• 한국데이터정보과학회:학술대회논문집
• /
• 2004.10a
• /
• pp.33-42
• /
• 2004

In this paper, a random shock model for a system is considered. Each shock arriving according to a Poisson process decreases the state of the system by a random amount. A repairman arriving according to another Poisson process of rate $\lambda$ repairs the system only if the state of the system is below a threshold $\alpha$. After assigning various costs to the system, we calculate the long-run average cost and show that there exist a unique value of arrival rate $\lambda$ and a unique value of threshold $\alpha$ which minimize the long-run average cost per unit time.

• Proceedings of the Korean Institute of Communication Sciences Conference
• /
• 1991.10a
• /
• pp.205-209
• /
• 1991

The conventional modeling equations for planar MOSFET can not be directly used for zero or minus junction depth concave MOSFET. In this paper, we suggest a new model which can simulate the electrical characteristics of concave MOSFET. The threshold voltage modeling was achieved using the charge sharing method considering the relative difference of source and drain depletion widths. To analyze the ID-VDS characteristics, the conventional expressions for planar MOSFET were employed with the electrical channel length as an effective channel length and the channel length modulation factor as ${\alpha}$ΔL. By comparing the proposed model with experimental results, we could get reasonably similar curves and we proposed a concave MOSFET conditiion which shows no short channel effect of threshold voltage(V${\gamma}$).

• Journal of the Korean Statistical Society
• /
• v.24 no.2
• /
• pp.471-479
• /
• 1995

A random shock model for a linearly deteriorating system is introduced. The system deteriorating linearly with time is subject to random shocks which arrive according to a Poisson process and decrease the state of the system by a random amount. The system is repaired by a repairmen arriving according to another Poisson process if the state when he arrives is below a threshold. Explicit expressions are deduced for the characteristic function of the distribution function of X(t), the state of the system at time t, and for the distribution function of X(t) if X(t) is over the threshold. The stationary case is briefly discussed.

• Journal of Animal Science and Technology
• /
• v.48 no.2
• /
• pp.161-168
• /
• 2006

Genetic parameters for linear type and composite traits were estimated by using Bayesian inference via Gibbs sampling with a multiple threshold animal model in Holstein cows. Fifteen linear type traits and 5 composite traits were included to estimate genetic variance and covariance components in the model. In this study, 30,204 records were obtained in the cows from 305 sires. Heritability estimates for linear type traits had the estimates as high as 0.28~0.64. Heritability estimates for composite traits were also high, when the traits were assumed to be categorical traits. Final score was more correlated with the composite traits than with the linear type traits.

• Journal of IKEEE
• /
• v.24 no.4
• /
• pp.1011-1016
• /
• 2020

We propose a framework called Stacked Gated Recurrent Unit - Infrequent Residual Analysis (SG-IRA) that detects anomalies in time-series data that can be trained on streams of raw sensor data without any pre-labeled dataset. To enable such unsupervised learning, SG-IRA includes an estimation model that uses a stacked Gated Recurrent Unit (GRU) structure and an analysis method that detects anomalies based on the difference between the estimated value and the actual measurement (residual). SG-IRA's residual analysis method dynamically adapts the detection threshold from the population using frequency analysis, unlike the baseline model that relies on a constant threshold. In this paper, SG-IRA is evaluated using the industrial control systems (ICS) datasets. SG-IRA improves the detection performance (F1 score) by 5.9% compared to the baseline model.

• Journal of Soil and Groundwater Environment
• /
• v.22 no.1
• /
• pp.49-58
• /
• 2017

Biotic ligand model (BLM) and species sensitivity distribution (SSD) were used to determine the site-specific Cu threshold concentration (5% hazardous concentration; HC5) in soil pore water. Model parameters for Cu-BLM were collected for six plants, one collembola, and two earthworms from published literatures. Half maximal effective concentration ($EC_{50}\{Cu^{2+}\}$), expressed as $Cu^{2+}$ activity, was calculated based on activities of major cations and the collected Cu-BLM parameters. The $EC_{50}\{Cu^{2+}\}$ varied from 2 nM to $251{\mu}M$ according to the variation in environmental factors of soil pore water (pH, major cation/anion concentrations) and the type of species. Hazardous activity for 5% (HA5) and HC5 calculated from SSD varied from 0.076 to $0.4{\mu}g/L$ and 0.4 to $83.4{\mu}g/L$, respectively. HA5 and HC5 significantly decreased with the increase in pH in the region with pH less than 7 due to the decrease in competition with $H^+$ and $Cu^{2+}$. In the region with pH more than 7, HC5 increased with the increase in pH due to the formation of complexes of Cu with inorganic ligands. In the presence of dissolved organic carbon (DOC), Cu and DOC form a complex, which decreases $Cu^{2+}$ activity in soil pore water, resulting in up to 292-fold increase in HC5 from 0.48 to $140{\mu}g/L$.

• KDI Journal of Economic Policy
• /
• v.31 no.2
• /
• pp.1-13
• /
• 2009

The monetary model suggests that nominal exchange rates between two countries will be determined by important macroeconomic variables. The existence of a cointegrating relationship among these fundamental variables is the backbone of the monetary model. In a recent paper, Rapach and Wohar (2002, Journal of International Economics) advance the literature by testing for linear cointegration in the monetary model using a century of data to increase power. They find evidence of cointegration in five or six of ten countries. We extend their work to the nonlinear framework by performing threshold cointegration tests that allow for asymmetric adjustments in two regimes. Asymmetric adjustments in exchange rates can occur, for example, if transactions costs are present or if policy makers react asymmetrically to changing fundamentals. Moreover, whereas Rapach and Wohar (2002) found it necessary to exclude the relative output variable in some cases to maintain the validity of their cointegration tests, we can include this variable as a stationary covariate to increase power. Overall, using their same long-span data, we find more support for cointegration in a nonlinear framework.

• Journal of the Institute of Electronics and Information Engineers
• /
• v.51 no.1
• /
• pp.161-171
• /
• 2014

When the Hough transform is applied to identify an instance of a given model, the output is typically a histogram of votes cast by a set of image features into a parameter space. The next step is to threshold the histogram of counts to hypothesize a given match. The question is "What is a reasonable choice of the threshold?" In a standard implementation of the Hough transform, the threshold is selected heuristically, e.g., some fraction of the highest cell count. Setting the threshold too low can give rise to a false alarm of a given shape(Type I error). On the other hand, setting the threshold too high can result in mis-detection of a given shape(Type II error). In this paper, we derive two conditional probability functions of cell counts in the accumulator array of the generalized Hough transform(GHough), that can be used to select a scientific threshold at the peak detection stage of the Ghough.

• Journal of the Korea Institute of Information and Communication Engineering
• /
• v.16 no.5
• /
• pp.982-988
• /
• 2012

This paper has presented the relation of scaling theory and threshold voltage of double gate(DG) MOSFET. In the case of conventional MOSFET, current and switching frequency have been analyzed based on scaling theory. To observe the possibility of application of scaling theory for threshold voltage of DGMOSFET, the change of threshold voltage has been observed and analyzed according to scaling theory. The analytical potential distribution of Poisson equation has been used, and this model has been already verified. To solve Poisson equation, charge distribution such as Gaussian function has been used. As a result, it has been observed that threshold voltage is grealty changed according to scaling factor and change rate of threshold voltages is traced for scaling of doping concentration in channel. This paper has explained for the best modified scaling theory reflected the influence of two gates as using weighting factor when scaling theory has been applied for channel length and channel thickness.

• Transactions of the Korean Society of Mechanical Engineers A
• /
• v.39 no.2
• /
• pp.163-168
• /
• 2015

In order to perform estimations with high reliability, it is necessary to deal with the tail part of the cumulative distribution function (CDF) in greater detail compared to an overall CDF. The use of a generalized Pareto distribution (GPD) to model the tail part of a CDF is receiving more research attention with the goal of performing estimations with high reliability. Current studies on GPDs focus on ways to determine the appropriate number of sample points and their parameters. However, even if a proper estimation is made, it can be inaccurate as a result of an incorrect threshold value. Therefore, in this paper, a GPD based on the Akaike information criterion (AIC) is proposed to improve the accuracy of the tail model. The proposed method determines an accurate threshold value using the AIC with the overall samples before estimating the GPD over the threshold. To validate the accuracy of the method, its reliability is compared with that obtained using a general GPD model with an empirical CDF.