• International journal of advanced smart convergence
• /
• 제9권4호
• /
• pp.42-51
• /
• 2020

In this paper, the authors propose the pseudo complex correlation coefficient (PCCC) of the two complex random variables (RV), because the four real correlation coefficients (RCC) of the corresponding four real RVs cannot be obtained only from the complex correlation coefficient (CCC) of given two complex RV. Such observation is motivated by the general statement; "The complex jointly-Gaussian random M-vector cannot be completely described by the complex covariance matrix, even though the real Gaussian random 2M-vector can be completely descried by the real covariance matrix. Therefore, in order to describe completely the complex jointly-Gaussian random M-vector, we need an additional matrix, namely the complex pseudo-covariance matrix, along with the complex covariance matrix." Then, we apply PCCC to correlated information sources (CIS) for non-orthogonal multiple access (NOMA) in 5G system, and investigate impact of the proposed PCCC on the achievable data rate of the stronger channel user in the conventional successive interference cancellation (SIC) NOMA with CIS. It is shown that for the given same CCC, the achievable data rates with the different PCCC are different, because the corresponding RCC are different. We also show that as the absolute value of the same CCC increases, the impact of the different PCCC becomes more significant.

• 대한기계학회논문집
• /
• 제17권5호
• /
• pp.1106-1114
• /
• 1993

본 연구에서는우수한 섬유강화 고분자복합판의 제조 및 개량을 섬유구조의 분리. 배향의 관점에서 연구한다. 유리섬유매트는 유리섬유를 50mm의 길이로 균일하 게 절단하여 공기중에서 분산시켜 6~7mm두께로 만들고,이 유리섬유매트를 바늘의 종류와 스트레칭 횟수에 따라 니들펀칭하여 유리섬유의 매트구조를 변화시킨다. 유리 섬유의 매트구조 별로 모재와 적층시킨 다음 열압축프레스를 사용하여 1차로 시이트를 제작하고, 이 제작된 시이트를 가열로로 가열하여 2차 고온압축 프레스성형한다. 이 때 섬유와 모재의 분리 및 배향의 상관관계를 나타내는 상관계수를 구하고, 이 계수에 미치는 매트 구조의 영향에 대한 실험결과를 보고한다.

• Communications for Statistical Applications and Methods
• /
• 제22권6호
• /
• pp.665-674
• /
• 2015

Lack of a general matrix formula hampers implementation of the semi-partial correlation, also known as part correlation, to the higher-order coefficient. This is because the higher-order semi-partial correlation calculation using a recursive formula requires an enormous number of recursive calculations to obtain the correlation coefficients. To resolve this difficulty, we derive a general matrix formula of the semi-partial correlation for fast computation. The semi-partial correlations are then implemented on an R package ppcor along with the partial correlation. Owing to the general matrix formulas, users can readily calculate the coefficients of both partial and semi-partial correlations without computational burden. The package ppcor further provides users with the level of the statistical significance with its test statistic.

• 한국소음진동공학회:학술대회논문집
• /
• 한국소음진동공학회 2002년도 춘계학술대회논문집
• /
• pp.253-259
• /
• 2002

The rigid body characteristics (value of mass, Position of center of mass, moments and products of inertia) of mechanical systems can be identified from FRF data or vibration spectra of rigid body motion. Therefore the accuracy of rigid body characteristics is connected directly with the accuracy of measured data for rigid body motions. In this paper, a method of improving accuracy of measurement of rigid body motion is presented. Applying rigid body theory, ail translational and rotational displacements at a tentative point on the rigid body are calculated using the measured translational displacements for several points and transfer matrix. Then the estimated displacements for the identical points are calculated using the 6 displacements of the tentative Point and transfer matrix. By using correlation coefficient between measured and estimated displacements, we can detect the existence of errors that are contained in a certain measured displacement. Consequently, the improved rigid body motion with respect to a tentative point can be obtained by eliminating the contaminated data.

• Journal of the Korean Data and Information Science Society
• /
• 제23권5호
• /
• pp.1037-1044
• /
• 2012

Multivariate control charts for effectively monitoring every component in the dispersion matrix of multivariate normal process are considered. Through the numerical results, we noticed that the multivariate control charts based on sample statistic $V_i$ by Hotelling or $W_i$ by Alt do not work effectively when the correlation coefficient components in dispersion matrix are increased. We propose a combined procedure monitoring every component of dispersion matrix, which operates simultaneously both control charts, a chart controlling variance components and a chart controlling correlation coefficients. Our numerical results show that the proposed combined procedure is efficient for detecting changes in both variances and correlation coefficients of dispersion matrix.

• 응용통계연구
• /
• 제35권1호
• /
• pp.77-91
• /
• 2022

의학통계와 신용평가 분야에서 혼합분포함수를 판별하는 최적분류점 추정하기 위하여 판별력을 측정하는 다양한 정확도 측도들이 존재한다. 최근에 혼동행렬 빈도수로 표현되는 Matthews의 상관계수와 정밀도와 재현율의 조화평균인 F1 통계량의 정확도 측도들이 최적분류점을 추정하는데 연구되었다. 본 연구에서는 이런 정확도 측도들 중에서 표본크기에 의존하는 정확도 측도들은 두 표본크기 차이가 많은 경우에 최적분류점을 설정하는데 적절하지 않음을 발견한다. 그리고 대안적인 정확도 측도로 혼동행렬의 비율들의 함수인 상관계수를 정의하고, 이를 최대화하는 분류점을 최적분류점으로 추정하는 방법을 제안하고 이 방법의 유용성과 활용성에 대하여 토론한다.

• 응용통계연구
• /
• 제28권3호
• /
• pp.385-392
• /
• 2015

주성분분석은 차원축소를 위한 대표적 기법이다. 주성분분석에서 변수들이 측정단위가 다르거나 분산의 불균형이 심할 경우 흔히 변수를 표준화한 다음 분석할 것이 권장된다. 표준화 변환은 표준편차를 나누어주는 변환인데, 측정단위에 무관하게 만들기 위해서라면 평균을 나누어주는 변환도 고려해볼 수 있다. 표준화 변환을 한 다음 주성분분석하는 것은 상관행렬로 주성분분석하는 것과 같은데, 평균을 나누어주는 변환을 한 후 주성분분석하는 것은 변동계수와 관련된 행렬로 주성분분석하는 것과 같음을 보이고, 그렇게 변환을 한 다음 주성분분석을 실시하는 것이 왜 필요한가를 설명하였다.

• Bulletin of the Korean Chemical Society
• /
• 제33권9호
• /
• pp.2955-2960
• /
• 2012

Product ion yields in the in- and post-source decays of three peptide ions, $[Y_5X+H]^+$ (X = Y (tyrosine), K (lysine), and R (arginine)), generated by matrix-assisted laser desorption ionization (MALDI) were measured at six wavelengths, 307, 317, 327, 337, 347, and 357 nm, using ${\alpha}$-cyano-4-hydroxycinnamic acid (CHCA) and 2,5-dihydroxybenzoic acid (DHB) as the matrices. The temperatures of the early and late plumes generated by MALDI were estimated via kinetic analysis of the product ion yield data. For both matrices, the temperature drop (${\Delta}T$), i.e. the difference in the temperature between the early and late plumes, displayed negative correlation with the absorption coefficient. This was in agreement with the previous reasoning that deeper laser penetration and larger amount of material ablation arising from smaller absorption coefficient would result in larger extent of expansion cooling. The results support the postulation of the expansion cooling occurring in the plume presented previously.

• Journal of applied mathematics & informatics
• /
• 제26권3_4호
• /
• pp.471-479
• /
• 2008

Let $R\;{\in}\;C^{m{\times}m}$ and $S\;{\in}\;C^{n{\times}n}$ be nontrivial unitary involutions, i.e., $R^*\;=\;R\;=\;R^{-1}\;{\neq}\;I_m$ and $S^*\;=\;S\;=\;S^{-1}\;{\neq}\;I_m$. We say that $G\;{\in}\;C^{m{\times}n}$ is a generalized reflexive matrix if RGS = G. The set of all m ${\times}$ n generalized reflexive matrices is denoted by $GRC^{m{\times}n}$. In this paper, an efficient method for the least squares solution $X\;{\in}\;GRC^{m{\times}n}$ of the matrix equation AXB = D with arbitrary coefficient matrices $A\;{\in}\;C^{p{\times}m}$, $B\;{\in}\;C^{n{\times}q}$and the right-hand side $D\;{\in}\;C^{p{\times}q}$ is developed based on the canonical correlation decomposition(CCD) and, an explicit formula for the general solution is presented.

• 융합신호처리학회논문지
• /
• 제23권3호
• /
• pp.143-149
• /
• 2022

This excerpt delineates a quantitative measure of relationship between a research title and its respective abstract extracted from different journal articles documented through a Korean Citation Index (KCI) database published through various journals. In this paper, we propose a machine learning-based similarity metric that does not assume normality on dataset, realizes the imbalanced dataset problem, and zero-variance problem that affects most of the rule-based algorithms. The advantage of using this algorithm is that, it eliminates the limitations experienced by Pearson correlation coefficient (r) and additionally, it solves imbalanced dataset problem. A total of 107 journal articles collected from the database were used to develop a corpus with authors, year of publication, title, and an abstract per each. Based on the experimental results, the proposed algorithm achieved high correlation coefficient values compared to others which are cosine similarity, euclidean, and pearson correlation coefficients by scoring a maximum correlation of 1, whereas others had obtained non-a-number value to some experiments. With these results, we found that an effective title must have high correlation coefficient with the respective abstract.