• Journal of the Korean Data and Information Science Society
• /
• v.24 no.2
• /
• pp.391-399
• /
• 2013

Partially linear regression is capable of providing more complete description of the linear and nonlinear relationships among random variables. In support vector regression (SVR) the hyper-parameters are known to affect the performance of regression. In this paper we propose an iterative reweighted least squares (IRWLS) procedure to solve the quadratic problem of partially linear support vector regression with a modified loss function, which enables us to use the generalized approximate cross validation function to select the hyper-parameters. Experimental results are then presented which illustrate the performance of the partially linear SVR using IRWLS procedure.

• Restorative Dentistry and Endodontics
• /
• v.43 no.3
• /
• pp.34.1-34.5
• /
• 2018

In the previous section, we established a simple linear regression line by finding the slope and intercept using the least square method as: ${\hat{Y}}=30.79+0.71X$. Finding the regression line was a mathematical procedure. After that we need to evaluate the usefulness or effectiveness of the regression line, whether the regression model helps explain the variability of the dependent variable. Also, statistical inference of the regression line is required to make a conclusion at the population level, because practically, we work with a sample, which is a small part of population. Basic assumption of sampling method is simple random sampling.

• Journal of the Korean Statistical Society
• /
• v.27 no.4
• /
• pp.407-420
• /
• 1998

This paper is concerned with selecting covariates to be included in building linear random effects models designed to analyze clustered response normal data. It is based on a Bayesian approach, intended to propose and develop a procedure that uses probabilistic considerations for selecting premising subsets of covariates. The approach reformulates the linear random effects model in a hierarchical normal and point mass mixture model by introducing a set of latent variables that will be used to identify subset choices. The hierarchical model is flexible to easily accommodate sign constraints in the number of regression coefficients. Utilizing Gibbs sampler, the appropriate posterior probability of each subset of covariates is obtained. Thus, In this procedure, the most promising subset of covariates can be identified as that with highest posterior probability. The procedure is illustrated through a simulation study.

• Journal of the Korea Society for Simulation
• /
• v.10 no.4
• /
• pp.41-50
• /
• 2001

When optimizing a complex system by determining the optimum condition of the system parameters of interest, we often employ the process of estimating the unknown objective function, which is assumed to be a second order spline function. In doing so, we normally use common random numbers for different set of the controllable factors resulting in more accurate parameter estimation for the objective function. In this paper, we will show some mathematical result for the analysis of variance when using common random numbers in terms of the regression error, the residual error and the pure error terms. In fact, if we can realize the special structure of the covariance matrix of the error terms, we can use the result of analysis of variance for the uncorrelated experiments only by applying minor changes.

• Industrial Engineering and Management Systems
• /
• v.15 no.4
• /
• pp.432-445
• /
• 2016

A random profile is the result of a process, the output of which is a function instead of a scalar or vector quantity. In the nature of these objects, two main dimensions of "functionality" and "randomness" can be recognized. Valuable researches have been conducted to present control charts for monitoring such processes in which a regression approach has been applied by focusing on "randomness" of profiles. Performing other statistical techniques such as hypothesis testing for different parameters, comparing parameters of two populations, ANOVA, DOE, etc. has been postponed thus far, because the "functional" nature of profiles is ignored. In this paper, first, some needed theorems are proven with an applied approach, so that be understandable for an engineer which is unfamiliar with advanced mathematical analysis. Then, as an application of that, a statistical test is designed for mean of continuous random profiles. Finally, using experimental operating characteristic curves obtained in computer simulation, it is demonstrated that the presented tests are properly able to recognize deviations in the null hypothesis.

• Journal of the Korea Institute of Military Science and Technology
• /
• v.10 no.1
• /
• pp.94-100
• /
• 2007

MVRS's measuring principles are based on the Doppler principle. It measures the velocities near the muzzle using the doppler signal output from the antenna and then predicts the velocity of the bullet leaving the muzzle by performing the regression analysis on previous measured velocities. There are a number of error sources when calculating the muzzle velocity. Antenna has long term frequency stability error and the doppler signal from the antenna has noise. These two error sources influence the accuracy of estimated velocities from the doppler signal. Estimated velocity errors result in the random error of data statistics. And when performing a regression analysis these random error components are transferred to the fitting error component. This study also analyzed the error components according to the hardware limitations of MVRS-700 and the signal processing method, and presented the calculated uncertainty of muzzle velocity.

• Proceedings of the Korea Concrete Institute Conference
• /
• 1995.04a
• /
• pp.231-236
• /
• 1995

The object of this thesis is an analytical study on flexural deformation of high strength concrete structures using reliability theory. Using the established experimental data that have been presented in various documents the stress-strain relationship curves of high strength(500kgf/$\textrm{cm}^2$)models are proposed. Based on both methods of logarithm regression analysis and multiple regression analysis adopted in order to establish the relationships between design parameters, response random variables and flexural deformation analyzed using Monte Carlo simulation and Simpson composite formula. Additional random variables are introduced to incorporate both the confidence in the analytical accuracy of engineering mechanics associated with structural response quantities and the uncertainty in the construction quality control. The result is expected to accomodate other important design parameter of high strength concrete design in treating reliability theory that practicing engineers, structural engineering often face.

• IEMEK Journal of Embedded Systems and Applications
• /
• v.16 no.1
• /
• pp.17-27
• /
• 2021

In this paper, we develop a galaxy image classification method based on hand-crafted features and machine learning techniques. Additionally, we provide an empirical analysis to reveal which combination of the techniques is effective for galaxy image classification. To achieve this, we developed a framework which consists of four modules such as preprocessing, feature extraction, feature post-processing, and classification. Finally, we found that the best technique for galaxy image classification is a method to use a median filter, ORB vector features and a voting classifier based on RBF SVM, random forest and logistic regression. The final method is efficient so we believe that it is applicable to embedded environments.

• Journal of the Semiconductor & Display Technology
• /
• v.21 no.2
• /
• pp.138-143
• /
• 2022

The employment prediction model proposed in this paper uses 16 independent variables, including self-introductions of M University students who applied for IPP and work-study internship, and 3 dependent variable data such as large companies, mid-sized companies, and unemployment. The employment prediction model for large companies was developed using Random Forest and Word2Vec with the result of F1_Weighted 82.4%. The employment prediction model for medium-sized companies and above was developed using Logistic Regression and Word2Vec with the result of F1_Weighted 73.24%. These two models can be actively used in predicting employment in large and medium-sized companies for M University students in the future.

• International Journal of Contents
• /
• v.17 no.4
• /
• pp.16-34
• /
• 2021

The purpose of this study was to explore how designers use software-based design tools for ideation and collaboration (for two cases: with designers and with developers). We conducted logistic regression analysis and random forest analysis. Software-based design tools are more popular among product designers and affiliated with design organizations with 51 to 100 members. We identify the features that influence designers to use design tools for the ideation and collaboration, and how these usage patterns are interrelated. Interrelated usage pattern is a key consideration for location of the menu and convenience of use. The results imply that reinforcement of the design tool features per designer profile is required and that design management should be consistent with the field of design and the nature of the organization.