• ETRI Journal
• /
• v.45 no.3
• /
• pp.448-461
• /
• 2023

This article performs a detailed data scrutiny on a chronic kidney disease (CKD) dataset to select efficient instances and relevant features. Data relevancy is investigated using feature extraction, hybrid outlier detection, and handling of missing values. Data instances that do not influence the target are removed using data envelopment analysis to enable reduction of rows. Column reduction is achieved by ranking the attributes through feature selection methodologies, namely, extra-trees classifier, recursive feature elimination, chi-squared test, analysis of variance, and mutual information. These methodologies are ranked via Technique for Order of Preference by Similarity to Ideal Solution (TOPSIS) using weight optimization to identify the optimal features for model building from the CKD dataset to facilitate better prediction while diagnosing the severity of the disease. An efficient hybrid ensemble and novel similarity-based classifiers are built using the pruned dataset, and the results are thereafter compared with random forest, AdaBoost, naive Bayes, k-nearest neighbors, and support vector machines. The hybrid ensemble classifier yields a better prediction accuracy of 98.31% for the features selected by extra tree classifier (ETC), which is ranked as the best by TOPSIS.

• Journal of Welding and Joining
• /
• v.5 no.1
• /
• pp.57-63
• /
• 1987

A method which can be used for evaluating slag detachability is proposed in this study. The proposed method was intended to get an absolute value for slag detachability, to give consistent value for a given welded joint, and finally to be simple to test. With a test fig made in this study, an impact by dropping a steel ball (13Kg in weight) is applied on the back side of an as-welded plate having a slag layer on the weld bead. Such impact applied forces the slag to drop off from the bead surface. In order to make a quantitative evaluation the amount of slag removed was measured with increasing the number of drops. Using this method six kinds of fluxes were evaluated in terms of the effects of flux type, basicity and weding variables on the slag detachability. As an initial result of this test, it was found that welding heat input affects the detachability significantly. Most importantly the evaluation made using the presently proposed method gives the same order of ranking as that of the actual practice done by a welder.

• Journal of Navigation and Port Research
• /
• v.34 no.7
• /
• pp.595-601
• /
• 2010

This paper aims to diagnose the strategy execution ability and to provide corresponding measures for Korean oceanic shipping companies. The analysis method is the t-test between importance awareness and Corresponding ability for strategy execution diagnosis index(XPP). According to the diagnosed results, the strategy development is unsatisfactory because the strategy implemented does not adhere to concurrent environmental change. Moreover, the execution of the strategy is also unsatisfactory. Therefore, an evaluation shows that there is a need for a SWOT analysis using BSC, an organization structure to strengthen the strategy execution ability and the support from the market condition analysis prediction center.

• Korean Journal of Human Ecology
• /
• v.2 no.2
• /
• pp.49-62
• /
• 1999

The purpose of this study is to evaluate the combination of details on the maternity clothes of one-piece type through visual evaluation which helps compensating pregnant women＇s body defects for their more attractive fashion styles. The data evaluated by a multiple ranking test were analyzed by mean, paired t-test, general linear models procedure and Duncan＇s multiple ranged test. The result are as follows : 1) The pregnant woman wearing the one-piece dress with notched collar, pleats and whole button looks longer in lower part of bodies, smaller in upper body, slimmer, have less appeared bust and abdomen, more balanced as a Whole than when wearing others. And also, it makes a pregnant woman be seen more refined and simple. 2) In case of a pregnant woman, a one-piece dress with notched collar, tuck and whole button makes her look longer in neck, narrower in shoulder, and more active than when wearing others. 3) With roll collar, pleats and whole button, it looks taller and more graceful than when wearing others.

• Fibers and Polymers
• /
• v.6 no.2
• /
• pp.162-168
• /
• 2005

A methodology for the objective evaluation of water repellency is studied using image analysis of the sprayed pattern on woven fabrics according to a standard spray test (AATCC Test Method 22-2001). The wet area ratio obtained from the spray standard test ranking is found to be exponentially related with its water repellency rating. Mean filtering is used to remove the effect of weave texture and the transmitted light through interyarn spaces. The ring frame of the instrument and wet region are recognized using Otsu thresholding technique. And Hough transform and outline operation are used to obtain the size and position of the ring frame. The objective assessment of the water repellency using image processing can reduce unnecessary confusion in the subjective determination of the water repellency.

• Journal of The Korean Association For Science Education
• /
• v.22 no.2
• /
• pp.345-356
• /
• 2002

This study investigated the trends in the number of applicants and mean score and applicants' responses on the test items of 'science inquiry' of the College Scholastic Ability Test(CSAT) implemented for 3 years$(1999\;{\sim}2001)$. The results of this study were as follows: The percentage of applicants of science track for 1995 CSAT were 43.13%, but reduced to 29.5% for 2001 CSAT. And unlike other tracks, the percentage of male applicants, ranking above average, of science track was 65.58%, which is about twofold of female applicants(34.42%). The mean score of 'Science inquiry' was 58.6 in 1999, and 69.5 in 2001. And the score of the applicants, ranking above average, of humanity and social science course and science course, were 85.8 and 90.7 respectfully in 2001 CSAT. These high mean scores were caused by the policy of "easy CSAT" so called. Most of test items were developed to have difficulty 60-79% or above 80%. This easy CSAT provoked intense dispute about the discriminating power of CSAT. The mean score of male applicants was higher than that of female. But the difference decreases every year. Applicants were generally very good at solving tests focusing on process skills only but poor at solving tests related to physics or calling for two or more science concepts. Thus special measures to cope with the decrease in applicants, especially female applicants, for science track should be provided. To increase discriminating power of CSAT, it is recommended to develop test items with wider range of difficulty and to reduce test items which are focussing process skills and can be solved without any special science concepts. And special consideration should be given to teaching the content area with poor achievement and high actual difficulty compared to the expected.

• KOREAN JOURNAL OF CROP SCIENCE
• /
• v.61 no.2
• /
• pp.92-97
• /
• 2016

This experiment aimed to compare the sensory ability of experts and untrained to evaluate three rice varieties by using five sensory evaluation methods. All panelists showed significant differences in their sensory abilities to distinguish among Haiami, Chucheong, and Dasan 1 rice varieties when using the duo-trio test and triangle test. The expert panelists showed a clear preference in the following order: Haiami > Chucheong > Dasan 1, when using the paired comparison test, ranking test, and multiple comparison test. However, the untrained panelists showed no significant differences in their sensory ability to distinguish between the Haiami and Chucheong varieties when using the multiple comparison test. The results indicate that, for sensory evaluation of cooked rice by untrained panelists, the paired comparison test is suitable for evaluating two samples and the ranking test is suitable for evaluating more than two samples.

• Journal of the Korea Society of Computer and Information
• /
• v.25 no.9
• /
• pp.37-44
• /
• 2020

AI technology has developed in the form of decision support technology in law, patent, finance and national defense and is applied to disease diagnosis and legal judgment. To search real-time information with Deep Learning, Big data Analysis and Deep Learning Algorithm are required. In this paper, we try to predict the entrance rate to high-ranking universities using a Deep Learning model, RNN(Recurrent Neural Network). First, we analyzed the current status of private academies in administrative districts and the number of students by age in administrative districts, and established a socially accepted hypothesis that students residing in areas with a high educational fever have a high rate of enrollment in high-ranking universities. This is to verify based on the data analyzed using the predicted hypothesis and the government's public data. The predictive model uses data from 2015 to 2017 to learn to predict the top enrollment rate, and the trained model predicts the top enrollment rate in 2018. A prediction experiment was performed using RNN, a Deep Learning model, for the high-ranking enrollment rate in the special education zone. In this paper, we define the correlation between the high-ranking enrollment rate by analyzing the household income and the participation rate of private education about the current status of private institutes in regions with high education fever and the effect on the number of students by age.

• Journal of the Korean Society of School Health
• /
• v.7 no.2
• /
• pp.135-143
• /
• 1994

This study is aimed at providing basic information necessary to set up education program and strategies to prevent high school students from smoking by school health care service. The main groups of study are 814 third-grade male students, 557 parents and 362 teachers, who were randomly chosen at 8 high schools in Seoul. Date analysis consisted of Chi-square test and percentage. The findings of the study are as follows: 1. The less interesting family life is, the more increasing current smoking rate is, (ex-smoking rate 53.5%, re-smoking rate 40.3%, current smoking rate 24.3%) 2. According th the results of $x^2$-test for the school life and the smoking, the students above ranking 41 showed th increase as 48.7% for continuous smoking, 18.9% for re-smoking, 67.6% for the present smoker. But it turned out that the students belonged to ranking 10 were not experienced the smoking. So it showed that there was a correlation between score and smoking. 3. It is noted that 93.3% of students, 93.3% of parents and 96.1% of teachers recognize harmful effect of smoking. But less than 70% those have recognized only half of all smoking knowledge. 4. There is a significant difference in the contends and types of education between parents and teachers. 5. For the time of home education and school health education to prevent the smoking, it turned out that 44.9% of students, 42.4% of parents, and 47.4% of teachers considered the optimal time as a high school' days. In addition it appeared that 40.5% of students, 33.4% of parents, and 54.6% of teachers recognized the necessity of the early education before the elementart school. For the optimal time to begin school health education, it showed that the middle school days were indicated from 56.6% of students, 52.7% of parents, the elementary school days were 54.6% of parents, the elementary school days were 54.6% of teachers.

• Health Policy and Management
• /
• v.13 no.4
• /
• pp.1-27
• /
• 2003

The purpose of this study was to develop the evaluation indicator for the health promotion programs of the Community Health Centers and to test its validity. The modified logic model was used as the evaluation model based on the literature reviews. Using this model, four dimensions, eleven sub­dimensions, and forty­one individual indicators were developed. These evaluation indicators are superior in reflecting the distinctiveness of the community health promotion programs, and also flexible enough to accommodate diverse programs. These indicators also emphasize the role of process evaluation, and the diversity of outcomes. To test content validity, survey method of experts in the community health promotion field was conducted. Eleven in three expert groups(professionals, practitioners in Community Health Centers, and policy makers) generally agreed with the validity of evaluation indicators. To examine criteria and construct validity, these indicators were used to evaluate the health promotion programs conducted by the 18 Key Community Health Centers. The data came from the interview surveys of the main health promotion practitioner and 30 visitors from each center. The ranks of these eighteen Community Health Centers were computed from these data. There was no significant difference in ranking either by these indicators or by the existing indicators, which was developed by Technical Support and Evaluation Team for criteria validity. There was no statistically significant difference in ranking between input, process and outcome dimensions. Based on these study results, evaluation indicators developed in this study are valid to evaluate Community Health Center's health promotion program. It can be used both by the Community Health Center for internal evaluation, and by the stakeholders for external evaluation.