• Proceedings of the KIEE Conference
• /
• 2006.10c
• /
• pp.588-590
• /
• 2006

Recently, many on-line approaches to instrument channel surveillance (drift monitoring and fault detection) have been reported worldwide. On-line monitoring (OLM) method evaluates instrument channel performance by assessing its consistency with other plant indications through parametric or non-parametric models. The heart of an OLM system is the model giving an estimate of the true process parameter value against individual measurements. This model gives process parameter estimate calculated as a function of other plant measurements which can be used to identify small sensor drifts that would require the sensor to be manually calibrated or replaced. This paper describes an improvement of auto-associative kernel regression by introducing a correlation coefficient weighting on kernel distances. The prediction performance of the developed method is compared with conventional auto-associative kernel regression.

• The Journal of the Korea Contents Association
• /
• v.21 no.3
• /
• pp.616-625
• /
• 2021

Deep neural networks are an approximation method that approximates an arbitrary function to a linear model and then repeats additional approximation using a nonlinear active function. In this process, the method of evaluating the performance of approximation uses the loss function. Existing in-depth learning methods implement approximation that takes into account loss functions in the linear approximation process, but non-linear approximation phases that use active functions use non-linear transformation that is not related to reduction of loss functions of loss. This study proposes parametric activation functions that introduce scale parameters that can change the scale of activation functions and location parameters that can change the location of activation functions. By introducing parametric activation functions based on scale and location parameters, the performance of nonlinear approximation using activation functions can be improved. The scale and location parameters in each hidden layer can improve the performance of the deep neural network by determining parameters that minimize the loss function value through the learning process using the primary differential coefficient of the loss function for the parameters in the backpropagation. Through MNIST classification problems and XOR problems, parametric activation functions have been found to have superior performance over existing activation functions.

• Proceedings of the Society of Korea Industrial and System Engineering Conference
• /
• 2002.05a
• /
• pp.365-370
• /
• 2002

In this study, according to MARMA(1,0) model which was suggested by Seppala, in case of existing autocorrelation in X control chart and EWMA control chart, the standard method and the non-parametric bootstrap method were compared and analysed using the bootstrap method which use the resampling prediction residual.

• Journal of the Korean Data and Information Science Society
• /
• v.15 no.3
• /
• pp.617-624
• /
• 2004

In this article the fuzzy number rank and the fuzzy rank transformation method are introduced in order to analyse the non-parametric fuzzy regression model which cannot be described as a specific functional form such as the crisp data and fuzzy data as a independent and dependent variables respectively. The effectiveness of fuzzy rank transformation methods is compared with other methods through the numerical examples.

• Journal of the Korean Society of Safety
• /
• v.32 no.5
• /
• pp.115-121
• /
• 2017

This paper is to introduce the main modeling assumptions and data structures associated with right-censored data to describe the successful methodological ideas for analyzing such a field-failure-data when components operating in different environments. The Kaplan - Meier method is the most popular method used for survival analysis. Together with the log-rank test, it may provide us with an opportunity to estimate survival probabilities and to compare survival between groups. An important advantage of the Kaplan - Meier curve is that the method can take into account some types of censored data, particularly right-censoring. The above non-parametric method was used to verify the equality of parts life used in different environments. After that, we performed the life distribution analysis using the parametric method. We simulated data from three distributions: exponential, normal, and Weibull. This allowed us to compare the results of the estimates to the known true values and to quantify the reliability indices. Here we used the Akaike information criterion to find a suitable life time distribution. If the Akaike information criterion is the smallest, the best model of failure data is presented. In this paper, no-nparametrics and parametrics methods are analyzed using R program which is a popular statistical program.

• Transactions of the Korean Society of Pressure Vessels and Piping
• /
• v.11 no.2
• /
• pp.31-39
• /
• 2015

Pipe wall-thinning by flow-accelerated corrosion (FAC) and various types of erosion is a significant and costly damage phenomenon in secondary piping systems of nuclear power plants (NPPs). Most NPPs have management programs to ensure pipe integrity due to wall-thinning that includes periodic measurements for pipe wall thicknesses using ultrasonic tests (UTs). Nevertheless, thinning evaluations are not easy because the amount of thickness reduction being measured is often quite small compared to the accuracy of the inspection technique. U.S. Electric Power Research Institute (EPRI) had proposed Total Point Method (TPM) as a thinning occurrence evaluation method, which is a very useful method for detecting locally thinned pipes or fittings. However, evaluation engineers have to discern manually the measurement data because there are no numerical algorithm for TPM. In this study, numerical algorithms were developed based on non-parametric and parametric statistical method.

• Journal of the Institute of Electronics and Information Engineers
• /
• v.50 no.3
• /
• pp.9-15
• /
• 2013

Recent works on ad hoc network study have shown that achievable throughput can be made to scale linearly with the number of receive antennas even if the transmitter has only a single antenna. In this paper, we propose a non-parametric linear minimum mean square error (MMSE) receiver for achieving further gain in performance when the channel state information at receiver (CSIR) of interferers is imperfect. The key feature to make our approach effective is to exploit the autocorrelation of the received signal. In fact, by incorporating the desired channel information on top of the observations including interference and noise only, the proposed method achieves large fraction of the optimal MMSE transmission capacity without transmission rate loss. From the SINR analysis as well as transmission capacity simulations in realistic ad hoc network system, we show that the proposed non-parametric linear MMSE receiver brings substantial performance gain over existing multiple receive antenna algorithms.

• The Korean Journal of Financial Management
• /
• v.20 no.2
• /
• pp.73-94
• /
• 2003

In general, the interest rate is forecasted by the parametric method which assumes the interest rate follows a certain distribution. However the method has a shortcoming that forecasting ability would decline when the interest rate does not follow the assumed distribution for the stochastic behavior of interest rate. Therefore, the nonparametric method which assumes no particular distribution is regarded as a superior one. This paper compares the interest rate forecasting ability between the two method for the Monetary Stabilization Bond (MSB) market in Korea. The daily and weekly data of the MSB are used during the period of August 9th 1999 to February 7th 2003. In the parametric method, the drift term of the interest rate process shows the linearity while the diffusion term presents non-linear decline. Meanwhile in the nonparametric method, both drift and diffusion terms show the radical change with nonlinearity. The parametric and nonparametric methods present a significant difference in the market price of interest rate risk. This means in forecasting the interest rate and the market price of interest rate risk, the nonparametric method is more appropriate than the parametric method.

• Steel and Composite Structures
• /
• v.45 no.2
• /
• pp.175-191
• /
• 2022

A review of previous studies shows that although there is a considerable difference between buckling loads of structures under follower and non-follower lateral loads, only the buckling load of FGM elliptical cylindrical shell under non-follower lateral load was investigated in the literature. This study is the first to obtain the buckling load of elliptical FGM cylindrical shells under follower lateral load and also make a comparison between buckling loads of elliptical FGM cylindrical shells under follower and non-follower lateral loads. Moreover, this research is the first one to derive the load potential function of elliptical cylindrical shell. In this regard, the FGM cylindrical elliptical shell was modeled using the semi-analytical finite strip method and based on the First Shear Deformation Theory (FSDT). The shell is discretized by strip elements aligned in the longitudinal direction. The Lagrangian and harmonic shape functions were considered in the circumference and longitudinal directions, respectively. The buckling pressure of the shell under follower and non-follower lateral loads was obtained from eigenvalue problem. The results obtained from the model were compared with those presented in the literature to evaluate the validity of the model. A comparison index was defined to compare the buckling loads of the shell under follower and non-follower lateral load. A parametric study was carried out to investigate the effects of material properties and shell geometry characteristics on the comparison index. For the elliptical cylindrical shells with length-to-radius ratio greater than 16 and major-to-minor axis ratio greater than 0.6, the comparison index reaches to more than 20 percent which is significant. Moreover, the maximum difference is about 30 percent in some cases. The results obtained from the parametric study indicate that the buckling load of long elliptical cylindrical shell under non-follower load is not reliable.

• The Transactions of The Korean Institute of Electrical Engineers
• /
• v.64 no.9
• /
• pp.1288-1296
• /
• 2015

The ac side current of a line commutated converter(LCC) high voltage direct current (HVDC) is characterized by highly non-sinusoidal waveform. If the harmonic current is allowed to flow in the connected ac network, it may cause unacceptable levels of distortion. Therefore, ac side filters are required as part of the total HVDC converter station, in order to reduce the harmonic distortion of the ac side current and voltage to acceptably low levels. The ac filters are also employed to compensate the requested reactive power because LCC HVDC also consume substantial reactive power. Among different types of filters, triple-tuned filters have been widely utilized for HVDC system. This paper presents two design methods of triple-tuned filter; equivalent method and parametric method. Using a parametric method, in particular this paper proposes a design algorithm for a triple tuned filter. Finally, the performance of the design algorithm is evaluated for a 250kV HVDC system in Jeju island. The results cleary demonstrate the effectiveness of proposed design method in harmonics reduction.