• Journal of the Korean Statistical Society
• /
• 제36권1호
• /
• pp.57-76
• /
• 2007

Kriging is a nonparametric regression method used in geostatistics for estimating curves and surfaces for spatial data. It may come as a surprise that the Kriging estimator, normally derived as the best linear unbiased estimator, is also the solution of a particular variational problem. Thus, Kriging estimators can also be interpreted as generalized smoothing splines where the roughness penalty is determined by the covariance function of a spatial process. We build off the early work by Silverman (1982, 1984) and the analysis by Cox (1983, 1984), Messer (1991), Messer and Goldstein (1993) and others and develop an equivalent kernel interpretation of geostatistical estimators. Given this connection we show how a given covariance function influences the bias and variance of the Kriging estimate as well as the mean squared prediction error. Some specific asymptotic results are given in one dimension for Matern covariances that have as their limit cubic smoothing splines.

• 한국소음진동공학회논문집
• /
• 제20권9호
• /
• pp.841-848
• /
• 2010

Previous experimental results show that the magnetostrictive transducer has the peculiar characteristic with relation to their reversible magnetization and its practical usage will be hindered by this phenomena. In this paper, the idea of anhysteretization is adopted in order to solve this problem. The experimental results reveal that the anhysteretization can get rid of the extraordinary phenomena which are occurred by the change of biasing magnetic field. The effects of two important parameters, which are the amplitude and the decaying time of this process, on the anhysteretization are investigated experimentally. Finally the best operating condition is proposed in order to maximize the sensitivity under the anhysteretization.

• 한국진공학회:학술대회논문집
• /
• 한국진공학회 2011년도 제40회 동계학술대회 초록집
• /
• pp.202-202
• /
• 2011

Diagnostics of plasma density is a key factor for monitoring plasma processing. Various probes are invented to measure plasma density and cut-off probe is a one of the most promising diagnostics tool for measuring plasma density. However, at the low density or high pressure the cut-off probe cannot clearly resolve the cut-off peak. Several reasons make this problem: Cut-off likes peaks caused by cavity resonances and weaken transmission spectrum signal at high pressure. Recently, You et al., have researched mechanism of cut-off probe and we improve the cut-off reliability and sensitivity base on that research. Modified cut-off antenna is adapted and bias cut-off probe method is tried. These experiment results have good agreement with the previous study and show good measurement characteristics.

• 한국진공학회:학술대회논문집
• /
• 한국진공학회 2011년도 제40회 동계학술대회 초록집
• /
• pp.52-52
• /
• 2011

A novel deposition process for n-type nanocrystalline silicon (n-type nc-Si) thin films at room temperature has been developed by adopting the neutral beam assisted chemical vapor deposition (NBa-CVD). During formation of n-type nc-Si thin film by the NBa-CVD process with silicon reflector electrode at room temperature, the energetic particles could induce enhance doping efficiency and crystalline phase in polymorphous-Si thin films without additional heating on substrate; The dark conductivity and substrate temperature of P-doped polymorphous~nano crystalline silicon thin films increased with increasing the reflector bias. The NB energy heating substrate(but lower than $80^{\circ}C$ and increase doping efficiency. This low temperature processed doped nano-crystalline can address key problem in applications from flexible display backplane thin film transistor to flexible solar cell.

• 수산해양기술연구
• /
• 제46권4호
• /
• pp.449-457
• /
• 2010

This study shows that the vertical migration speed of sound scattering layers (SSLs), which is distributed in near Funka Bay, were measured by 3D velocity components acquired from a bottom moorng ADCP. While the bottom mooring type has a problem to measure the velocity vectors of sound scattering layer distributed near to surface, both the continuous vertical migration patterns and variability of backscatterers were routinely investigated as well. In addition, the velocity vectors were compared with the vertical migration velocity estimated from echograms of Mean Volume Backscattering Strength, and estimated to produce observational bias due to SSLs which is composed of backscatterers such as euphausiids, nekton, and fishes have swimming ability.

• Journal of Communications and Networks
• /
• 제9권4호
• /
• pp.402-407
• /
• 2007

The network throughput is an important performance criteria for the packet ring networks. Since maximizing the network throughput can lead to severe bias in bandwidth allocation among all flows, fairness should be imposed to prevent bandwidth starvation. The challenge here, therefore, is the joint optimization of the network throughput and fairness. In this paper, we present the optimal bandwidth assignment scheme to decompose this optimization problem into two tasks, one for finding fair bandwidth assignment and the other for finding the optimal routing. The network throughput is maximized under the fairness constraints when these tasks are performed iteratively.

• 한국시뮬레이션학회논문지
• /
• 제9권4호
• /
• pp.67-75
• /
• 2000

Often system analysts are interested in the estimation of percentile for system performance. For instance, in PERT network system, the percentile that the project. Typically the control variate method is used to reduce the variability of mean response using the correlation between the response and the control variates with a little additional cost during the course of simulation. In the same spirit, we apply this method to estimate the percentile of project completion time in PERT system, and evaluate the efficiency of the controlled estimator for its percentile.1 Simulation results indicate that the controlled estimators are more effective in reducing the variances of estimators than the simple estimators, however those tend to a little underestimate the percentiles for some critical values. We need more simulation experiments to examine such a kind of bias problem. We expect this research presents a step forward in the area of variance reduction techniques of stochastic simulation.

• 대한전자공학회:학술대회논문집
• /
• 대한전자공학회 2000년도 ITC-CSCC -1
• /
• pp.403-405
• /
• 2000

This paper describes a single transistor type ferroelectric field effect transistor (1Tr FeFET) memory cell scheme, which select one unit memory cell and program/read it. The well voltage can be controlled by isolating the common row well lines. Through applying bias voltage to Gate and Well, respectively, we implement If FeFET memory cell scheme in which interference problem is not generated and the selection of each memory cell is possible. The results of HSPICE simulations showed the successful operations of the proposed cell scheme.

• 한국자기학회:학술대회 개요집
• /
• 한국자기학회 2002년도 동계연구발표회 논문개요집
• /
• pp.160-161
• /
• 2002

One problem in giant magnetoresistance(GMR) spin valves and magnetic tunneling junctions(MTJ) exchange biased by Mn-based antiferromagnets is the Mn diffusion into the ferromagnetic layer and other layers upon annealing.$^{1-3}$ It seems that Mn diffusion that may occur during annealing has a key role in the exchange biasing. We have fabricated multilayers inserting the nanolayer(NL) between antiferromagnet and ferromagent using ion-beam deposition system to study the diffusion effect for the exchange bias. (omitted)

• ETRI Journal
• /
• 제31권2호
• /
• pp.121-128
• /
• 2009

In this paper, we describe a fixed-threshold sequential minimal optimization (FSMO) for structured SVM problems. FSMO is conceptually simple, easy to implement, and faster than the standard support vector machine (SVM) training algorithms for structured SVM problems. Because FSMO uses the fact that the formulation of structured SVM has no bias (that is, the threshold b is fixed at zero), FSMO breaks down the quadratic programming (QP) problems of structured SVM into a series of smallest QP problems, each involving only one variable. By involving only one variable, FSMO is advantageous in that each QP sub-problem does not need subset selection. For the various test sets, FSMO is as accurate as an existing structured SVM implementation (SVM-Struct) but is much faster on large data sets. The training time of FSMO empirically scales between O(n) and O($n^{1.2}$), while SVM-Struct scales between O($n^{1.5}$) and O($n^{1.8}$).