• Journal of the Korean Data and Information Science Society
• /
• 제17권3호
• /
• pp.785-794
• /
• 2006

Suggested is an EM algorithm for estimation in mixture of shifted Poisson distributions with known shift parameters. For this type of mixture distribution, we have to utilize values of shift parameters to determine whether each of data belongs to some component distribution. We propose a method of estimating values of component information and then follow typical EM methodology. Simulation results show that the algorithm provides reasonable performance for the distribution.

• 대한전기학회논문지
• /
• 제40권2호
• /
• pp.144-153
• /
• 1991

This paper presents an algorithm to improve accuracy and reliability in the state estimation of contaminated bad data. The conventional algorithms for detection of bad data have the problems of excessive memory requirements and long computation time. In order to overcome these problems, a measurement compensation approach is proposed to reduce computation time, and the partitioned measurement error model has the advantage of remarkable reduction in computation time and memory requirements in estimated error computation. The proposed algorithm has been tested for IEEE sample systems, which shows its applicability to on-line power systems.

• 산업공학
• /
• 제11권2호
• /
• pp.191-197
• /
• 1998

Having a reliable standard time data is very important for productivity improvement of any manufacturing company. In this study we present an estimation procedure of standard time data for companies having multi-item extremely small quantity production type and discuss a case study. Included in the discussion are the importance of setup time reduction and the roles of management supervisors, and labor.

• Communications for Statistical Applications and Methods
• /
• 제12권2호
• /
• pp.323-333
• /
• 2005

In this paper, we develop a MCMC method for estimating the skew normal distributions. The method utilizing the data augmentation technique gives a simple way of inferring the distribution where fully parametric frequentist approaches are not available for small to moderate sample cases. Necessary theories involved in the method and computation are provided. Two numerical examples are given to demonstrate the performance of the method.

• International Journal of Reliability and Applications
• /
• 제2권1호
• /
• 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.

• 산업경영시스템학회지
• /
• 제15권25호
• /
• pp.53-62
• /
• 1992

Computer software users develop and utilize their application software by themselves since Processing methods are different by quantity and qualify of the information The developed model needs input data and error numbers generated during the testing phases. However. total error numbers of the existing model and each error time was needed as data for developing the new model. But, maximum likelihood estimation must be used to exponential model of binomial-type and estimating of parameters by using the searched data. Parameter estimation can be done with trial and error or simulation.

• Journal of applied mathematics & informatics
• /
• 제6권2호
• /
• pp.661-668
• /
• 1999

Reliability estimation using Gibbs sampler considered for modeling mixture exponential reliability problems. Gibbs sampler is developed to compute the features of the posterior distribution. Bayesian estimation of complicated functions requires simpler esti-mation techniques due to the mathematical difficulties involved in the Bayes approach. The Maximum likelihood estimator and the Gibbs estimator of reliability of the system are derived. By simula-tion risk behaviors of derived estimators are compared. model de-termination based on relative error is considered. A numerical study with a simulated data set is provided.

• 제어로봇시스템학회:학술대회논문집
• /
• 제어로봇시스템학회 2002년도 ICCAS
• /
• pp.69.2-69
• /
• 2002

Process measurements contain random and gross errors and the size estimation of gross errors is required for production accounting. Mixed integer programming technique had been applied to identify and estimate the gross errors simultaneously. However, the compensate model based on mixed integer programming used all measured variables or spanning tree as gross error candidates. This makes gross error estimation problem combinatorial or computationally expensive. Mixed integer programming with test statistics is proposed for computationally inexpensive gross error identification /estimation. The gross error candidates are identified by measurement test and the set of gross error candidates are...

• 대한전기학회논문지
• /
• 제37권4호
• /
• pp.232-239
• /
• 1988

The approximate overdetermined method is proposed for high resolution spectral estimation in case of short data record length or narrow band signal. And a new recursive AR parameter estimation is derived in the form of fast algorithm. For ARMA spectral estimation, two stage procedure is used in estimating ARMA parameters. First AR parameters are estimated by using the modified Yule-Walker equations, and then MA parameters are implicitly estimated by estimating numerator spectral(NS) coefficients.

• 한국환경과학회지
• /
• 제19권12호
• /
• pp.1375-1384
• /
• 2010

The purpose of this research is to understand the change of runoff characteristics by estimated spatial rainfall. Therefore, this paper largely composed of two parts. First, we compared the simulated result according to estimation method, ID(Inverse Distance Method, ID2(Inverse Square Distance Method), and Kr(General Covariance Kriging Method), after letting miss rainfall data to the observed data. Second, we reviewed the runoff characteristics of the distributed runoff model according to the estimated spatial rainfall. On the basis of Yuseong water level station, we select the target basin as Gabchun watershed. We assumed 1 point or 2 point of the 6 rainfall gauge stations in watershed were missed. We applied the spatial rainfall distributed by Kr to Hy-GIS GRM, distributed runoff model. When 1 point rainfall data is missed, Kr is superior to others in point rainfall estimation and runoff estimation of Hy-GIS GRM. However, in case rainfall data of 2 points is missed, all of three methods did not give suitable result for them. In conclusion, Kr showed better applicability than other estimated methods if rainfall's data less than 2 points is missed.