• 한국지능시스템학회논문지
• /
• 제19권2호
• /
• pp.273-278
• /
• 2009

The determination of the associated weights in the theory of ordered weighted averaging (OWA) operators is one of the important issue. Recently, Wang and Parkan [Information Sciences 175 (2005) 20-29] proposed a minimax disparity approach for obtaining OWA operator weights and the approach is based on the solution of a linear program (LP) model for a given degree of orness. Recently, Liu [International Journal of Approximate Reasoning, accepted] showed that the minimum variance OWA problem of Fuller and Majlender [Fuzzy Sets and Systems 136 (2003) 203-215] and the minimax disparity OWA problem of Wang and Parkan always produce the same weight vector using the dual theory of linear programming. In this paper, we give an improved proof of the minimax disparity problem of Wang and Parkan while Liu's method is rather complicated. Our method gives the exact optimum solution of OWA operator weights for all levels of orness, $0\leq\alpha\leq1$, whose values are piecewise linear and continuous functions of $\alpha$.

• 대한전기학회논문지
• /
• 제45권3호
• /
• pp.399-406
• /
• 1996

This paper presents a method of hierarchical state estimation of the time-varying linear systems via Block-pulse function(BPF). When we estimate the state of the systems where noise is considered, it is very difficult to obtain the solutions because minimum error variance matrix having a form of matrix nonlinear differential equations is included in the filter gain calculation. Therefore, hierarchical approach is adapted to transpose matrix nonlinear differential equations to a sum of low order state space equation from and Block-pulse functions are used for solving each low order state space equation in the form of simple and recursive algebraic equation. We believe that presented methods are very attractive nd proper for state estimation of time-varying linear systems on account of its simplicity and computational convenience. (author). 13 refs., 10 figs.

• 전자공학회논문지B
• /
• 제30B권7호
• /
• pp.31-41
• /
• 1993

In this paper, a fuzzy adaptive controller is proposed for the process with large delay time and unmodelled dynamics. The fuzzy adaptive controller consists of self tuning controller and fuzzy tuning part. The self tuning controller is designed with the continuous time GMV (generalized minimum variance) using emulator and weighted least square method. It is realized by the hybrid method. The controller has robust characteristics by adapting the inference rule in design parameters. The inference processing is tuned according to the operating point of the process having the nonlinear characteristics considering the practical application. We review the characteristics of the fuzzy adaptive controller through the simulation. The controller is applied to practical electric furnace. As a result, the fuzzy adaptive controller shows the better characteristics than the simple numeric self tuning controller and the PI controller.

• 한국소음진동공학회:학술대회논문집
• /
• 한국소음진동공학회 2004년도 추계학술대회논문집
• /
• pp.1093-1096
• /
• 2004

Bearings are elementary machinery component which loads and do rotating motion. Excessive loads or many other reasons can cause incipient faults to be created and grown in each component. Moreover, it happens that incipient faults which were caused by manufacturing or assembling process' errors of the bearings are created. Finding the incipient faults as early as possible is necessary to the bearings in severe condition: high speed or frequently varying load condition, etc. How early we can detect the faults has to do with how the detection algorithm finds the fault information from measured signal. Fortunately, the bearing fault signal makes periodic impulse train. This information allows us to find the faults regardless how much noise contaminates the signal. This paper shows the basic signal processing idea and experimental results that demonstrate how good the method is.

• 품질경영학회지
• /
• 제41권1호
• /
• pp.149-162
• /
• 2013

Purpose: The purpose of this study was to design of a probabilistic model for optimum manpower planning in R&D department by Montecarlo simulation. Methods: We investigate the process and the requirement of manpower planning and scheduling in R&D department. The empirical distributions of necessary time and manpower for R&D projects are developed. From the empirical distributions, we can estimate a probability distribution of optimum manpower in R&D department. A simulation method of estimating the probability distribution of optimum manpower is considered. It is a useful tool for obtaining the sum, the variance and other statistics of the distributions. Results: The real industry cases are given and the properties of the model are investigated by Montecarlo Simulation. we apply the model to the research laboratory of the global company, and investigate and compensate the weak points of the model. Conclusion: The proposed model provides various and correct information such as average, variance, percentile, minimum, maximum and so on. A decision maker of a company can easily develop the future plan and the task of researchers may be allocated properly. we expect that the productivity can be improved by this study. The results of this study can be also applied to other areas including shipbuilding, construction, and consulting areas.

• 산업공학
• /
• 제23권3호
• /
• pp.257-263
• /
• 2010

Taguchi defined a good quality as 'A correspondence of product characteristic's expected value to the objective value satisfying the minimum variance condition.' For his good quality, he suggested Taguchi Method which is called Robust design which is irrelevant to the effect of these noise factors. Taguchi Method which has many success examples and which is used by many manufacturing industry. But Optimal solution of Taguchi Method is one among the experiments which is not optimal area of experiment point. On the other hand, Response Surface Method (RSM) which has advantage to find optimal solution area experiments points by approximate polynomial regression. But Optimal of RSM is depended on initial point and RSM can not use many factors because of a great many experiment. In this paper, we combine the Taguchi Method and the Response Surface Method with each advantage which is called Taguchi-RSM. Taguchi-RSM has two step, first step to find first solution by Taguchi Method, second step to find optimal solution by RSM with initial point as first step solution. We give example using catapults.

• 한국해양공학회:학술대회논문집
• /
• 한국해양공학회 2002년도 추계학술대회 논문집
• /
• pp.68-72
• /
• 2002

Localization with array sensors has been applied for not only military but also non-military purposes. The identification of submarines and fish finding are those examples. Nowadays the demand for noise identification is increasing to characterize noise sources and improve acoustic performance of underwater acoustic equipment. For that reason KRISO/KORDI recently constructed an anechoic basin which bus reflection only at the free surface. This paper suggests a noise identification methods using MUSIC algorithm in such an acoustic field. For comparison phase delay sum and minimum valiance methods are also described. At first basic principles are described. A several numerical simulations are also performed. The results say that reflection effect many cause a new non-real source although good estimation is obtained under no reflection conditions.

• 한국근적외분광분석학회:학술대회논문집
• /
• 한국근적외분광분석학회 2001년도 NIR-2001
• /
• pp.1244-1244
• /
• 2001

In linear discriminant analysis there are two important properties concerning the effectiveness of discriminant function modeling. The first is the separability of the discriminant function for different classes. The separability reaches its optimum by maximizing the ratio of between-class to within-class variance. The second is the stability of the discriminant function against noises present in the measurement variables. One can optimize the stability by exploring the discriminant variates in a principal variation subspace, i. e., the directions that account for a majority of the total variation of the data. An unstable discriminant function will exhibit inflated variance in the prediction of future unclassified objects, exposed to a significantly increased risk of erroneous prediction. Therefore, an ideal discriminant function should not only separate different classes with a minimum misclassification rate for the training set, but also possess a good stability such that the prediction variance for unclassified objects can be as small as possible. In other words, an optimal classifier should find a balance between the separability and the stability. This is of special significance for multivariate spectroscopy-based classification where multicollinearity always leads to discriminant directions located in low-spread subspaces. A new regularized discriminant analysis technique, the principal discriminant variate (PDV) method, has been developed for handling effectively multicollinear data commonly encountered in multivariate spectroscopy-based classification. The motivation behind this method is to seek a sequence of discriminant directions that not only optimize the separability between different classes, but also account for a maximized variation present in the data. Three different formulations for the PDV methods are suggested, and an effective computing procedure is proposed for a PDV method. Near-infrared (NIR) spectra of blood plasma samples from mastitic and healthy cows have been used to evaluate the behavior of the PDV method in comparison with principal component analysis (PCA), discriminant partial least squares (DPLS), soft independent modeling of class analogies (SIMCA) and Fisher linear discriminant analysis (FLDA). Results obtained demonstrate that the PDV method exhibits improved stability in prediction without significant loss of separability. The NIR spectra of blood plasma samples from mastitic and healthy cows are clearly discriminated between by the PDV method. Moreover, the proposed method provides superior performance to PCA, DPLS, SIMCA and FLDA, indicating that PDV is a promising tool in discriminant analysis of spectra-characterized samples with only small compositional difference, thereby providing a useful means for spectroscopy-based clinic applications.

• 한국근적외분광분석학회:학술대회논문집
• /
• 한국근적외분광분석학회 2001년도 NIR-2001
• /
• pp.1042-1042
• /
• 2001

In linear discriminant analysis there are two important properties concerning the effectiveness of discriminant function modeling. The first is the separability of the discriminant function for different classes. The separability reaches its optimum by maximizing the ratio of between-class to within-class variance. The second is the stability of the discriminant function against noises present in the measurement variables. One can optimize the stability by exploring the discriminant variates in a principal variation subspace, i. e., the directions that account for a majority of the total variation of the data. An unstable discriminant function will exhibit inflated variance in the prediction of future unclassified objects, exposed to a significantly increased risk of erroneous prediction. Therefore, an ideal discriminant function should not only separate different classes with a minimum misclassification rate for the training set, but also possess a good stability such that the prediction variance for unclassified objects can be as small as possible. In other words, an optimal classifier should find a balance between the separability and the stability. This is of special significance for multivariate spectroscopy-based classification where multicollinearity always leads to discriminant directions located in low-spread subspaces. A new regularized discriminant analysis technique, the principal discriminant variate (PDV) method, has been developed for handling effectively multicollinear data commonly encountered in multivariate spectroscopy-based classification. The motivation behind this method is to seek a sequence of discriminant directions that not only optimize the separability between different classes, but also account for a maximized variation present in the data. Three different formulations for the PDV methods are suggested, and an effective computing procedure is proposed for a PDV method. Near-infrared (NIR) spectra of blood plasma samples from daily monitoring of two Japanese cows have been used to evaluate the behavior of the PDV method in comparison with principal component analysis (PCA), discriminant partial least squares (DPLS), soft independent modeling of class analogies (SIMCA) and Fisher linear discriminant analysis (FLDA). Results obtained demonstrate that the PDV method exhibits improved stability in prediction without significant loss of separability. The NIR spectra of blood plasma samples from two cows are clearly discriminated between by the PDV method. Moreover, the proposed method provides superior performance to PCA, DPLS, SIMCA md FLDA, indicating that PDV is a promising tool in discriminant analysis of spectra-characterized samples with only small compositional difference.

• 한국항공우주학회지
• /
• 제37권1호
• /
• pp.36-41
• /
• 2009

임무를 수행하는데 있어 정확한 자세 정보는 필수적이다. 두 개 또는 그 이상의 관측벡터를 이용하는 자세 결정 알고리듬에는 크게 두 가지가 널리 알려져 있다. 하나는 결정적인 방법인 TRIAD 알고리듬이며, 다른 하나는 최적의 해를 찾는 방법인 QUEST 알고리듬이다. 본 논문은 TRIAD 알고리듬의 성능 향상과 서로 다른 정확도를 가진 센서의 조합을 이용한 자세 결정 방법을 제안하였다. 첫째, 보다 정확한 자세 행렬을 구하기 위하여 직교화 방법을 이용하는 대신 방향 여현 행렬을 오일러 각으로 바꾸고, 분산 대신 공분산행렬을 고려하여 편향되지 않은 최소 공분산 기법을 적용하였다. 또한, 세 개 이상의 측정값이 주어졌을 경우 TRIAD 알고리듬을 적용할 수 있는 방법을 제안하였다. 제안된 평균 TRIAD 알고리듬의 성능은 서로 다른 센서의 조합을 가정하여 표준편차와 확률적 측면에서의 수치 시뮬레이션을 통해 분석되었다.