• Korean Journal of Radiology
• /
• v.22 no.6
• /
• pp.983-993
• /
• 2021

Objective: To investigate the image quality of ultralow-dose CT (ULDCT) of the chest reconstructed using a cycle-consistent generative adversarial network (CycleGAN)-based deep learning method in the evaluation of pulmonary tuberculosis. Materials and Methods: Between June 2019 and November 2019, 103 patients (mean age, 40.8 ± 13.6 years; 61 men and 42 women) with pulmonary tuberculosis were prospectively enrolled to undergo standard-dose CT (120 kVp with automated exposure control), followed immediately by ULDCT (80 kVp and 10 mAs). The images of the two successive scans were used to train the CycleGAN framework for image-to-image translation. The denoising efficacy of the CycleGAN algorithm was compared with that of hybrid and model-based iterative reconstruction. Repeated-measures analysis of variance and Wilcoxon signed-rank test were performed to compare the objective measurements and the subjective image quality scores, respectively. Results: With the optimized CycleGAN denoising model, using the ULDCT images as input, the peak signal-to-noise ratio and structural similarity index improved by 2.0 dB and 0.21, respectively. The CycleGAN-generated denoised ULDCT images typically provided satisfactory image quality for optimal visibility of anatomic structures and pathological findings, with a lower level of image noise (mean ± standard deviation [SD], 19.5 ± 3.0 Hounsfield unit [HU]) than that of the hybrid (66.3 ± 10.5 HU, p < 0.001) and a similar noise level to model-based iterative reconstruction (19.6 ± 2.6 HU, p > 0.908). The CycleGAN-generated images showed the highest contrast-to-noise ratios for the pulmonary lesions, followed by the model-based and hybrid iterative reconstruction. The mean effective radiation dose of ULDCT was 0.12 mSv with a mean 93.9% reduction compared to standard-dose CT. Conclusion: The optimized CycleGAN technique may allow the synthesis of diagnostically acceptable images from ULDCT of the chest for the evaluation of pulmonary tuberculosis.

• Journal of the Korea Convergence Society
• /
• v.7 no.4
• /
• pp.141-154
• /
• 2016

Objectives: The purpose of the study was to identify factors influencing on nursing students' end-of-life care attitude. Methods: A sample of convenience of 147 nursing students, Instrument included death anxiety, death attitude, Self-esteem, Life satisfaction, end-of-life care attitude. Results: A significant negative correlation was found among end-of-life care attitude, death anxiety, death attitude. Death anxiety(${\beta}$=-.392), self-esteem(${\beta}$=.179) & experience of learning(${\beta}$=-.227) about death were significant predictive variables. This variables accounted for 18.7% of the variance in end-of-life care attitude. Conclusions: Based on the Findings of this study, it can be used to develop educational programs for end-of-life care.

• Journal of Biomedical Engineering Research
• /
• v.24 no.2
• /
• pp.99-106
• /
• 2003

In this paper, a method of discriminating EEG for diagnoses of mental activity is proposed. The proposed method for classification of schizophrenia and normal EEG is based on the wavelet transform and the artificial neural network. The wavelet coefficients of $\alpha$ band, $\beta$ band, $\theta$ band, and $\delta$ band are obtained using the wavelet transform. The magnitude, mean, and variance of wavelet coefficients for each EEG band are applied to the input data of the system's ANN. The architecture of the ANN s a four layered feedforward network with two hidden layer which implements the error back propagation learning algorithm. Through the classification of schizophrenia composed of 19 ANNs corresponding to 19 channels, the classifying system show that it can classify the 100% of the normal EEG group and the 86.67% of the schizophrenia EEG group.

• Journal of Korean Society for Quality Management
• /
• v.35 no.2
• /
• pp.37-44
• /
• 2007

Today, the statistical process control (SPC) in manufacture environment is an important role at the process by the productivity improvement of the manufacturing systems. The control chart in this statistical method is widely used as an important statistical tool to find the assignable cause that provoke the change of the process parameters such as the mean of interest or standard deviation. But the traditional SPC don't grasp the change of process according to the points fallen the near control limits because of monitoring the variance of process such as the fixed sampling interval and the sample size and handle the cost of the aspect of these sample point. The control chart can be divided into the statistical and economic design. Generally, the economic design considers the cost that maintains the quality level of process. But it is necessary to consider the cost of the process improvement by the learning effects. This study does the economic design in the VSI $\bar X$ control chart and added the concept of loss function of Taguchi in the cost model. Also, we preyed that the VSI $\bar X$ control chart is better than the FSI $\bar X$ in terms of the economic aspects and proposed the standard of the process improvement using the VSI $\bar X$ control chart.

• Journal of Biomedical Engineering Research
• /
• v.27 no.6
• /
• pp.323-331
• /
• 2006

The purpose of this study was to investigate the effect of performing a cognitive task during treadmill walking on the stride rate variability. Ten university students(age $24.0{\pm}0.25$, height $172{\pm}3.1cm$, weight $66{\pm}5.3kg$) were participated in dual task experiments which consist of both walking alone and walking with a cognitive task. Two-back task was selected for the cognitive task since it did not have learning effect during the experimental procedure.3D motion analysis system was used to measure subject's position data by changing walking speed with 4.8, 5.6, 6.4, 6.8, and 7.2 km/hr. Stride rate was calculated by the time between heel contact and heel contact. Accuracy rate of a cognitive task during walking, coefficient of variance, allometric scaling methods and Fano factor were used to estimated the stride rate variability. As the walking speed increased, accuracy rate decreased and the logarithmic value of Fano factor increased which showed the statistical difference. Thus it can be concluded that the gait control mechanism is distracted by the secondary attention focus which is the cognitive task ie. two-back task. Further study is needed to clarify this by increasing the number of subject and experiment time.

• Journal of Digital Convergence
• /
• v.12 no.6
• /
• pp.415-423
• /
• 2014

The purpose of this study was to investigate the level of multicultural competencies and influencing factors of multicultural competencies in nursing students. The participants of 181 subjects were recruited from three colleges in K and B. A structured questionnaire was used to collect data, and data were analyzed using descriptive statistics, t-test, one way-ANOVA and multiple regression with SPSS/WIN 17.0. Results showed that cultural competence of nursing students was middle range. There was a significant positive correlation between cultural competence, empathy, and self-efficacy. The significant factors influencing cultural competence of nursing students were empathy, self-efficacy, and education of multiple cultural. These three factors explained 51% of the variance in multicultural competencies of nursing students. The study finding suggest that to develop the learning program with achievement level of multicultural competencies for nursing students.

• Human Ecology Research
• /
• v.53 no.2
• /
• pp.119-130
• /
• 2015

In this study, we examined the effects of a mother's reading motivation on the home literacy environment. Seven hundred fifty-seven mothers with three to five year old children participated in this study and completed the Adult Motivation for Reading Scale and the Home Literacy Environment Questionnaire. The subcategories of the Adult Motivation for Reading Scale are "reading as part of self," "reading efficacy," "reading for recognition," and "reading to do well in other realms." The Home Literacy Environment Questionnaire has three subcategories, namely reading books, reading behavior and modeling of parents, and literacy learning. The mean, standard deviation, one-way analysis of variance (ANOVA), and hierarchical multiple regression analysis were used to analyze the data. The results showed that (1) the home literacy environment was significantly different depending on the mother's education and family income levels, (2) the mother's reading motivation also differed significantly depending on the mother's education and family income levels, and (3) the mother's reading motivation has a significant explanatory effect on the home literacy environment. In addition, the mothers falling into the reading motivation subcategories of "reading part of self" or "reading to do well in other realms" were found to enrich their home literacy environment. Therefore, this study demonstrates that the mother's reading motivation is an important factor affecting the home literacy environment.

• The Journal of Korean Academic Society of Nursing Education
• /
• v.22 no.4
• /
• pp.549-558
• /
• 2016

Purpose: The purpose of this study was to develop and validate a Nursing Competency Scale in Simulation (NCSS) for nursing students. Methods: A preliminary version of the NCSS of 14 items was derived from the literature. A panel of seven experts reviewed the preliminary version for content validation and developed 15 items scale. A convenient sample of 195 nursing students completed the survey and two evaluators measured the performances of nine teams in a simulation scenario with NCSS. The data were analyzed using exploratory factor analysis, descriptive statistics, independent t-test and Cronbach's alpha. Intraclass correlation coefficient (ICC) was used in order to estimate the degree of inter-rater reliability. Results: An exploratory factor analysis demonstrated that two factor structures of the NCSS explained 51.1% of the total variance. Two factors were named psychosocial skills and cognitive and psychomotor skills. The mean scores of NCSS between third and 4th grade were significantly different providing support for its known-group validity. Cronbach's alpha was .90 and ranged from .79 to .88. The overall ICC for inter-rater agreement was 0.89 (95% CI 0.03 to 0.98). Conclusion: This scale shows preliminary evidence for validity and reliability. It could be a useful instrument for measuring learning outcome in simulation for nursing students' clinical competency.

• Korean Medical Education Review
• /
• v.18 no.3
• /
• pp.174-179
• /
• 2016

The purpose of this study is to examine the factors that influence school life satisfaction based on personal variables, self-esteem, interpersonal relationships, and perception of the educational environment at a medical school in Korea. The data were collected from 228 medical students who agreed to participate in the study at a medical school. The Dundee Ready Medical Environment Measure (DREEM) and the self-esteem scale by Rosenberg were used. Questions measuring satisfaction of medical school life and interpersonal relationships (with professors, with senior/junior students, and with friends) were asked using a 5 point Likert scale. The data were analyzed by t-test, analysis of variance, and multiple regression analysis. The satisfaction of medical school life of male students was significantly higher than female students and increased with years of schooling. In DREEM, the students' perception of teachers decreased by school years. The relationship with senior and junior students of third year students was higher than other school years. The result of the regression analysis to determine the variables that affect satisfaction of medical school life showed that interpersonal relationships with senior and junior students, the students' social self-perception, and the students' perception of learning were significant. The results of this study will help medical schools in their plans to improve the level of satisfaction for the happiness and successful academic achievements of their students.

• Journal of the Korea Academia-Industrial cooperation Society
• /
• v.14 no.4
• /
• pp.1942-1950
• /
• 2013

This paper suggests a new method of detecting attacks of network traffic by visualizing original traffic data and applying multi-class SVM (support vector machine). The proposed method first generates 2D images from IP and ports of transmitters and receivers, and extracts linear patterns and high intensity values from the images, representing traffic attacks. It then obtains variance of ports of transmitters and receivers and extracts the number of clusters and entropy features using ISODATA algorithm. Finally, it determines through multi-class SVM if the traffic data contain DDoS, DoS, Internet worm, or port scans. Experimental results show that the suggested multi-class SVM-based algorithm can more effectively detect network traffic attacks.