• Journal of KIISE:Software and Applications
• /
• v.26 no.11
• /
• pp.1282-1287
• /
• 1999

통신 프로그램은 고도의 신뢰성과 기능성, 확장성, 그리고 유지 보수성이 필요하다. 프로그램 테스트의 결과와 McCabe의 Complexity를 측정한 데이타를 가지고 회귀모델을 만들고 그 신뢰성을 분석함으로서 프로그램의 결함과 복잡도의 관련성을 평가한다.본 연구에서 사용한 통신 프로그램은 500개 블록이 59가지 기능을 수행하는 교환 기능 중에서 복잡도가 너무 많아서 통계 처리의 bias가 될 블록을 제외하고 394 블록을 선정하여 SAS에 의해서 통계 분석을 하고 회귀 분석 모델을 설계하였다. t 분포에 의하여 방정식의 유의성 수준을 검증하고 프로그램의 결함수에 가장 큰 영향을 주고 있는 복잡도가 McCabe의 복잡도와 설계 복잡도 임을 밝혀냈다. 이 연구 결과에 의해서 설계 정보 및 유지 보수 정보를 얻을 수 있다. Abstract Switching software requires high reliability, functionality, extendability and maintainability. For doing, software quality model based on MaCabe's complexity measure is investigated. It is experimentally shown using regression analysis the program fault density depends on the complexity and size of the function unit. The software should be verified and tested if it satisfies its requirements with automated analysis tools. In this paper we propose the regression model with the test data.The sample program for the regression model consists of more than 500 blocks, where each block compose of 10 files, which has 59 functions of switching activity.Among them we choose 394 blocks and analyzed for 59 functions by testing tools and SAS package. We developed Regression Analysis Model and evaluated significant of the equation based on McCabe's cyclomatic complexity, block design complexity, design complexity, and integration complexity.The results of our experimental study are that number of fault are under the influence of McCabe's complexity number and design complexity.

• Journal of Korean Clinical Health Science
• /
• v.2 no.2
• /
• pp.148-157
• /
• 2014

Purpose. This study compares and analyzes customer service on customer satisfaction and customer royalty on customer satisfaction targeting the customers visiting a hospital or a clinic which is franchised or not. And it aims at helping business rationalization for a medical institution. Methods. This paper conducts a survey and selects a sample of 670 customers except the missing value targeting the customers of 4 primary health care institutions and 4 bigger health care institutions in Seoul and Gyeonggi province. It conducts frequency analysis for the purpose of investigating the respondents' generic characteristic and factor of their medical institution selection, and factor analysis, reliability analysis and regression analysis for the hypothesis testing. Results. The first hypothesis testing result is significant in level of significance of 0.01. The second one is the same as the first one, but the dummy variable shows a negative regression coefficient(-0.479). The third one is significant in level of significance of 0.01, but the forth one is not significant. And the respondents prioritize website(Home page) and convenience in use of a hospital procedure for selecting a hospital or a clinic. Conclusions. The additional analysis finds that the franchised group has more satisfaction than none franchised group. But in case of their royalty, the average of franchised and none franchised groups are not significantly different. Therefore, the results of this paper reveal to support the results of the advanced researches.

• The KIPS Transactions:PartD
• /
• v.12D no.2 s.98
• /
• pp.283-288
• /
• 2005

Test case prioritization methods schedule test cases for execution when we can not practically run all test cases for regression testing. We proposed a new prioritization method that is based on historical execution and mr detection data. And we conducted an experiment to compare the proposed method with existing Random and LRU methods using the fault age under the long run environment as criterion. The experiment shows several interesting results. First, our results show that they are complementary. Random method shows good performance for programs that have many error-detectable test cases and HED is more effective for the programs that can be detected by very small amount of test cases. But LRU is more effective for the programs that have relatively medium amount of error detectable test cases. Next, the performance of prioritization method is affected by the size of test suites. Two experiments that have different size of test suites show considerably different fault ages and performance order. And lastly, the $20\%$ of test cases shows considerably good performance compared to the execution result of the full test suite.

• International Journal of Highway Engineering
• /
• v.14 no.2
• /
• pp.11-17
• /
• 2012

This research describes how to predict a model of the tensile strain related to the fatigue cracking performance of several asphalt concrete structures through design of experiments(e.g., Response Surface Methodology) and harmony search(HS) algorithm. The axisymmetric analysis program of finite element method, which is the KICTPAVE, was used to determine the strain level at the interface layer between asphalt layer and lean concrete layer. Once the training database set of various strain levels was constructed under the several condition of layer stiffnesses and thicknesses in the asphalt concrete structures, the data set was trained through the HS algorithm in order to determine the regression coefficients defined based on a response surface methodology. Furthermore, the testing set, which was not used for the training procedure of HS algorithm, was also constructed in order to evaluate whether the regression coefficients of a prediction model can be appropriately applied for other cases in asphalt concrete structures.

• Journal of the Korean Data and Information Science Society
• /
• v.25 no.6
• /
• pp.1385-1395
• /
• 2014

Economic traits of livestock are affected by environmental factors and genetic factors. In addition, it is not affected by one gene, but is affected by interaction of genes. We used a linear regression model in order to adjust environmental factors. And, in order to identify gene-gene interaction effect, we applied data mining techniques such as neural network, logistic regression, CART and C5.0 using five-SNPs (single nucleotide polymorphism) of FASN (fatty acid synthase). We divided total data into training (60%) and testing (40%) data, and applied the model which was designed by training data to testing data. By the comparison of prediction accuracy, C5.0 was identified as the best model. It were selected superior genotype using the decision tree.

• The Korean Journal of Franchise Management
• /
• v.7 no.2
• /
• pp.27-35
• /
• 2016

Purpose - The primary objective of this study is to investigate the impact of employee characteristics on employees' preference towards corporate pension products. This study can provide a guidance for maximization of benefits for employees and their affiliated corporation. Employee characteristics include average length of labour, wage system of annual salary, age, types of interest rates and size of corporation. Existing research generally concentrate on vitalizations of corporate pension product raising an imperfection, improvements, tax benefit analysis and legal consideration. Thus, this study intensively analyses the effect of employee attributes on firms' decision for corporate pension products, such as DB(defined benefit) and DC(defined contribution) type. Research design, data, and methodology - The data were collected using self-administrated questionnaire survey on corporate pension products from CEOs or HR directors 250 foreign-invested companies', purchasing pension plans in practice with domestic financial trustees (insurance companies, banks and security companies). Hypotheses testing was conducted using Logistic Regression analysis with SPSS/PC+ 21.0. Results - The findings of the study are as follows. Employees with the long length of labour are more likely to have DB plan; more likely to prefer DC plan with the dividend distribution product regarding the types of interest rate. SMEs(less than 100 employees) are more likely to select DC plan whereas high fluctuation in wage with annual salary has no impacts. In addition, the ages has no significant effect on the preference. Conclusions - This study has examined with the empirical testing that employees' variable attributes and qualities are one of the vital factors for corporation pension plan selection. Currently, majority employees are highly likely to join DB plan and Defined interest types. Corporation with less than 10 employees prefer IRP scheme while most of corporation are intended to join DC plan. In a very near future, corporation more than 300 employees will be required to purchase mandatory plan under national regulation. For maximization of employees' contentment to corporation pension insurance and for complementing the flaws of existing plans, the future studies shall also research in a perspective of employee benefit.

• Journal of Digital Convergence
• /
• v.15 no.10
• /
• pp.233-241
• /
• 2017

This study has attempted to empirically analyze the mediating effects of small and medium venture firms' manufacturing capability and testing and inspection capability on the relation between their external information network heterogeneity and technology commercialization capability with a view to diversifying the research stream on the influential factors to small and medium firms' technology commercialization capability. By performing the ordinary least squares regression analysis, the Sobel test, and the Baron and Kenny test based on the 683 data of South Korean small and medium venture firms with the IBM SPSS version 23, this study provides the three empirical findings to be useful for future studies on the roles of small and medium venture firms' the manufacturing capability and testing and inspection capability. First, small and medium venture firms' manufacturing capability partially mediates the positive effect of their external information network heterogeneity on their technology commercialization capability. Second, their testing and inspection capability partially mediates this positive effect. Third, their manufacturing capability and testing and inspection capability jointly and partially mediates this positive effect.

• Asian-Australasian Journal of Animal Sciences
• /
• v.33 no.9
• /
• pp.1387-1399
• /
• 2020

Objective: The objective of this study was to estimate the genetic parameters and trends for milk, fat, and protein yields in the first three lactations of Thai dairy cattle using a 3-trait,-3-lactation random regression test-day model. Methods: Data included 168,996, 63,388, and 27,145 test-day records from the first, second, and third lactations, respectively. Records were from 19,068 cows calving from 1993 to 2013 in 124 herds. (Co) variance components were estimated by Bayesian methods. Gibbs sampling was used to obtain posterior distributions. The model included herd-year-month of testing, breed group-season of calving-month in tested milk group, linear and quadratic age at calving as fixed effects, and random regression coefficients for additive genetic and permanent environmental effects, which were defined as modified constant, linear, quadratic, cubic and quartic Legendre coefficients. Results: Average daily heritabilities ranged from 0.36 to 0.48 for milk, 0.33 to 0.44 for fat and 0.37 to 0.48 for protein yields; they were higher in the third lactation for all traits. Heritabilities of test-day milk and protein yields for selected days in milk were higher in the middle than at the beginning or end of lactation, whereas those for test-day fat yields were high at the beginning and end of lactation. Genetics correlations (305-d yield) among production yields within lactations (0.44 to 0.69) were higher than those across lactations (0.36 to 0.68). The largest genetic correlation was observed between the first and second lactation. The genetic trends of 305-d milk, fat and protein yields were 230 to 250, 25 to 29, and 30 to 35 kg per year, respectively. Conclusion: A random regression model seems to be a flexible and reliable procedure for the genetic evaluation of production yields. It can be used to perform breeding value estimation for national genetic evaluation in the Thai dairy cattle population.

• Journal of Digital Convergence
• /
• v.14 no.6
• /
• pp.167-175
• /
• 2016

This study analyzed empirically the same data through SPSS statistic(regression analysis) and AMOS program(structural equation model) used for cause and effect analysis. The result of empirical analysis was as follows. The different outcome of coefficients and p-values were deducted. Especially, in the mediated effect testing, meanwhile, SPSS statistic(regression analysis) pictured mediated effect, AMOS program(structural equation model) did not picture mediated effect on the reject zone of null hypothesis(absolute t-value and C.R.-value were nearby 1.96). Eventually, this study showed that what program used determined the outcomes of coefficients and p-values(In particular, the outcomes were differentiated further in the increasing measurement error) though using the same data.

• Journal of the Korean Institute of Illuminating and Electrical Installation Engineers
• /
• v.13 no.4
• /
• pp.120-126
• /
• 1999

;The consicErations for reminder life of transmission line is gradually higher. It is requisite for investigation of ACSR's life to test tensile load of ACSR as a fundamental data. It is vary important to analysis correlations between results of tensile load testing and elasped years. Estimation of ACSR's life can be obtained by statistics processing using mechanical experirrental results. It is a general method to use regression analysis as a statistics processing technique. In this paper, we did experiment on tensile strength of ACSR by using a new and old ACSR as sample experirrental materials. The limit of life estimation is decided by basic line using twenty percentage reduction of rate tensile strength. This basic line is like to results of Canada Ontario Hydro-research. There are $95[\textrm{mm}^2]$, $97[\textrm{mm}^2]$, $120[\textrm{mm}^2]$, $240[\textrm{mm}^2]$ ACSRs which are experimented on this study. 1be life estimation of these ACSR is presented by table 1 to be obtained through the linear regression and nonlinear regression analysis. SPSS and statistics toolbox of matlab is used for analysis.lysis.