• Journal of Korea Society of Industrial Information Systems
• /
• 제7권1호
• /
• pp.42-49
• /
• 2002

In this paper, we develop the Bayesian multiple comparison procedure for the normal model. The procedure which we suggest is based on the fractional Bayes factor of O'Hagan (1995). We apply our procedure to normal populations, when noninformative prior is assumed to the model parameters. We derive explicit form of Bayes Factors when the number of populations is greater than 3. A famous data is analyzed by the proposed procedure. For this example, the suggested method is straightforward for specifying distributionally and to implement computationally, with output readily adapted for required comparison.

• The Journal of the Korea Contents Association
• /
• 제16권12호
• /
• pp.574-590
• /
• 2016

This research aims to examine the effects of various types of social comparison in SNS on users' life satisfaction. For this, this research posited four types of social comparison including upward contrast, upward identification, downward contrast and downward identification that might affect SNS users' life satisfaction. Several other factors including demographic variables, SNS usage time, offline social capital and social comparison orientation as control variables were taken into account and the moderating effects of social comparison orientation in the relationships between four types of social comparison and users' life satisfaction was also examined. An online survey was employed for collecting data and the date collected were analyzed with hierarchical regression analysis. The results showed that ages and marriage status have influences on SNS users' life satisfaction. It was proven that the degrees to which SNS users participate in family activities and club/group activities in which they are interested have correlations with their life satisfaction. The findings also revealed that only upward contrast and upward identification among four types of social comparison have influences on the life satisfaction and there is the moderating effect of social comparison orientation on the relationship between upward identification and life satisfaction. On the basis of the results, the necessity of new perspectives in understanding social comparison experience in SNS as compared to the existing literature were discussed.

• Journal of the Ergonomics Society of Korea
• /
• 제31권1호
• /
• pp.247-254
• /
• 2012

Objective: The objective of the study is to analyze adult men's somatotype characteristics, age range from 20s to 50s comparing the direct anthropometric measurement values and to provide the basis information for developing clothing patterns. Background: The comparative study among the age groups is very fundamental to understand the body characteristics of each subjects group. Therefore, comparison of body measurements in age groups was applied in this study. Method: The anthropometric data from the $5^{th}$ Anthropometry of Size Korea(2004) and $6^{th}$ Anthropometry of Size Korea(2010) were applied for the data analysis. Results: As a result, the chest depth/chest width index(the value of chest depth divided by chest width) was increased and the waist depth/waist width index was decreased in all age groups. In addition, the hip depth/hip width index was decreased in age of 20's and 50's. This means that the chest width and hip width were decreased and the waist width were increased. From the data of the 5th Size Korea, the obese men(BMI: 25~30) in the 50s showed the highest percentage of 47.1%, and 44.8% of obese men(BMI: 25~30) in the 40s recorded the highest rate base on the data of the 6th Size Korea. Conclusion: It is concluded that the some differences were showed between the 5th anthropometric data and the 6th data. In particular, obesity tendencies of men in their 20's and 30's were observed significantly compared to other age groups. Application: These findings from the study can be utilized men's wear design and construction that reflect body characteristics.

• Journal of the Institute of Electronics and Information Engineers
• /
• 제54권5호
• /
• pp.90-96
• /
• 2017

Due to the merit of having wide range with low cost, HF radar's ship detection and tracking research as maritime surveillance system has been recently studied. Many ship detection and tracking algorithms have been developed so far, however, performance comparison cannot be conducted properly because the states of target ships (such as moving path, size, etc.) differ from each study. In this paper, we propose a simulator based on compact HF radar, which generates data according to the size and moving path of target ship. Given the generated data with identical ship state, it is possible to conduct performance comparison. In order to validate the proposed simulator, the simulated data has been compared with real data collected by the SeaSonde HF radar sites. As a result, it has been shown that our simulated data resembles the real data. Therefore, the performance of various detection or tracking algorithms can be compared and analyzed respectively by using our simulated data.

• Journal of the Korean Data and Information Science Society
• /
• 제23권4호
• /
• pp.757-764
• /
• 2012

This research is for comparison of test statistics for homogeneity when the data is collected based on complex sample design. The survey data based on complex sample design does not satisfy the condition of independency which is required for the standard Pearson multinomial-based chi-squared test. Today, lots of data sets ara collected by complex sample designs, but the tests for categorical data are conducted using the standard Pearson chi-squared test. In this study, we compared the performance of three test statistics for homogeneity between two populations using data from the 2009 customer satisfaction evaluation survey to the service from Gyeongsangnam-do regional offices of education: the standard Pearson test, the unbiasedWald test, and the Pearsontype test with survey-based point estimates. Through empirical analyses, we fist showed that the standard Pearson test inflates the values of test statistics very much and the results are not reliable. Second, in the comparison of Wald test and Pearson-type test, we find that the test results are affected by the number of categories, the mean and standard deviation of the eigenvalues of design matrix.

• Journal of the Korea Institute of Military Science and Technology
• /
• 제21권2호
• /
• pp.173-179
• /
• 2018

Estimating reliability of a non-repairable system using the degradation data, variance assumption such as homogeneity (constant) or heteroscedasticity (time-variant) could affect accuracy of reliability estimation. This paper showed reliability estimation and comparison results under normal conditions using accelerated degradation data obtained from destructive measurements, according to variance assumption of the data at each measurement time. Degradation data from three accelerated conditions with stress factors of temperature and humidity were used to estimate reliability. The $B_{10}$ lifetime was estimated as 1243.8 years by constant variance assumption, and 18.9 years by time-variant variance. And variance assumption provided different analysis results of important stresses to reliability. Thus, accurate assumption of variance at each measurement time is required when estimating reliability using degradation data of a non-repairable system.

• Journal of the Korea institute for structural maintenance and inspection
• /
• 제23권4호
• /
• pp.120-130
• /
• 2019

In this study, based on the correlation between traffic volume data and vertical displacement data developed in previous research using the bridge maintenance big data of 2006, the vertical displacement estimation model using the traffic volume data of Gwangan Bridge for 10 years A comparison of the performance of the developed model with the current applicability is presented. The present applicability of the developed model is analyzed that the estimated displacement is similar to the actual displacement and that the displacement estimation performance of the model based on the structured regression analysis and the principal component analysis is not significantly different from each other. In conclusion, the vertical displacement estimation model using the traffic volume data developed by this study can be effectively used for the analysis of the behavior according to the traffic load of Gwangan Bridge.

• Journal of the Korea Academia-Industrial cooperation Society
• /
• 제13권11호
• /
• pp.5025-5032
• /
• 2012

The purpose of this study is to compare the working memory and the phonological awareness between Children with multi-cultural families and general families. The research subjects were 15 multi-cultural and 15 general primary school students who were attending 1st-3rd grade in D city. Working memory tested K-TTFC-2 by standardized tool. Phonological awareness abilities was considering the age of the subjects, tested phoneme awareness. Data process was conducted by t -test and frequency test in SPSS program. The results were as follows. First, working memory comparison of both groups showed significant differences. Especially had significant difference in chapter 1, chapter 4. Second, comparison of phonological awareness between both groups showed significant statistic differences. Third, the Phonological awareness comparison of both groups showed that there are differences in sound matching(word medial coda), substituting middle sound in monosyllabic words, phoneme switching. This research result is considered that can be used as the fundamental data for the development of the therapy data considering the working memory and the phonological awareness of children with multi-cultural families.

• Biomedical Science Letters
• /
• 제16권1호
• /
• pp.19-24
• /
• 2010

We analyzed and compared the concentration of total cholesterol (CHOL), high density lipoprotein (HDL) cholesterol, low density lipoprotein (LDL) cholesterol and triglyceride (TG) in serum and the serum protein electrophoresis fractions of thyroid disease patients. In comparison with the average of reference, our data showed that the average concentration of CHOL, LDL cholesterol and TG in hyperthyroidism patients were decreased significantly, but HDL cholesterol was increased significantly. In hypothyroidism patients, CHOL, HDL cholesterol, LDL cholesterol and TG were all increased significantly. In comparison of the concentration of lipids in each patient to reference range, 28.3% of hyperthyroidism patients showed abnormally low level of total cholesterol. In the patients with hypothyroidism, the percentage of patients showed abnormally high level of CHOL, HDL cholesterol, LDL cholesterol and TG were 37.7%, 10%, 68.8% and 49.1%, respectively. In our studies of serum protein electrophoresis, the average of ${\alpha}_2$-globulin and $\gamma$-globulin in hyperthyroidism patients were increased and $\beta$-globulin was decreased significantly. In hypothyroidism patients, the average of $\gamma$-globulin was increased and $\beta$-globulin was decreased significantly. In comparison of protein fractions of each patient to reference range, 38.3% and 50.0% of hyperthyroidism patients showed abnormally high levels of ${\alpha}_2$-globulin and $\gamma$-globulin, but 73.3% of patients showed abnormally low level of $\beta$-globulin. In hypothyroidism patients, 70.4% of patients were abnormally decreased in $\beta$-globulin and 63.9% of patients were abnormally increased in $\gamma$-globulin. These data suggest that the concentrations of CHOL, HDL cholesterol, LDL cholesterol and TG are not critical data for clinical interpretation of hyperthyroidism, but the levels of them are useful for interpretation of hypothyroidism patients. Our results of serum protein electrophoresis suggest that the concentration of serum protein electrophoresis fractions can be useful to understand the thyroid disease.

• International Journal of Advanced Culture Technology
• /
• 제9권3호
• /
• pp.131-141
• /
• 2021

The present study is following a series of research investigations on design resources coming from collected data referring to users' awareness and preferences. The aim of this research is to test the Healthcare Environmental Color Index as a basis for practitioners in the field of healthcare design. An array of color samples selected from previous research, have been presented to the respondents via an online survey, in order to identify the preferences of the two groups on the relation between environmental color and health. As a result of the first experiment and through the comparison of processed data, the maximum percentage of respondents from each group is validating the relation between environmental color and health. For the second experiment we intend to highlight the patterns of color preferences for each group, and thus to test the color samples healing function. The compared data also showed a higher awareness of Koreans than Romanians on the potential of color applied to healing environment. Last but not least in the third experiment we show the top five color samples preferred by each group. It is significant that the comparison of the results validated once more some of our previous findings related to the healthcare environment, such as: the general preference for the green hue (associated to fatigue relax according to color psychology) and the blue hue (sedation release effect) but also the yellow hue - associated to bright energy. Three out of the top five preferred color samples have been identical to both groups while the other two samples have shown characteristic variations. These results show that similarities are strong and can be used in a glocal design strategy as an accessible tool for any practitioner. Based on the Healthcare Environmental Color Index and users' preferences analysis, a new design culture for healthcare can be established and developed.