• Communications for Statistical Applications and Methods
• /
• v.27 no.1
• /
• pp.129-140
• /
• 2020

In this paper, we introduce an efficient algorithm for the non-convex penalized multinomial logistic regression that can be uniformly applied to a class of non-convex penalties. The class includes most non-convex penalties such as the smoothly clipped absolute deviation, minimax concave and bridge penalties. The algorithm is developed based on the concave-convex procedure and modified local quadratic approximation algorithm. However, usual quadratic approximation may slow down computational speed since the dimension of the Hessian matrix depends on the number of categories of the output variable. For this issue, we use a uniform bound of the Hessian matrix in the quadratic approximation. The algorithm is available from the R package ncpen developed by the authors. Numerical studies via simulations and real data sets are provided for illustration.

• 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.

• Proceedings of the Korean Society of Precision Engineering Conference
• /
• 1994.10a
• /
• pp.188-192
• /
• 1994

This paper presenta new method for tool interference acoidance using rectanguar approximation in NC machining of scuptured surface. The procedure of algorithm for approximation of sculptured surface to rectangular surface is described. Using this algorithm, we can check concave, convex, and side interference region and avoid these interferenes.

• Journal of Institute of Control, Robotics and Systems
• /
• v.19 no.11
• /
• pp.955-959
• /
• 2013

It is possible to obtain an omnidirectional stereo image via a single camera by using a catadioptric approach with a convex mirror and concave lens. In order to measure three-dimensional distance using the imaging system, the optical parameters of the system are required. In this paper, a calibration procedure to extract the parameters of the imaging system is described. Based on the parameters, experiments are carried out to verify the performance of the three-dimensional distance measurement of a single camera omnidirectional stereo imaging system.

• Journal of the Korea Safety Management & Science
• /
• v.15 no.1
• /
• pp.77-85
• /
• 2013

In the location science, environmental effect becomes a new main consideration for site selection. For the unwanted facility location selection, decision makers should consider the cost of resolving the environmental conflict. We introduced the negative influence cost for the facility which was inversely proportional to distance between the facility and residents. An unwanted facility location problem was suggested to minimize the sum of the negative influence cost and the transportation cost. The objective cost function was analyzed as nonlinear type and was neither convex nor concave. Three GRASP (Greedy Randomized adaptive Search Procedure) methods as like Random_GRASP, Epsilon_GRASP and GRID_GRASP were developed to solve the unwanted facility location problem. The Newton's method for nonlinear optimization problem was used for local search in GRASP. Experimental results showed that quality of solution of the GRID_GRASP was better than those of Random_GRASP and Epsilon_GRASP. The calculation time of Random_GRASP and Epsilon_GRASP were faster than that of Grid_GRASP.

• Communications for Statistical Applications and Methods
• /
• v.29 no.1
• /
• pp.53-64
• /
• 2022

High dimensional time series is gaining considerable attention in recent years. The sparse vector heterogeneous autoregressive (VHAR) model proposed by Baek and Park (2020) uses adaptive lasso and debiasing procedure in estimation, and showed superb forecasting performance in realized volatilities. This paper extends the sparse VHAR model by considering non-convex penalties such as SCAD and MCP for possible bias reduction from their penalty design. Finite sample performances of three estimation methods are compared through Monte Carlo simulation. Our study shows first that taking into cross-sectional correlations reduces bias. Second, nonconvex penalties performs better when the sample size is small. On the other hand, the adaptive lasso with debiasing performs well as sample size increases. Also, empirical analysis based on 20 multinational realized volatilities is provided.

• The Journal of Korean Institute of Electromagnetic Engineering and Science
• /
• v.25 no.10
• /
• pp.1077-1086
• /
• 2014

We propose a design method of a Rotman lens for curved array antenna applicable to conformal array. In this paper, design equations are derived to obtain an array curve, transmission line lengths of a Rotman lens in conjunction with a curved array antenna, and the phase error of a Rotman lens based on these design equations is minimized through the beam curve optimization procedure and the refocusing procedure. Rotman lenses designed by the proposed design equations and design procedures still maintain 3 focal points, can feed a convex or concave array antenna with circular curve, parabolic curve, V-shaped curve, etc as well as a straight line array antenna, and have minimal phase error.

• Journal of the Korean Society for Precision Engineering
• /
• v.15 no.8
• /
• pp.46-59
• /
• 1998

This paper presents shape design, surface construction, and cutting path generation for the surface of marine ship propeller blades. A propeller blade should be designed to satisfy performance constraints that include operational speed which impacts rotations per minutes, stresses related to deliverable horst power, and the major length of the marine ship which impacts the blade size and shape characteristics. Primary decision variables that affect efficiency in the design of a marine ship propeller blade are the blade diameter and the expanded area ratio. The blade design resulting from these performance constraints typically consists of sculptured surfaces requiring four or five axis contoured machining. In this approach a standard blade geometry description consisting of blade sections with offset nominal points recorded in an offset table is used. From this table the composite Bezier surface geometry of the blade is created. The control vertices of the Hazier surface patches are determined using a chord length fitting procedure from tile offset table data. Cutter contact points and path intervals are calculated to minimize travel distance and production time while maintaining a cusp height within tolerance limits. Long path intervals typically generate short tool paths at the expense of increased however cusp height. Likewise, a minimal tool path results in a shorter production time. Cutting errors including gouging and under-cut, which are common errors in machining sculptured surfaces, are also identified for both convex and concave surfaces. Propeller blade geometry is conducive to gouging. The result is a minimal error free cutting path for machining propeller blades for marine ships.

• Korean Journal of Crystallography
• /
• v.6 no.2
• /
• pp.141-157
• /
• 1995

Single crystals of TeO2 with large diameter were grown by Czochralski technique with auto-diameter control system. The ratio of crystal to crucible was 60-70%. The effect of critical pulling and rotation rate on the crystal quality was studied. Optimum growth parameters for high quality crystal pulling rate was less than 1.2 mm/hr. The solid-liquid interface was convex at the rotation rate of 10-23 rpm and concave at the rotation rate of more than 25 rpm, depending on the size of crystal and crucible. The platinum concentration in the melts is one of the main factors of the constitutional supercooling and thus the bubble entrapment in the growing crystal. Growth axis was confirmed to {110} direction during the whole growth procedure. Infrared spectrometric study and dislocation density measurment by chemical etching method on the grown crystal were performed. Finally, the reasons of cooperation of striations, inclusions, and optical inhomogeneities were discussed.

• Progress in Medical Physics
• /
• v.27 no.2
• /
• pp.64-71
• /
• 2016

We develop a manufacture procedure for the production of a patient specific customized bolus (PSCB) using a 3D printer (3DP). The dosimetric accuracy of the 3D-PSCB is evaluated for electron beam therapy. In order to cover the required planning target volume (PTV), we select the proper electron beam energy and the field size through initial dose calculation using a treatment planning system. The PSCB is delineated based on the initial dose distribution. The dose calculation is repeated after applying the PSCB. We iteratively fine-tune the PSCB shape until the plan quality is sufficient to meet the required clinical criteria. Then the contour data of the PSCB is transferred to an in-house conversion software through the DICOMRT protocol. This contour data is converted into the 3DP data format, STereoLithography data format and then printed using a 3DP. Two virtual patients, having concave and convex shapes, were generated with a virtual PTV and an organ at risk (OAR). Then, two corresponding electron treatment plans with and without a PSCB were generated to evaluate the dosimetric effect of the PSCB. The dosimetric characteristics and dose volume histograms for the PTV and OAR are compared in both plans. Film dosimetry is performed to verify the dosimetric accuracy of the 3D-PSCB. The calculated planar dose distribution is compared to that measured using film dosimetry taken from the beam central axis. We compare the percent depth dose curve and gamma analysis (the dose difference is 3%, and the distance to agreement is 3 mm) results. No significant difference in the PTV dose is observed in the plan with the PSCB compared to that without the PSCB. The maximum, minimum, and mean doses of the OAR in the plan with the PSCB were significantly reduced by 9.7%, 36.6%, and 28.3%, respectively, compared to those in the plan without the PSCB. By applying the PSCB, the OAR volumes receiving 90% and 80% of the prescribed dose were reduced from $14.40cm^3$ to $0.1cm^3$ and from $42.6cm^3$ to $3.7cm^3$, respectively, in comparison to that without using the PSCB. The gamma pass rates of the concave and convex plans were 95% and 98%, respectively. A new procedure of the fabrication of a PSCB is developed using a 3DP. We confirm the usefulness and dosimetric accuracy of the 3D-PSCB for the clinical use. Thus, rapidly advancing 3DP technology is able to ease and expand clinical implementation of the PSCB.