• Journal of the Korean Data and Information Science Society
• /
• v.15 no.2
• /
• pp.331-337
• /
• 2004

In the analysis of massive volume data, a neural network model is a useful tool. To implement the Neural network model, it is important to select initial value. Since the initial values are generally used as random value in the neural network, the convergent performance and the prediction rate of model are not stable. To overcome the drawback a possible method use samples randomly selected from the whole data set. That is, coefficients estimated by logistic regression based on the samples are the initial values.

• International Journal of Reliability and Applications
• /
• v.14 no.2
• /
• pp.107-114
• /
• 2013

Modelling of failures is an important element of reliability modelling. Empirical modelling approach suitable for complex item is explored in this paper. First step of the empirical modelling approach is to plot hazard function, density function, Weibull probability plot as well as cumulative intensity function to see which model fits best for the given data. Next step of the empirical modelling approach is select appropriate model for the data and fit the parametric model accordingly and estimate the parameters.

• Journal of Korean Society of Industrial and Systems Engineering
• /
• v.26 no.3
• /
• pp.1-9
• /
• 2003

Databases are central to business information systems and RDBMS is most widely used for the database system. Normalization was designed to control various anomalies (insert, update, delete anomalies). However, normalized database design does not account for the tradeoffs necessary for performance. In this research, I model a database design method considering denormalization of duplicating attributes in order to reduce frequent join processes. This model considers response time for processing each select, insert, update, delete transaction, and for treating anomalies. A branch and bound method is proposed for this model.

• Journal of the Ergonomics Society of Korea
• /
• v.20 no.1
• /
• pp.45-62
• /
• 2001

This study suggests a genetic algorithm-based partial least squares (GA-based PLS) method to select the design variables for building a usability model. The GA-based PLS uses a genetic algorithm to minimize the root-mean-squared error of a partial least square regression model. A multiple linear regression method is applied to build a usability model that contains the variables seleded by the GA-based PLS. The performance of the usability model turned out to be generally better than that of the previous usability models using other variable selection methods such as expert rating, principal component analysis, cluster analysis, and partial least squares. Furthermore, the model performance was drastically improved by supplementing the category type variables selected by the GA-based PLS in the usability model. It is recommended that the GA-based PLS be applied to the variable selection for developing a usability model.

• International journal of advanced smart convergence
• /
• v.10 no.4
• /
• pp.215-224
• /
• 2021

The purpose of this study is to estimate the factors that affect college students' drinking needs and spending. An analysis model to estimate the determinants affecting drinking needs was applied with a truncated Poisson model and a truncated negative binomial model. Tests to select more appropriate models of the two types were made using the comparison of log-likelihood function and the over-dispersion test. The analysis result was interpreted by applying the truncated negative binomial model as the truncated Poisson model showed over-dispersion. We also applied the Tobit model to analyze the determinantsthat affect college students' expenditure on drinking. According to the analysis, gender, grade, allowance and parental occupation were the factors influencing statistics, and gender, type of household income, and student religion were the factors influencing expenditure.

• Korean Journal of Computational Design and Engineering
• /
• v.16 no.1
• /
• pp.21-30
• /
• 2011

Similarity assessment of a CAD model is one of important issues from the aspect of model re-using. In real practice, many new mechanical parts are designed by modifying existing ones. The reuse of part enables to save design time and efforts for the designers. Design time would be further reduced if there were an efficient way to search for existing similar designs. This paper proposes an efficient algorithm of similarity assessment for mechanical part model with design history embedded within the CAD model. Since it is possible to retrieve the design history and detailed-feature information using CAD API, we can obtain an accurate and reliable assessment result. For our purpose, our assessment algorithm can be divided by two: (1) we select suitable parts by comparing MSG (Model Signature Graph) extracted from a base feature of the required model; (2) detailed-features' similarities are assessed with their own attributes and reference structures. In addition, we also propose a indexing method for managing a model database in the last part of this article.

• Proceedings of the Korean Society for Noise and Vibration Engineering Conference
• /
• 2008.04a
• /
• pp.290-293
• /
• 2008

This paper proposes a criterion to select the modes for modal truncated model of flexible rotor only supported by active magnetic bearings. The proposed approach relies on the concepts of minimum control input and output energy assuming that the system is subjected to transient disturbances. Accurate large order model for the levitated rotor is taken by finite element analysis and transformed to the modal equation. By proposed methodology, which modal states should be retained in the truncated model are investigated over the whole operational speed range by the calculation. Finally, the effectiveness is verified by checking the model error between original model and reduced model.

• Proceedings of the Korean Operations and Management Science Society Conference
• /
• 2003.05a
• /
• pp.980-983
• /
• 2003

The purpose of this paper is to construct a CIDEAR (Cross Impact Data Envelopment Analysis Assurance Region) model which evaluates proposed R&D projects considering cross impacts among them and selects them to utilize R&D resources effectively as well as to maximize effectiveness of investments. For this purpose, the following six steps are designed as the main procedure. $\lceilDecision\;Theory\;&\;Evaluation\;Model\rfloor$, $\lceilAR\;Decision\;&\;Evaluation\;Model\rfloor$, $\lceilResource\;&\;Performance\;Analysis Model\rfloor$, $\lceilCross\;Impact\;Assumption\;Model\rfloor$, $\lceilpriority\;Oder\;Decision\;Model\rfloor$, $\lceilEfficiency\;Cause\;Analysis\;Model\rfloor$. $\lceilCIDEAR\rfloor$ model can deal with the affairs of R&D projects having the characteristics of mutual independence as well as mutual dependence. Hence it is possible to evaluate and select R&D projects more accurately than any other models.

• Communications for Statistical Applications and Methods
• /
• v.26 no.2
• /
• pp.149-161
• /
• 2019

In this article, we suggest the following approaches to simultaneous variable selection and outlier detection. First, we determine possible candidates for outliers using properties of an intercept estimator in a difference-based regression model, and the information of outliers is reflected in the multiple regression model adding mean shift parameters. Second, we select the best model from the model including the outlier candidates as predictors using stochastic search variable selection. Finally, we evaluate our method using simulations and real data analysis to yield promising results. In addition, we need to develop our method to make robust estimates. We will also to the nonparametric regression model for simultaneous outlier detection and variable selection.

• Korean Journal of Construction Engineering and Management
• /
• v.18 no.2
• /
• pp.108-116
• /
• 2017

It is expected that the maintenance cost of domestic bridges will increase considerably due to the increase of bridge service time. In response to this situation, the government and relevant ministries are focusing on developing ways to efficiently allocate limited budgets and to rationally select maintenance bridge. In this study, to develop a risk - based bridge maintenance priority decision model, 14 common risk factors causing damage to bridges were extracted and AHP analysis was performed to select 5 important factors. Based on the existing literature review and expert consultation, we derive the evaluation criteria and the impact weights of the selected factors, and based on this, I presented risk based bridge maintenance priority model. Using this model in combination with existing maintenance priority methods will lead to more reasonable bridge maintenance priorities.