• Journal of the Korean Society for Aeronautical & Space Sciences
• /
• v.36 no.12
• /
• pp.1186-1192
• /
• 2008

The reliability of gas turbine engine blades was studied. Yield strength, Young’s modulus, engine speed and gas temperature were considered as statistically independent random variables. The failure probability was calculated using five different methods. Advanced Mean Value Method was the most efficient without significant loss in accuracy. When random variables were assumed to have normal, lognormal and Weibull distributions with the same means and standard deviations, the CDF of limit state equation did not change significantly with the distribution functions of random variables. The normalized sensitivity of failure probability with respect to standard deviations of random variables was the largest with gas temperature. The effect of means and standard deviations of random variables was studied. The increase in the mean of gas temperature and the standard deviation of engine speed increased the failure probability the most significantly.

• Journal of Korean Society for Atmospheric Environment
• /
• v.18 no.2
• /
• pp.113-126
• /
• 2002

This study was carried out to evaluate the temporal (daily, weekly, and seasonal) variations of volatile organic compounds (VOCs) concentrations at a road-side site in a heavy-traffic central area of Metropolitan Taegu. Ambient air sampling was undertaken continuously for 14 consecutive days in each of four seasons from the spring of 1999 to the winter of 2000. The VOC samples were collected using adsorbent tubes, and were determined by thermal desorption coupled with GC/MS analysis. A total of 10 aromatic VOCs of environmental concern were determined, including benzene, toluene, ethylbenzene, m＋p-xylenes, styrene, o-xylene, 1,3,5-trimethylbenzene, 1,2,4-trimethylbenzene, and naphthalene. Among 10 target VOCs, the most abundant compounds appeared to be toluene (1.5 ∼ 102 ppb) and xylenes (0.1 ∼ 114 ppb), while benzene levels were in the range of 0.3 ∼6 ppb. It was found that the general trends of VOC levels were significantly dependent on traffic conditions at the sampling site since VOC concentrations were at their maximum during rush hours (AM 7∼9 and PM 7 ∼9). However, some VOCs such as toluene, xylenes, and ethylbenzene were likely to be affected by a number of unknown sources other than vehicle exhaust, being attributed to the use of paints, and/or the evaporation of solvents used nearby the sampling site. In some instances, extremely high concentrations were found for these compounds, which can not be explained solely by the impact of vehicle exhaust. The results of this study may be useful for estimating the relative importance of different emission sources in large urban areas. Finally, it was suggested that the median value might be more desirable than the arithmetic mean as a representative value for the VOC data group, since the cumulative probability distribution (n=658) does not follow the normal distribution pattern.

• Journal of Preventive Medicine and Public Health
• /
• v.29 no.1 s.52
• /
• pp.27-41
• /
• 1996

This study described methods to predict human health risk associated with exposure to environmental carcinogens using animal bioassay data. Also, biological assumption for various dose-response models were reviewed. To illustrate the process of risk estimate using relevant dose-response models such as Log-normal, Mantel-Bryan, Weibull and Multistage model, we used four animal carcinogenesis bioassy data of chloroform and chloroform concentrations of tap water measured in large cities of Korea from 1987 to 1995. As a result, in the case of using average concentration in exposure data and 95% upper boud unit risk of Multistge model, excess cancer risk(RISK I) was about $1.9\times10^{-6}$, in the case of using probability distribution of cumulative exposure data and unit risks, those risks(RISK II) which were simulated by Monte-Carlo analysis were about $2.4\times10^{-6}\;and\;7.9\times10^{-5}$ at 50 and 95 percentile, respectively. Therefore risk estimated by Monte-Carlo analysis using probability distribution of input variables may be more conservative.

• The Journal of Engineering Geology
• /
• v.17 no.3
• /
• pp.483-494
• /
• 2007

The properties of fracture system on road-cut slopes along the Busan-Ulsan express way under construction are investigated and analyzed. Fracture spacing distributions show log-normal form with extension fractures and negative exponential form with shear fractures. Straight line segments in log-log plots of cumulative fracture length indicate a power-law scaling with exponents of -1.13 in site 1, -1.01 in site 2 and -1.52 in site 3. It is likely that the stability and strength of rock mass are the lowest in site 1 as judged from the analyses of spacing, density and inter-section of fractures in three sites. In contrast, the highest efficiency of the fracture network for conducting fluid flow is seen in site 3 where the largest cluster occupies 73% through the window map. Based on the field survey data, this study modified weighting values of the RMR system using a multiple regression analysis method. The analysis result suggests a modified weighting values of the RMR parameters as follows; 18 for the intact strength of rock; 61 for RQD; 2 for spacing of discontinuities; 2 for the condition of discontinuities; and 17 for ground water.

• The Korean Journal of Applied Statistics
• /
• v.33 no.1
• /
• pp.25-46
• /
• 2020

This paper presents ordinal probit semiparametric regression models using Bayesian Spectral Analysis Regression (BSAR) method. Ordinal probit regression is a way of modeling ordinal responses - usually more than two categories - by connecting the probability of falling into each category explained by a combination of available covariates using a probit (an inverse function of normal cumulative distribution function) link. The Bayesian probit model facilitates posterior sampling by bringing a latent variable following normal distribution, therefore, the responses are categorized by the cut-off points according to values of latent variables. In this paper, we extend the latent variable approach to a semiparametric model for the Bayesian ordinal probit regression with nonparametric functions using a spectral representation of Gaussian processes based BSAR method. The latent variable is decomposed into a parametric component and a nonparametric component with or without a shape constraint for modeling ordinal responses and predicting outcomes more flexibly. We illustrate the proposed methods with simulation studies in comparison with existing methods and real data analysis applied to a Korean National Health and Nutrition Examination Survey (KNHANES) 2016 for investigating nonparametric relationship between smoking behavior and coffee intake.

• Journal of Korean Society of Coastal and Ocean Engineers
• /
• v.19 no.2
• /
• pp.105-112
• /
• 2007

Sediment transport model based on the Lagrangian concept considering the grain size distribution(GSD) was setup and the change of the sediment diffusion range was analysed in the condition of considering and not considering the GSD. The GSD curve is assumed as the Log-normal distribution function in order to consider the GSD with respect to the Lagrangian concept and the random numbers, i.e. sediment particles, are generated based on the distribution function. The sediment particles is assumed as the spherical type and the random numbers based on the sediment weight is converted to the sediment diameters. Sediment transport patterns are analysed by the settling simulation, in which the settling velocity is computed by the van Rijn formulae and the horizontal diffusion coefficient is used as the constant parameter. The diffusion patterns are very similar to the patterns with GSD condition. The diffusion range defined as the range including 90%, 99% sediment weight of the total sediment weight, however, is larger than without considering GSD condition in 90%-option and shorter than with considering GSD condition in 99-option, respectively. The diffusion range is defined as tile p-percentage of the cumulative sediment weight region with reference to the 50% region, 90%- option, 99%-option, respectively.

• The Korean Journal of Applied Statistics
• /
• v.33 no.4
• /
• pp.395-407
• /
• 2020

Most classification accuracy measures for optimal threshold are divided into two types: one is expressed with cumulative distribution functions and probability density functions, the other is based on ROC curve and AUC. Unal (2017) proposed the index of union (IU) as an accuracy measure that considers two types to get them. In this study, ten kinds of accuracy measures (including IU) are divided into six categories, and the advantages of the IU are studied by comparing the measures belonging to each category. The optimal thresholds of these measures are obtained by setting various normal mixture distributions; subsequently, the first and second type of errors as well as the error sums corresponding to each threshold are calculated. The properties and characteristics of the IU statistic are explored by comparing the discriminative power of other accuracy measures based on error values.The values of the first type error and error sum of IU statistic converge to those of the best accuracy measures of the second category as the mean difference between the two distributions increases. Therefore, IU could be an accuracy measure to evaluate the discriminant power of a model.

• Journal of Distribution Science
• /
• v.14 no.4
• /
• pp.117-125
• /
• 2016

Purpose - As consumers' needs for purchasing fresh and safe food have been bigger in Korea, their interest in local food is also growing recently. So, the number of local food stores has been increased from 3 in 2012 to 103 in 2015. Local food stores should operate a business responding consumers' needs in order that local food stores are not to be a one-time fad. Therefore, the purpose of this study is to analyze the characteristics of consumers who use a local food store and provide helpful implications to design a strategy for sustainable growth of local food store. Research design, data, and methodology - In this study, Probit model was used for empirical analysis in order to examine the effect of purchase choice attributes of agricultural products, consumer's satisfaction, and their demographic factors upon the intention to use a local food store. After estimating coefficients of the probit model, marginal effects were calculated as a standard normal, and cumulative distribution is differentiated with respect to explanatory variables. To collect the data, questionnaire survey was carried out with the consumers using the local food store (Youngjin Nonghyup near to Jeonju city located in Jeollabuk-do). Result - The data analysis found that the more consumers are satisfied with local food store, the higher intention they have to use the local food store. In addition, it was known that the factors related to quality of agricultural products and shopping convenience among the purchase choice attributes have a considerable impact on the purchase intention of a local food store. In demographic factors, income was turned out to be an important factor affecting purchase intention of local food. Such a result supports the hypothesis that high income consumers are likely to purchase local food, which is based on the inference that consumers who have a high income tend to pursue wellbeing life. Futhermore, information delivery, through a reputable media source among general factors, was known to play an important role in forming an intention to purchase local food. According to the analysis of marginal effects, probability of purchase intention of a local food store is increased by 11.4%, if a monthly average income of a household is above 4.5 million Won(Korean currency). If purchasing satisfaction with local food stores is high, the probability of purchase intention would be increased by 24.1%. Likewise, such a probability goes up by 8.7%, 5.8%, respectively as an increasing one unit of quality of agricultural products and shopping convenience of local food stores, respectively. Conclusion - For attaining sustainable growth in a local food store, it is considered necessarily to establish a proper store operation system to meet consumers' needs, especially for quality and shopping convenience of local food. Moreover, as it was found that appropriate communication through media source has a positive effect on the intention to use local food store, PR activity seems to be necessary to expand the consumers' demands for local foods.

• Journal of Intelligence and Information Systems
• /
• v.17 no.4
• /
• pp.227-240
• /
• 2011

New concepts and ideas often result from extensive recombination of existing concepts or ideas. Both researchers and developers build on existing concepts and ideas in published papers or registered patents to develop new theories and technologies that in turn serve as a basis for further development. As the importance of patent increases, so does that of patent analysis. Patent analysis is largely divided into network-based and keyword-based analyses. The former lacks its ability to analyze information technology in details while the letter is unable to identify the relationship between such technologies. In order to overcome the limitations of network-based and keyword-based analyses, this study, which blends those two methods, suggests the keyword network based analysis methodology. In this study, we collected significant technology information in each patent that is related to Light Emitting Diode (LED) through text mining, built a keyword network, and then executed a community network analysis on the collected data. The results of analysis are as the following. First, the patent keyword network indicated very low density and exceptionally high clustering coefficient. Technically, density is obtained by dividing the number of ties in a network by the number of all possible ties. The value ranges between 0 and 1, with higher values indicating denser networks and lower values indicating sparser networks. In real-world networks, the density varies depending on the size of a network; increasing the size of a network generally leads to a decrease in the density. The clustering coefficient is a network-level measure that illustrates the tendency of nodes to cluster in densely interconnected modules. This measure is to show the small-world property in which a network can be highly clustered even though it has a small average distance between nodes in spite of the large number of nodes. Therefore, high density in patent keyword network means that nodes in the patent keyword network are connected sporadically, and high clustering coefficient shows that nodes in the network are closely connected one another. Second, the cumulative degree distribution of the patent keyword network, as any other knowledge network like citation network or collaboration network, followed a clear power-law distribution. A well-known mechanism of this pattern is the preferential attachment mechanism, whereby a node with more links is likely to attain further new links in the evolution of the corresponding network. Unlike general normal distributions, the power-law distribution does not have a representative scale. This means that one cannot pick a representative or an average because there is always a considerable probability of finding much larger values. Networks with power-law distributions are therefore often referred to as scale-free networks. The presence of heavy-tailed scale-free distribution represents the fundamental signature of an emergent collective behavior of the actors who contribute to forming the network. In our context, the more frequently a patent keyword is used, the more often it is selected by researchers and is associated with other keywords or concepts to constitute and convey new patents or technologies. The evidence of power-law distribution implies that the preferential attachment mechanism suggests the origin of heavy-tailed distributions in a wide range of growing patent keyword network. Third, we found that among keywords that flew into a particular field, the vast majority of keywords with new links join existing keywords in the associated community in forming the concept of a new patent. This finding resulted in the same outcomes for both the short-term period (4-year) and long-term period (10-year) analyses. Furthermore, using the keyword combination information that was derived from the methodology suggested by our study enables one to forecast which concepts combine to form a new patent dimension and refer to those concepts when developing a new patent.

• Journal of Korean Academy of Fundamentals of Nursing
• /
• v.9 no.2
• /
• pp.190-200
• /
• 2002

Purpose; The purpose of this study was to develop an instrument to measure sexual satisfaction in Korean adults. Method: Development of items for the instrument was done by a collecting, reorganizing, reducing and selecting process based on the literature. A total of 19 items were selected in this process. For evaluation of the appropriateness of the 19 items, questionnaires were given to an expert group consisting of 18 professionals (7 men and 11 women). Eighteen items having a response of 70% in 'very good' item or 'good' item were included as items for the instrument. With these 18 items, a 5 point Likert scale was developed, and reliability and validity tests of the scale were done. The subjects for the test were 1,127 Korean adults living in 11 areas in Korea, Data were collected from Dec. 1, 2000 to Feb. 28, 2001 and analyzed with SPSS/PC+ 10.0 program. Item analysis and factor analysis were used to assess the reliability and validity of the scale. Chronbach alpha and corrected item-total correlation were obtained to verify internal consistency, and principal component analysis with the varimax rotation was used to identify structure validity of the developed tool. Result: Reliability of the scale was .9503 and corrected item-total correlations of the items were distributed from .5208 to 7899. As a result of the factor analysis, the items were categorized into three factors. The cumulative variance of the three factors was 67.1%, and all of the variances of the factors were above 5%. Because factor 1 (8 items) indicated a special feeling of psychological satisfaction with sexual activity, it was named 'psychological factor'. Factor 2 (8 items) indicated a feeling of satisfaction in the interaction with sexual partner through communication and variation, therefore it was named 'interactional factor'. Factor 3 (2 items) was about the frequency and duration of sexual intercourse and indicated physical dimensions of satisfaction, so it was named 'physical factor'. The average score for sexual satisfaction of the 1,127 subjects was 65.32 (${\pm}12.71$), and histogram of the score showed a normal distribution with skewness - .425. Conclusion: Finally, a Korean Sexual Satisfaction Scale(KSSS) was accepted as a 5 point Likert scale with 18 items after the statistical test for reliability and validity. In conclusion, KSSS is a useful instrument which is valid and reliable can be used to understand the sexuality of Korean adults.