• Journal of the Korean Professional Engineers Association
• /
• v.20 no.3
• /
• pp.15-25
• /
• 1987

Statistical control charts are useful tools to monitor and control the manufacturing processes and are widely used in most Korean industries. Many Korean companies, however, do not always obtain desired results from the traditional control charts by Shewhart such as the X-chart, X-chart, X-chart, etc. This is partly because the quality charterstics of the process are not distributed normally but are skewed due to the intermittent production, small lot size, etc. In Shewhart X-chart, which is the most widely used one in Korea, such skewed distributions make the plots to be inclined below or above the central line or outside the control limits although no assignable causes can be found. To overcome such shortcomings in nonnormally distributed processes, a distribution-free type of confidence interval can be used, which should be based on order statistics. This thesis is concerned with the design of control chart based on a sample median which is easy to use in practical situation and therefore properties for nonnormal distributions may be easily analyzed. Control limits and central lines are given for tile more famous nonnormal distributions, such as Gamma, Beta, Lognormal, Weibull, Pareto, Truncated-normal distributions. Robustness of the proposed median control chart is compared with that of the X-chart, the former tends to be superior to the latter as the probability distribution of the process becomes more skewed. The average run length to detect the assignable cause is also compared when the process has a Normal or a Gamma distribution for which the properties of X are easy to verify, the proposed chart is slightly worse than the X-chart for the normally distributed product but much better for Gamma-distributed products. Average Run Lengths of the other distributions are also computed. To use the proposed control chart, the probability distribution of the process should be known or estimated. If it is not possible, the results of comparison of the robustness force us to use the proposed median control chart based on a normal distribution. To estimate the distribution of the process, Sturge's formula is used to graph the histogram and the method of probability plotting, $X^2$-goodness of fit test and Kolmogorov-Smirnov test, are discussed with real case examples. A comparison of the propose4 median chart and the X chart was also performed with these examples and the median chart turned out to be superior to the X-chart.

• Journal of the Korea Academia-Industrial cooperation Society
• /
• v.15 no.6
• /
• pp.3448-3454
• /
• 2014

Generally existing structure analysis was applied to elastic analysis basically in practice. Considering the nonlinear material and the nonlinear geometric to be a more precise analysis, for this reason, The necessity for a structual analysis have been constantly required. Therefore, after optimization is performed, designed a simple model which is applied the principle of nonlinear in this study, a structural analysis of existing experienced users, have a aims at presenting theory and a method in order to perform anyone the analysis easily. In this study, the proposed model applied to die ribs, Regarding the shear load, less strain and stress was generated but strength was sufficient. The initial strain and stress was reconfigured to fit the size and shape, A hyperstudy in conjunction with Abaqus with nonlinear structural analysis, revealed an acceptable maximum and minimum range of stress and under the conditions of minimum strain, the plate made with a constant increment. In the experimental models, the plate thickness was given a power of 40 Newton, according to the thickness of the press die through an iterative process. When the stress and strain was applied to the die thickness, 7-8mm thickness could be obtained by optimizing.

• Journal of the Korea Academia-Industrial cooperation Society
• /
• v.16 no.3
• /
• pp.1832-1843
• /
• 2015

Recently, since the "Capital Market Consolidation Act" has been effective in 2009, the competition among the securities companies in Korean security market has been fierce. Thus, securities business lately are needed by the market environmental requirements rapidly changed for various strategies. The purpose of this study was to identify the effect of corporate attribute, employee attribute, financial product attribute securities on customer satisfaction, trust with the firm, and usage intention. As the subjects I selected the customer of securities in Seoul in 2014 and conducted survey with questionnaires. Among total 400, I chose 378 as the valid sample by convenience sampling. For the data process, I used SPSS 20.0 I verified the perspective hypotheses after testing reliability and validity of fit by the data process. The results are as following. First, it was shown that the sub-factors of corporate attribute, employee attribute, financial product attribute in securities as ethics, innovation, size, kind, professionalism, ethics, profitability and diversity had significant effect on usage intention. Second, the study confirms that reliability and satisfaction influences customer loyalty as moderate variable. The industrial and academic significance of this study is that it may serve as a useful base date to understand customer behavior and draw new strategies in a financial management environment.

• Sijohaknonchong
• /
• v.26
• /
• pp.93-123
• /
• 2007

Ahn Minyoung's editorial work of gajib(songbook) was the work for realization of artistic ability which had been a pursuit for his life. According to recent excavation of 'Seungpyeonggok' that is another gajib editted by Ah Minyoung, it is found that his editorial work of gajib was began in earlier days. 'Seungpyeonggok' composes 12 pieces of works, and it arranged each piece of work with melody of gagok, respectively. For the size, it is evaluated to 'the smallest gajib' among the left gajib at present. This gajib was composed to celebrate the gathering of Seungpyeonggye which led by Ahn Minyoung. There is Preface which was written by Ahn Minyoung, and the content of preface could be similar to the one in his another gajib 'Geumokchongbu' except some omission, variation, or alternation of content and phrase partly to fit for the character of each gajib. The names of Seungpyeonggye's members are shown in the preface of 'Seungpyeonggok', so it is important material for studying the appearances and activities of the members at that time. The purpose and intention of Seungpyeonggye's gathering was clarified in the preface of 'Seungpyeonggok' was composed to the repertoir of gagok sung at the celebration party. All the collected works are related to Daewongun directly or indirectly in their contents. Because the celebration party of Seungpyeonggye was designed for Daewongun, all the contents are dedication for Dasewongun easily. And the works of 12-pieces previously discussed were found as playing repertoir, 'type of pyeon-ga' which was composed to 8-pieces and 4-pieces identically.

• Journal of the Korea Society for Simulation
• /
• v.15 no.3
• /
• pp.23-30
• /
• 2006

A recommender system for E-commerce site receives information from customers about which products they are interested in, and recommends products that are likely to fit their needs. In this paper, we investigate several methods for large-scale product purchase data for the purpose of producing useful recommendations to customers. We apply the traditional data mining techniques of cluster analysis and collaborative filtering(CF), and CF with reduction of product-dimensionality by use of latent semantic indexing(LSI). If reduced product-dimensionality obtained from LSI shows a similar latent trend of customers for buying products to that based on original customer-product purchase data, we expect less computational effort for obtaining the nearest-neighbor for target customer may improve the efficiency of recommendation performance. From simulation experiments on synthetic customer-product purchase data, CF-based method with reduction of product-dimensionality presents a better performance than the traditional CF methods with respect to the recall, precision and F1 measure. In general, the recommendation quality increases as the size of the neighborhood increases. However, our simulation results shows that, after a certain point, the improvement gain diminish. Also we find, as a number of products of recommendation increases, the precision becomes worse, but the improvement gain of recall is relatively small after a certain point. We consider these informations may be useful in applying recommender system.

• Journal of the Korea Convergence Society
• /
• v.6 no.6
• /
• pp.293-299
• /
• 2015

MOOC (Massive Open Online Course) is an online course aimed at limited participation and open access via the web. There is even the prospect that MOOC may break down the existing university system and open a new horizon of education. However, MOOC is going differently from the first prospect that it would threat the existing higher education institutions. So this study wishes to provide a starting point of discussion that we can produce and utilize MOOC to fit our situation of higher education by revealing the inherent problems of MOOC. MOOC is a basically online education, so that it cannot help inheriting the essential weakness of the existing one: the interaction, supervision and evaluation. The newly added concept 'massive' raises the problem of class size which is the most sensitive part in the field of education. The concept 'open' reverses a customized education because MOOC is a kind of video clips of a lecture for unspecific massive learners. As a conclusion, we predicts that MOOC will be positioned as a higher education service for very prominent learners in self-led learning ability and people who cannot access even traditional online higher education institutions. Also MOOC is highly likely to be used as a means of Flipped Learning in universities. Therefore, considering these points in the future, we need to develop MOOC to suit these targets.

• Transactions of the Korean Society of Mechanical Engineers A
• /
• v.34 no.6
• /
• pp.731-742
• /
• 2010

Modeling of rubber for design or analysis often requires confusing or complex work because there are a large number of constitutive models to be considered. Some models have few material constants, while others have many. Researchers have to prepare and fit extensive experimental data with caution and discretion. In this paper, we first compared some typical rubber models in which deformation was carried out by stretching up to around eight times the original size. We conclude that continuum-based models and chain molecular models can be used in the study of the small deformation in most engineering applications, but chain molecular models are preferred in the study of the large deformations in most biomaterial applications. As discrimination problems, Treloar's patch and cylindrical balloon stick are tested theoretically and numerically for studying bifurcation. In the case of Treloar's patch, by using the Kearsley's equation, we show that bifurcation exists for continuum-based models but not for chain molecular models. Both models show bifurcation in the cylindrical balloon stick. Therefore, in the analysis of the bifurcation of rubber showed that its existence also depends on the constitutive model selected.

• Journal of Environmental Health Sciences
• /
• v.41 no.3
• /
• pp.203-215
• /
• 2015

Objectives: This study was designed to evaluate the filtration efficiencies and pressure drops of five commercial cloth masks (4 plate type, 1 cup type) in comparison to the performance of a class 1 disposable respirator (reference respirator). A further objective was to evaluate the effects of the number of layers and wash treatment independently on filtration efficiencies and pressure drops. Methods: Polydisperse NaCl aerosols were generated in an aerosol chamber and their concentrations were measured by an optical particle counter (OPC) in the size range of $0.3{\sim}10{\mu}m$ (five channels). Results: The filtration efficiencies of the five cloth masks and the reference respirator were D: 9.5%, C: 18.5%, E: 23.6%, A: 28.5%, B: 29.7% and R: 91.1%, respectively, and the pressure drops through them were C, D: 0.8 Pa, E: 1.7 Pa, B: 6.4 Pa, A: 42.7 Pa and R: 19.3 Pa, respectively. The filtration efficiencies of the cloth masks and reference respirator were below the class 1 respirator criterion (${\geq}94.0%$) of the Ministry of Employment and Labor (MOEL) and Ministry of Food and Drug Safety (MFDS). The pressure drops satisfied the class 1 respirator criterion (${\leq}70Pa$) of MOEL and MFDS. When the cloth masks were folded into two and four layers, the filtration efficiencies of cloth masks A, B, C, D (plate type) increased 1.7-4.6 times, and 2.3-6.8 times, respectively, compared to the efficiencies of the same products in a single layer. Pressure drops increased as the number of layers was increased. The filtration efficiency of cloth mask E with a liner was 1.3 times higher than that of the same mask without a liner, and the pressure drop was lower in the no-liner configuration. After a single washing, the filtration efficiencies of all the cloth mask products decreased 1.04-4.0 times compared to those of the same products intact. For the cloth masks C and E, their filtration efficiencies were significantly decreased after washing (p<0.05). The pressure drops of all cloth masks were 1.2-2.0 times lower after washing. Conclusions: The filtration efficiencies of the five cloth masks were below 30% and did not improve greatly by increasing the number of layers. After a single washing, their performances decreased. Considering the above and other issues identified with cloth masks, such as poor fit and stretched fibers through use, people should not expect protection against particulate matters from the cloth masks on the market.

• Journal of Korean Academy of Nursing
• /
• v.31 no.2
• /
• pp.221-231
• /
• 2001

This study was conducted by analyzing all 33 articles based on the LISREL, published from January 1991 to March 1999 in Korea. The analyses consisted of the publication date of articles, principal dependent variables, subjects of the research, adequacy of sampling, adequacy of research purposes and results, accordance between theoretical model and hypothetical model, fit measures, theoretical base of model modification, and adequacy of conclusion. The results were as follows : . The thesis of 33 articles in total were outnumbered as 25 (75.8%) to 8 (24.2%) research articles. As for a sex classification of the subjects, 45.5% of the research were conducted around a female group of subjects, while 54.5% were done for both sex, The range of the sample size was 105 to 803, and the average was 259 subjects. . A single theoretical variable was measured for each measurement variable, any difference between variables was hardly found in 8 articles (24.2%), and 19 articles (57.6%) did not consider any measurement error. To analyze if the representative has been articles (21.2%) were seen with a sign of a representative. Questionnaires were used in a majority (31 articles) of the data collecting process. Only 2 articles (6.1%) were measured with a physiologic index simultaneously. . 14 articles (42.2%) were centered on theory development, 10 articles on theory synthesis, and 9 articles on theory test. The research purposes and results were consistent in 25 articles (75.5%) and 8 articles (24.2%) were inconsistent. The quality of life and health promotion behavior were the concepts most frequently studied as a dependent variable, and 7 articles centered on them. In applied theories a health promotion model was used on 4 articles (12.1%), while role theory and stress-coping models were in 3 articles respectively. . The articles were analyzed to see if the hypothetical model was elaborated and tested by the theoretical model. Twenty-five articles proved to be rationale for the inconsistencies. Also, 56.5% proposed hypotheses were supported among the subject articles, and 30 articles (90.0%) suggested a revised model. Path coefficient (17 articles) and theoretical adequacy (17 articles) were the standards mostly used. In conclusion, the principal factors were obtained from the research are to be considered as the principes of LISREL application. First, a model has to be established on a theoretical base rather than empirical results dependent on the data. The results are also required to be globally interpreted. Secondly, at least 200 samples are necessary to satisfy the need. Third, more than 3 measurement variables are to be adjusted to a single theoretical variable; the measurement errors must be suggested as well. Finally, normal distribution characteristics of the data and the estimation method need to be reported. Based on the research result, the follows are suggested; . Systematic criteria on the LISREL application and procedure need to be developed . Agreement form is required to report the results of research using the LISREL

• Journal of Korea Water Resources Association
• /
• v.49 no.5
• /
• pp.439-450
• /
• 2016

For the design of infrastructures controlling the flood events at ungauged basins, this study tries to find the regional flood frequencies using peak flow data generated by the spatial extension of flood records. The Chungju Dam watershed is selected to validate the possibility of regional flood frequency analysis using the spatially extended flood data. Firstly, based on the index flood method, the flood event data from the spatial extension method is evaluated for 22 mid/smaller sub-basins at the Chungju Dam watershed. The homogeneity of the Chungju dam watershed was assessed in terms of the different size of watershed conditions such as accumulated and individual sub-basins. Based on the result of homogeneity analysis, this watershed is heterogeneous with respect to individual sub-basins because of the heterogeneity of rainfall distribution. To decide the regional probability distribution, goodness-of fit measure and weighted moving averages method from flood frequency analysis were adopted. Finally, GEV distribution was selected as a representative distribution and regional quantile were estimated. This research is one step further method to estimate regional flood frequency for ungauged basins.