoustical Society of Korea
• /
• v.16 no.3E
• /
• pp.19-23
• /
• 1997

The goal of postprocessing in automatic speech recognition is to improve recognition performance by utterance verification at the output of recognition stage. It is focused on the effective rejection of out-of vocabulary words based on the confidence score of hypothesized candidate word. We present two methods for computing confidence scores. Both methods are based on the distance between each observation vector and the representative code vector, which is defined by the most likely code vector at each state. While the first method employs simple time normalization, the second one uses a normalization technique based on the concept of on-line garbage mode[1]. According to the speaker independent isolated words recognition experiment with discrete density HMM, the second method outperforms both the first one and conventional likelihood ratio scoring method[2].

• English Language & Literature Teaching
• /
• v.17 no.1
• /
• pp.17-35
• /
• 2011

The purpose of this study was to explore the effect of an explicit word instruction for EFL beginning readers and their perception on the learning experience. Data were attained from 16 fourth graders who took English class as a development activity. Data include the results of pre- and post-test of high frequency sight word recognition, oral reading ability, students' survey responses, and teacher observation. The descriptive statistics were obtained for the result of the pre- and post-test. The findings from the student survey and teacher observation were also provided and interpreted to better understand the result of project and students' perception on the learning experience. The followings are the results of this study. The word recognition ability of the students was dramatically improved after the project. The students were satisfied with the overall learning experience perceiving it as helpful and fun learning. They expressed that the explicit word instruction helped their word recognition and reading ability. The results also supported that the confidence of students on their reading ability were heightened. Several suggestions are made for teachers and researchers on the word instruction for young EFL learners who are beginning readers.

• Communications for Statistical Applications and Methods
• /
• v.10 no.2
• /
• pp.497-505
• /
• 2003

Under normality assumption, the tolerance interval for a future observation is sometimes of great interest in statistics. In this paper, we state the influence function on the standard deviation $\sigma$, and use it to derive the influence function on tolerance limits. Simulation study shows that the two influence functions perform very well.

• Journal of the Korean Data and Information Science Society
• /
• v.13 no.2
• /
• pp.271-284
• /
• 2002

In this paper we consider the robust inference for the parameter of linear regression model based on weighted least squares. First we consider the sequential test of multiple outliers. Next we suggest the way to assign a weight to each observation $(x_i,\;y_i)$ and recommend the robust inference for linear model. Finally, to check the performance of confidence interval for the slope using proposed method, we conducted a Monte Carlo simulation and presented some numerical results and examples.

• Journal of dental hygiene science
• /
• v.8 no.4
• /
• pp.353-359
• /
• 2008

To find out the relationship between the experience of clinical practice and the performance confidence, some 2nd and 3rd grade students in D health college who completed clinical practice in 2008. Sept. were surveyed. The results are as follows. 1. During the clinical practice of the dental hygiene students, the performance experience was highest in the basic prep. part among every part. As for the dental hygiene part, the students showed more than 70%, rather higher performance experience in the following parts: arrangement before and after treatment, suction, basic instruments setup, local anesthesia setup, extraction setup, resin filling setup, temporary filling setup, cements mixing, and ligation and removal setup. 2. As for performance confidence, those with performance experience showed higher performance confidence than those with only observation experience or with no experience in every treatment field except basic prep. (p < 0.001). 3. It was proven that the hygiene students have seldom had performance experience in other treatment parts except in assisting treatment part in clinical practice. In order to improve future performance experience on dental hygiene activities, subsequent research is needed to set more specific and objective criterion about the dental hygiene students' clinical practice.

• The Journal of the Korea Contents Association
• /
• v.19 no.3
• /
• pp.126-137
• /
• 2019

This study is a descriptive research that aimed to investigate the relationship among the knowledge, attitude, self-confidence, and ability to perform basic life support of nursing students, and to identify the factors affecting their performance ability of basic life support. The subjects in this study were 85 senior nursing students. And a questionnaire survey and an observation assessment for their ability to perform basic life support were conducted. The data were analyzed by descriptive statistics, t-test, ANOVA, Pearson's correlation coefficient, Multiple Linear Regression with SPSS WIN 23.0 program. Performance ability on Basic life support was found to be in a significant positive correlation with knowledge, self-confidence. Factors affecting the ability to perform basic life support were knowledge, number of training sessions received, and last training time. Therefore, programs for repetitive basic life support training at 3-month intervals should be developed to maintain the performance ability of basic life support.

• International Journal of Advanced Culture Technology
• /
• v.10 no.1
• /
• pp.180-186
• /
• 2022

This study is a pilot study to confirm the effectiveness of training after applying emergency simulation training for inactive nurses and to present a new model of simulation training operation method. In this study, the control group is a group that directly participates in the simulation activity, and the experimental group is the group that observes the control group's simulation activity. Experimental group and control group were matched 1:1 to experience all the roles of the resuscitation team. The study participants were 5 inactive nurses in the experimental group and 5 inactive nurses in the control group, and the total training time was 5 hours. The emergency simulation operation composition consists of theory education, skill education, and simulation. The interview was conducted. The educational satisfaction of the participants was 4.65 points for theory education and 4.70 points for practical education based on 5 points. Participants' performance confidence improved from 3.60 points before operation to 7.20 points after operation. Emergency simulation operation consisted of pre-test, theory education, skill education, simulation implementation, debriefing, and post-test. Participants expressed that the choice of group greatly reduced the burden and anxiety about performing the role of the resuscitation team. However, difficulties and inexperience in the operation of the defibrillator were reported in the experimental group. The control group reported that the simulation activity of the experimental group was not significantly different from theirs. Through the results of this study, it was confirmed that emergency simulation education not only reduced the burden and anxiety of inactive nurses, but also had an effect of education. Based on the research results, it is proposed to expand the participants and verify the effectiveness of education through specific variables such as learning commitment, learner confidence, simulation satisfaction, and team effectiveness.