• Journal of the Institute of Electronics Engineers of Korea SP
• /
• v.44 no.6
• /
• pp.93-99
• /
• 2007

Robust nonlinear image denoising algorithms for the class of ${\alpha}$-stable distribution are introduced. The proposed amplitude-limited sample average filter(ALSAF) proves to be the maximum likelihood estimator under the heavy-tailed Gaussian noise environments. The error norm for this estimator is equivalent to Huber#s minimax norm. It is optimal in the respect of maximizing the efficacy under the above noise environment. It is mired with the myriad filter to propose an amplitude-limited myriad filter(ALMF). The behavior and performance of the ALSAF and ALMF in ${\alpha}$-stable noise environment are illustrated and analyzed through simulation.

• Journal of Korean Institute of Industrial Engineers
• /
• v.17 no.1
• /
• pp.95-108
• /
• 1991

For the case where the lifetime at a constant stress level has exponential distribution, optimal accelerated life test plans are developed under the assumptions of intermittent inspection and Type I censoring. In a optimal plan, the low and high stress levels, the proportion of test units allocated and the inspection times at each stress are determined such that the asymptotic variance of the maximum likelihood estimator of logarithmic transformed mean at the use condition is minimized. In addition to the optimal plan in which numerical technique to solve the set of nonlinear equations must be employed to determine inspection times at each stress level, we also propose another plans which employ equally-spaced or equal probability inspection schemes at two overstress levels of corresponding optimal one. For both optimal and proposed plans, computational results indicate that the asymptotic variance of the estimated mean at the use stress is insensitive to number of inspections at overstress levels for the range of parameter values considered.

• Journal of the Korean Data and Information Science Society
• /
• v.7 no.2
• /
• pp.295-299
• /
• 1996

In this paper, optimal change times are determined for fully three-step stress accelerated life tests, which minimize the asymptotic variance for maximum likelihood estimator of logarithm of the failure rate at the usual condition and exponential distribution is given for life time data.

• 제어로봇시스템학회:학술대회논문집
• /
• 2001.10a
• /
• pp.167.5-167
• /
• 2001

Single point attitude determination method provides an optimal attitude minimizing the Wahba loss function. However, for the insufficient number of measurement vectors, the conventional single point methods has no unique solution. Thus, we introduce the sequential method to and an optimal attitude minimizing the windowed loss function. In this paper, this function is de ned as the sum of square errors for all measurement vectors within the axed sliding window. For simple implementation, the proposed algorithm is rewritten as a recursive form. Moreover, the covariance matrix is derived and expressed as a recursive form. Finally, we apply this algorithm to the attitude determination system with three LOS measurement sensors.

• 제어로봇시스템학회:학술대회논문집
• /
• 1987.10b
• /
• pp.464-469
• /
• 1987

The Kalman filter is an optimal linear estimator that has been an active research topic for the past three decades. The scheme has become the milestone of modern filtering, and it is applied to many areas including navigations and controls of free vehicle. The Kalman filter technique is matured. But some problems are still remained to be resolved. The prevention of divergence induced by digital implementation, nonoptimal application for nonlinear system, and application to non-Gaussian processes are some of the problems. This paper surveys the problems. The square root filtering is suggested to prevent the divergence. The extended Kalman filter is used for nonlinear systems. And, many other approaches to Kalman-like optimal estimators are also investigated.

• 전기의세계
• /
• v.30 no.8
• /
• pp.509-516
• /
• 1981

The optimal control theory is applied to the design of a digital control system for a nuclear reactor. A linear dynamic model obtained at 85% of rated power and a quadratic performance index are used. A minimal order observer used in cascade with the feedback controller is suggested as a state estimator. The total reactor power control is studied in the range of 80% to 100% of rated power, with the steady state and load-following control. The control algorithm considered is suitable for implementation in direct digital control.

• Journal of the Korean Statistical Society
• /
• v.19 no.2
• /
• pp.105-112
• /
• 1990

Let (X, Y) be a pair random variables and let f denote the regression function of the response Y on the measurement variable X. Let K(f) denote a derivative of f. The least squares method is used to obtain a tensor spline estimator $\hat{f}$ of f based on a random sample of size n from the distribution of (X, Y). Under some mild conditions, it is shown that $K(\hat{f})$ achieves the optimal rate of convergence for the estimation of K(f) in $L_2$ and $L_{\infty}$ norms.

• International Journal of Reliability and Applications
• /
• v.2 no.1
• /
• pp.49-56
• /
• 2001

In this paper we consider empirical Bayes estimation of the hazard rate and survival probabilities with right censored data under the assumption that the hazard function is constant over the period of observation and the prior distribution is gamma. We provide an estimator of the first derivative of the prior moment generating function that converges at each point to the true value in $L_2$ and use it to obtain, easy to compute, asymptotically optimal estimators under the squared error loss function.

• Journal of the Korea Society of Computer and Information
• /
• v.10 no.2 s.34
• /
• pp.21-30
• /
• 2005

In general, the robust estimation method is well known for a good statistical estimator that is insensitive to small departures from the idealized assumptions for which the estimation is optimized. While there are many existing robust estimation techniques that have been proposed in the literature, two main techniques used in computer vision are M-estimators and least-median of squares (LMS). Among these. we utilized the M-estimators since they are known to provide an optimal estimation of affine motion parameters. The M-estimators have higher statistical efficiency but tolerate much lower percentages of outliers unless properly initialized. To resolve these problems, we proposed an adaptive M-estimators algorithm that effectively separates outliers from non-outliers and estimate affine model parameters, using a continuous sigmoid weight function. The experimental results show the superiority of our method.

• The Journal of Korean Institute of Communications and Information Sciences
• /
• v.29 no.2C
• /
• pp.238-246
• /
• 2004

In this paper, an estimator that take advantages of time and frequency correlation within an OFDM symbol is investigated. OFDM systems using the proposed estimator can be very effective in detecting signals under non-sampled space and time-varying channels. Also, under same complexity, the proposed estimator outperforms the previously proposed estimator. Since even if there are no assumption about channel correlation, the linear interpolation method instead of optimal interpolation using correct channel correlation is proposed in case the receiver does not know the channel correlation function in time domain. Therefore the proposed channel estimator help improving the performance of OFDM systems under non-sampled spaced and fast time-varying channels.