• Journal of the Korean Data and Information Science Society
• /
• v.14 no.2
• /
• pp.355-366
• /
• 2003

A unified procedure for principal component regression (PCR), partial least squares (PLS) and ordinary least squares (OLS) is proposed. The process gives solutions for PCR, PLS and OLS in a unified and non-iterative way. This enables us to see the interrelationships among the three regression coefficient vectors, and it is seen that the so-called E-matrix in the solution expression plays the key role in differentiating the methods. In addition to setting out the procedure, the paper also supplies a robust numerical algorithm for its implementation, which is used to show how the procedure performs on a real world data set.

• Communications for Statistical Applications and Methods
• /
• v.22 no.2
• /
• pp.147-157
• /
• 2015

We consider a sparse high-dimensional linear regression model. Penalized methods using LASSO or non-convex penalties have been widely used for variable selection and estimation in high-dimensional regression models. In penalized regression, the selection and prediction performances depend on which penalty function is used. For example, it is known that LASSO has a good prediction performance but tends to select more variables than necessary. In this paper, we propose an additive sparse penalty for variable selection using a combination of LASSO and minimax concave penalties (MCP). The proposed penalty is designed for good properties of both LASSO and MCP.We develop an efficient algorithm to compute the proposed estimator by combining a concave convex procedure and coordinate descent algorithm. Numerical studies show that the proposed method has better selection and prediction performances compared to other penalized methods.

• Communications for Statistical Applications and Methods
• /
• v.11 no.3
• /
• pp.485-494
• /
• 2004

An algorithm is proposed to identify multiple outliers in linear regression. It is based on the clustering of residuals from the least median of squares estimation. A cut-height criterion for the hierarchical cluster tree is suggested, which yields the optimal clustering of the regression outliers. Comparisons of the effectiveness of the procedures are performed on the basis of the classic data and artificial data sets, and it is shown that the proposed algorithm is superior to the one that is based on the least squares estimation. In particular, the algorithm deals very well with the masking and swamping effects while the other does not.

• International Journal of Highway Engineering
• /
• v.16 no.5
• /
• pp.59-66
• /
• 2014

PURPOSES : This study is to predict the Sound Pressure Level(SPL) obtained from the Noble Close ProXimity(NCPX) method by using the Extended Kalman Filter Algorithm employing the taylor series and Linear Regression Analysis based on the least square method. The objective of utilizing EKF Algorithm is to consider stochastically the effect of error because the Regression analysis is not the method for the statical approach. METHODS : For measuring the friction noise between the surface and vehicle's tire, NCPX method was used. With NCPX method, SPL can be obtained using the frequency analysis such as Discrete Fourier Transform(DFT), Fast Fourier Transform(FFT) and Constant Percentage Bandwidth(CPB) Analysis. In this research, CPB analysis was only conducted for deriving A-weighted SPL from the sound power level in terms of frequencies. EKF Algorithm and Regression analysis were performed for estimating the SPL regarding the vehicle velocities. RESULTS : The study has shown that the results related to the coefficient of determination and RMSE from EKF Algorithm have been improved by comparing to Regression analysis. CONCLUSIONS : The more the vehicle is fast, the more the SPL must be high. But in the results of EKF Algorithm, SPLs are irregular. The reason of that is the EKF algorithm can be reflected by the error covariance from the measurements.

• Proceedings of the Korean Society of Precision Engineering Conference
• /
• 1997.10a
• /
• pp.450-453
• /
• 1997

There are many studies about optimization using genetic algorithm and desirability function. It's very important to find the optimal value of something like response surface or regression model. In this study I ind~cate the problem using the old type desirability function, and suggest the new type desirabhty functton that can fix the problem better, and simulate the model. Then I'll suggest the form of desirability function to find the optimum value of response surfaces which are made by mean and standard deviation using genetic algorithm and new type desirability function.

• Journal of the Korean Data and Information Science Society
• /
• v.15 no.2
• /
• pp.477-483
• /
• 2004

One of the major paradigms for supervised learning in neural network community is back-propagation learning. The standard implementations of back-propagation learning are optimal under the assumptions of identical and independent Gaussian noise. In this paper, for regression function estimation, we introduce $\varepsilon-insensitive$ back-propagation learning algorithm, which corresponds to minimizing the least absolute error. We compare this algorithm with support vector machine(SVM), which is another $\varepsilon-insensitive$ supervised learning algorithm and has been very successful in pattern recognition and function estimation problems. For comparison, we consider a more realistic model would allow the noise variance itself to depend on the input variables.

• The Transactions of the Korean Institute of Power Electronics
• /
• v.26 no.4
• /
• pp.241-248
• /
• 2021

A battery state-of-health (SOH) estimation algorithm using a machine learning-based linear regression method is proposed for estimating battery aging. The proposed algorithm analyzes the change trend of the open-circuit voltage (OCV) curve, which is a parameter related to SOH. At this time, a section with high linearity of the SOH and OCV curves is selected and used for SOH estimation. The SOH of the aged battery is estimated according to the selected interval using a machine learning-based linear regression method. The performance of the proposed battery SOH estimation algorithm is verified through experiments and simulations using battery packs for electric vehicles.

• Communications for Statistical Applications and Methods
• /
• v.29 no.3
• /
• pp.333-351
• /
• 2022

The skew-t distribution is an attractive family of asymmetrical heavy-tailed densities that includes the normal, skew-normal and Student's-t distributions as special cases. In this work, we propose an EM-type algorithm for computing the maximum likelihood estimates for skew-t linear regression models with censored response. In contrast with previous proposals, this algorithm uses analytical expressions at the E-step, as opposed to Monte Carlo simulations. These expressions rely on formulas for the mean and variance of a truncated skew-t distribution, and can be computed using the R library MomTrunc. The standard errors, the prediction of unobserved values of the response and the log-likelihood function are obtained as a by-product. The proposed methodology is illustrated through the analyses of simulated and a real data application on Letter-Name Fluency test in Peruvian students.

• Journal of the Korean Operations Research and Management Science Society
• /
• v.28 no.3
• /
• pp.61-66
• /
• 2003

In many multiple regression analyses, the “multi-collinearity” problem arises since some independent variables are highly correlated with each other. Practically, the Ridge regression method is often adopted to deal with the problems resulting from multi-collinearity. We propose a better alternative method using iteration to obtain an exact least squares estimator. We prove the solvability of the proposed algorithm mathematically and then compare our method with the traditional one.

• Journal of the Korean Data and Information Science Society
• /
• v.18 no.4
• /
• pp.847-857
• /
• 2007

This paper provides a statistical algorithm which detects COD (chemical oxygen demand) measurement machine error on real-time. For this we propose to use regression model fitting and check its validity against the current observations. The main idea is that the normal regression relation between COD measurement and other parameters inside the machine will be violated when the machine is out of order.