• Journal of the Korean Statistical Society
• /
• v.25 no.4
• /
• pp.515-527
• /
• 1996

It has been known for mean field models that the limiting distribution reflecting the asymptotic behavior of the system is non-Gaussian at the critical state. Recently, however, Papangelow showed for the critical Curie-Weiss mean field model that there exist Gaussian structures in the asymptotic behavior of the total magnetization. We construct Gaussian structures existing in the internal fluctuation of the system for the critical case of a generalized Curie-Weiss mean field model.

• Journal of the Korean Institute of Telematics and Electronics A
• /
• v.29A no.3
• /
• pp.1-7
• /
• 1992

This paper discusses the self-adaptive equalization technique which has adaptibility to channel characteristics varation without training sequence. The criterion function used in this paper is based on the concept of cumulant matching. This function can be applied to nonminimum phase channel, and we can verify the fact that if the constrained condition is satisfied. this criterion has no local optimum. As the adaption algorithm, the normalized gradient-searching technique is used. Simulations verify the performance of our method in case of 8PAM, 8PSK(CCITT V.27), 16QAM(CCITT V.29) sources and three type nonminimum phase channels.

• Proceedings of the KIEE Conference
• /
• 2007.07a
• /
• pp.571-573
• /
• 2007

본 논문에서는 전력계통의 신뢰도를 확률적인 관점에서 접근하고 평가 할 수 있는 신뢰도평가 시스템의 기본 개념과 설계를 소개한다． 확률기반 신뢰도 평가시스템은 Enumeration 기반，Cumulant 기반， Monte-Carlo 시뮬레이션 기반의 세 가지 기법을 사용하여 신뢰도를 평가하도록 설계하였다．

• Journal of the Korean Chemical Society
• /
• v.48 no.4
• /
• pp.339-350
• /
• 2004

The simplified cumulant method was applied to diffraction data of $CClF_3$ to study the equilibrium molecular parameters over a range of temperatures. The molecular parameters of $CClF_3$ by the simplified cumulant method were compared with those from the traditional method. Also the instrumentation of picosecond time resolved electron diffraction (TRED) and the experimental details are described. The total experimental temporal resolution was discussed in terms of the electron pulse width. The TRED system was applied to study the molecular structures for $CClF_3$ at room temperature. The molecular structural parameters $CClF_3$ from TRED are compared with those from GED/RT. The molecular parameters ($r_e$)of bonded C-F and C-Cl for $CClF_3$ by simplified CA are 132.00(2) pm and 175.20(3) pm, respectively, by using GED/RT. From the results of TRED experiments $r_a$ for bonded C-F and C-Cl are 132.23(13) pm and 177.23(19) pm.

• Journal of Korea Water Resources Association
• /
• v.42 no.6
• /
• pp.433-443
• /
• 2009

For the better understanding of the temporal characteristics of soil water, this study is to suggest a stochastic soil water model and to apply it for impact assessment of climate change. The loss function is divided into 3 stages for more specified comprehension of the probabilistic behavior of soil water, and especially, the soil water model considering the stochastic characteristics of precipitation is developed in order to consider the variation of climatic factors. The simulation result of soil water model confirms that the proposed soil water model can re-generate the observation properly, and it also proves that the soil water behaves with consistent cycle based on the precipitation pattern. Moreover, with the simulation results with a climate change scenario, it can be predicted that the future soil water will have higher variations than present soil water.

• The Journal of the Institute of Internet, Broadcasting and Communication
• /
• v.18 no.4
• /
• pp.85-90
• /
• 2018

This paper compares the adaptive eualization performance of CR-MMA (Constellation Reduction-MMA) and CR-MMA (Constellation Matching-MMA) in order to minimization of intersymbol interference that is occur in channel for 2-dimensional QAM signal. For obtain the error signal in order to updating the tap coefficient of conventional adaptive equalization algorithm MMA, the CR-MMA converts the constellation reduction concept of high order 2-dimensional QAM nonconstant modulus signal to constant modulus signal and the CM-MMA use the constellation matchine error concept in order to force the matching the $2^{nd}$ and $4^{th}$ cumulant of equalizer output and transmitted signal constellation. By applying the different method for getting the error signal, these algorithm are possible to obtain the improved equalization performance compared to the conventional MMA algorithm, the improved performance of CR-MMA and CM-MMA were compared by computer simulation in this paper. As a result of simulation, the CM-MMA has more better performance in the equalizer internal performance than CR-MMA, but not in equalizer external performance as in SER.

• The Transactions of the Korean Institute of Electrical Engineers
• /
• v.40 no.1
• /
• pp.1-9
• /
• 1991

This paper describes a new method of calculating expected energy generation and loss of load probability (L.O.L.P) for electric power system operation and expansion planning. The method represents an equivalent load duration curve (E.L.D.C) as a mixture of cumulants approximation (M.O.N.A). By regarding a load distribution as many normal distributions-rather than one normal distribution-and representing each of them in terms of Gram-Charlier expansion, we could improve the accuracy of results. We developed an algorithm which automatically determines the number of distribution and demarcation points. In modeling of a supply system, we made subsets of generators according to the number of generator outage: since the calculation of each subset's moment needs to be processed rapidly, we further developed specific recursive formulae. The method is applied to the test systems and the results are compared with those of cumulant, M.O.N.A. and Booth-Baleriaux method. It is verified that the M.O.C.A. method is faster and more accure than any other method.

• The Korean Journal of Applied Statistics
• /
• v.14 no.2
• /
• pp.333-344
• /
• 2001

통계적 추론에 사용되는 많은 통계량들은 평균벡터의 평활함수의 형태로 표현이 가능하다. 본 연구에서는 이들 통계량들의 분포함수에 대한 안부점근사법을 제시하였다. 이 방법은 Na(1998)에서 제시된 일반적 통계량의 분포함수에 대한 안부점근사법이 평균벡터의 평활함수모형에 특히 유용하게 사용될 수 있음을 보인 것이다. 이 근사법은 정규근사에 비해 근사의 정도가 뛰어나며, 특히 통계량의 꼬리부분의 확률에 대해서도 정확도가 그대로 유지되는 장점이 있어 정밀한 추론이 요구되는 많은 문제에 효과적으로 사용될 수 있다. 모의 실험에 사용할 평균벡터의 평활함수 모형으로는 스튜던트화 분산을 고려하였다.

• Proceedings of the Korean Institute of Intelligent Systems Conference
• /
• 2000.11a
• /
• pp.305-309
• /
• 2000

In this paper, we presents a new methodology for face recognition after analysing conventional ICA(Independent Component Analysis) based approach. In the literature we found that ICA based methods have followed the same procedure without any exception, first PCA(Principal Component Analysis) has been used for feature extraction, next ICA learning method has been applied for feature enhancement in the reduced dimension. However, it is contradiction that features are extracted using higher order moments depend on variance, the second order statistics. It is not considered that a necessary component can be located in the discarded feature space. In the new methodology, features are extracted using the magnitude of kurtosis(4-th order central moment or cumulant). This corresponds to the PCA based feature extraction using eigenvalue(2nd order central moment or variance). The synergy effect of PCA and ICA can be achieved if PCA is used for noise reduction filter. ICA methodology is analysed using SVD(Singular Value Decomposition). PCA does whitening and noise reduction. ICA performs the feature extraction. Simulation results show the effectiveness of the methodology compared to the conventional ICA approach.

• Proceedings of the Korean Society of Computer Information Conference
• /
• 2009.01a
• /
• pp.49-54
• /
• 2009

A fuzzy weighted mean method on a 2D shape recognition system is introduced in this paper. The bispectrum based on third order cumulant is applied to the contour sequence of each image for the extraction of a feature vector. This bispectral feature vector, which is invariant to shape translation, rotation and scale, represents a 2D planar image. However, to obtain the best performance, it should be considered certain criterion on the calculation of weights for the fuzzy weighted mean method. Therefore, a new method to calculate weights using means by differences of feature values and their variances with the maximum distance from differences of feature values. is developed. In the experiments, the recognition results with fifteen dimensional bispectral feature vectors, which are extracted from 11.808 aircraft images based on eight different styles of reference images, are compared and analyzed.