• Journal of information and communication convergence engineering
• /
• 제8권2호
• /
• pp.159-162
• /
• 2010

This paper presents a new Kurtosis driven Variable Step-Size Normalized Least Mean Square (KVSSN-LMS) algorithm to prevent repeater from oscillation due to feedback signal of radio frequency (RF) repeater. To get better Mean Square Error (MSE) performance, step-size is adjusted using the kurtosis. The proposed algorithm shows the better performance of steady state MSE. The proposed algorithm shows a better ERLE performance than that of KVSS-LMS, VSS-NLMS, NLMS algorithms.

• 한국해양공학회:학술대회논문집
• /
• 한국해양공학회 2006년 창립20주년기념 정기학술대회 및 국제워크샵
• /
• pp.127-134
• /
• 2006

Based on a weakly non-Gaussian theory the occurrence probability of freak waves is formulated in terms of the number of waves in a time series and the surface elevation kurtosis. Finite kurtosis gives rise to a significant enhancement of freak wave generation in comparison with the linear narrow banded wave theory. For fixed number of waves, the estimated amplification ratio of freak wave occurrence due to the deviation from the Gaussian theory is 50% - 300%. The results of the theory are compared with laboratory and field data.

• Structural Engineering and Mechanics
• /
• 제32권4호
• /
• pp.489-500
• /
• 2009

The aim of this paper is to compare wavelet, kurtosis and pseudofractal based techniques for structural health monitoring in the presence of measurement noise. A detailed comparison and assessment of these techniques have been carried out in this paper through numerical experiments for the calibration of damage extent of a simply supported beam with an open crack serving as an illustrative example. The numerical experiments are deemed critical due to limited amount of experimental data available in the field of singularity based detection of damage. A continuous detectibility map has been proposed for comparing various techniques qualitatively. Efficiency surfaces have been constructed for wavelet, kurtosis and pseudofractal based calibration of damage extent as a function of damage location and measurement noise level. Levels of noise have been identified for each technique where a sudden drop of calibration efficiency is observed marking the onset of damage masking regime by measurement noise.

• 응용통계연구
• /
• 제17권3호
• /
• pp.507-518
• /
• 2004

Malkovich & Afifi (1973)는 합교원리 (union-intersection principle)를 이용하여 왜도와 첨도를 다변량으로 일반화하였으나 이는 자료의 차원이 클 경우에는 사용이 용이하지 않다. 본 논문에서는 이러한 단점을 보완하는 이들의 근사통계량을 제안한다. 그리고 제안된 근사통계량, Malkovich & Afifi (1973)의 통 계 량, Mardia(1970)의 왜도와 첨도의 검 정력을 모의실험을 통하여 비교한다.

• 한국정밀공학회지
• /
• 제18권10호
• /
• pp.53-60
• /
• 2001

Surface roughness plays a significant role in friction, wear, and lubrication in machine components. Most engineering surfaces have the nongaussian height distribution. So, in this study, contact simulations are conducted for not only gaussian surfaces but also nongaussian surfaces. Nongaussian rough surface considering the kurtosis is generated numerically And the effects of kurtosis on real contact area fraction, average gap, and mean asperity contact pressure are studied. It will be shown that the real contact area fraction and the mean asperity contact pressure are sensitive to the characteristics of surface geometry according to kurtosis.

• Communications for Statistical Applications and Methods
• /
• 제28권5호
• /
• pp.463-475
• /
• 2021

Desgagné and de Micheaux (2018) proposed an alternative univariate normality test to the Jarque-Bera test. The proposed statistic is based on the sample second power skewness and kurtosis while the Jarque-Bera statistic uses sample Pearson's skewness and kurtosis that are the third and fourth standardized sample moments, respectively. In this paper, we generalize their statistic to a multivariate version based on orthogonalization or an empirical standardization of data. The proposed multivariate statistic follows chi-squared distribution approximately. A simulation study shows that the proposed statistic has good control of type I error even for a very small sample size when critical values from the approximate distribution are used. It has comparable power to the multivariate version of the Jarque-Bera test with exactly the same idea of the orthogonalization. It also shows much better power for some mixed normal alternatives.

• Communications for Statistical Applications and Methods
• /
• 제30권4호
• /
• pp.423-435
• /
• 2023

The Jarque and Bera (1980) statistic is one of the well known statistics to test univariate normality. It is based on the sample skewness and kurtosis which are the sample standardized third and fourth moments. Desgagné and de Micheaux (2018) proposed an alternative form of the Jarque-Bera statistic based on the sample second power skewness and kurtosis. In this paper, we generalize the statistic to a multivariate version by considering some data driven directions. They are directions given by the normalized standardized scaled residuals. The statistic is a modified multivariate version of Kim (2021), where the statistic is generalized using an empirical standardization of the scaled residuals of data. A simulation study reveals that the proposed statistic shows better power when the dimension of data is big.

• Journal of the Korean Data and Information Science Society
• /
• 제28권5호
• /
• pp.959-970
• /
• 2017

본 연구에서는 두 변수의 상관계수를 반영한 이변량 자료의 왜도와 첨도 통계량을 제안하고, 시각적으로 표현할 수 있는 표면그림을 개발한다. 이변량 왜도 통계량은 이변량 확률표본 자료의 치우침 방향과 정도를 표현하는 실수 한 쌍으로 정의한다. 첨도는 양의 값을 가지며 이변량 정규분포를 기준으로 꼬리 부분의 두터운 정도를 파악할 수 있다. 그리고 표면그림은 분위벡터를 바탕으로 평면에 구현한다. 다양한 형태의 이변량 자료를 생성하여 표면그림을 작성하고 왜도와 첨도를 계산하여 탐색해 본 결과, 왜도와 첨도 값들은 표면그림으로 구현한 이변량 자료의 특징을 잘 반영하는 것을 발견할였다. 그러므로 본 논문에서 제안한 왜도, 첨도 그리고 표면그림은 이변량 분포를 분석하는 기술통계학적 방법으로 활용할 수 있다.

• 정보처리학회논문지B
• /
• 제11B권4호
• /
• pp.429-436
• /
• 2004

본 논문에서는 침도를 추가한 뉴우턴법과 할선법에 기초한 고정점 알고리즘의 독립성분분석을 각각 제안하였다. 여기서 첨도의 추가는 유사한 속성을 가지는 성분의 군집화된 분석순서를 얻기 위함이고, 고정점 알고리즘은 학습파라미터와 무관한 빠른 성분분석과 우수한 분석성능을 얻기 위함이다. 제안된 두 가지 독립성분분석 각각을 500개 샘플을 가지는 6개의 혼합신호와 $512\times512$ 픽셀을 가지는 10개의 혼합영상 분리에 각각 적용한 결과, 제안된 두 가지 기법은 항상 일정한 분석순서를 유지하여 첨도가 추가되지 않은 기존의 기법들에서 알고리즘의 수행 때마다 랜덤하게 변하는 분석순서의 제약을 해결할 수 있었다. 특히 군집화의 속성을 가진 제안된 독립성분분석들은 신호나 영상의 분류나 식별에도 적용할 수 있다. 한편 할선법의 제안된 기법이 뉴우턴법의 제안된 기법보다 빠르면서도 우수한 분리성능이 있음을 확인하였다.

• 한국기계가공학회지
• /
• 제3권2호
• /
• pp.18-24
• /
• 2004

The effect of surface characterization parameters, such as surface roughness, skewness and kurtosis, on sliding friction and wear was studied experimentally. The friction coefficient was examined under the various parameters and sliding speed, normal load and type of lubricant with ball-on-disk type tribo-meter. The surface of the lower skewness in negative or the higher kurtosis between the same arithmetic mean value tends to indicate low friction.