• 제목/요약/키워드: Generalized means

검색결과 243건 처리시간 0.023초

Pre-Adjustment of Incomplete Group Variable via K-Means Clustering

  • Hwang, S.Y.;Hahn, H.E.
    • Journal of the Korean Data and Information Science Society
    • /
    • 제15권3호
    • /
    • pp.555-563
    • /
    • 2004
  • In classification and discrimination, we often face with incomplete group variable arising typically from many missing values and/or incredible cases. This paper suggests the use of K-means clustering for pre-adjusting incompleteness and in turn classification based on generalized statistical distance is performed. For illustrating the proposed procedure, simulation study is conducted comparatively with CART in data mining and traditional techniques which are ignoring incompleteness of group variable. Simulation study manifests that our methodology out-performs.

  • PDF

ON GENERALIZED FINSLER STRUCTURES WITH A VANISHING hυ-TORSION

  • Ichijyo, Yoshihiro;Lee, Il-Yong;Park, Hong-Suh
    • 대한수학회지
    • /
    • 제41권2호
    • /
    • pp.369-378
    • /
    • 2004
  • A canonical Finsler connection Nr is defined by a generalized Finsler structure called a (G, N)-structure, where G is a generalized Finsler metric and N is a nonlinear connection given in a differentiable manifold, respectively. If NT is linear, then the(G, N)-structure has a linearity in a sense and is called Berwaldian. In the present paper, we discuss what it means that NT is with a vanishing hv-torsion: ${P^{i}}\;_{jk}\;=\;0$ and introduce the notion of a stronger type for linearity of a (G, N)-structure. For important examples, we finally investigate the cases of a Finsler manifold and a Rizza manifold.

A NOTE ON TWO NEW CLOSED-FORM EVALUATIONS OF THE GENERALIZED HYPERGEOMETRIC FUNCTION 5F4 WITH ARGUMENT $\frac{1}{256}$

  • B. R. Srivatsa Kumar;Dongkyu Lim;Arjun K. Rathie
    • 한국수학교육학회지시리즈B:순수및응용수학
    • /
    • 제30권2호
    • /
    • pp.131-138
    • /
    • 2023
  • The aim of this note is to provide two new and interesting closed-form evaluations of the generalized hypergeometric function 5F4 with argument $\frac{1}{256}$. This is achieved by means of separating a generalized hypergeometric function into even and odd components together with the use of two known sums (one each) involving reciprocals of binomial coefficients obtained earlier by Trif and Sprugnoli. In the end, the results are written in terms of two interesting combinatorial identities.

THE INCOMPLETE GENERALIZED τ-HYPERGEOMETRIC AND SECOND τ-APPELL FUNCTIONS

  • Parmar, Rakesh Kumar;Saxena, Ram Kishore
    • 대한수학회지
    • /
    • 제53권2호
    • /
    • pp.363-379
    • /
    • 2016
  • Motivated mainly by certain interesting recent extensions of the generalized hypergeometric function [Integral Transforms Spec. Funct. 23 (2012), 659-683] and the second Appell function [Appl. Math. Comput. 219 (2013), 8332-8337] by means of the incomplete Pochhammer symbols $({\lambda};{\kappa})_{\nu}$ and $[{\lambda};{\kappa}]_{\nu}$, we introduce here the family of the incomplete generalized ${\tau}$-hypergeometric functions $2{\gamma}_1^{\tau}(z)$ and $2{\Gamma}_1^{\tau}(z)$. The main object of this paper is to study these extensions and investigate their several properties including, for example, their integral representations, derivative formulas, Euler-Beta transform and associated with certain fractional calculus operators. Further, we introduce and investigate the family of incomplete second ${\tau}$-Appell hypergeometric functions ${\Gamma}_2^{{\tau}_1,{\tau}_2}$ and ${\gamma}_2^{{\tau}_1,{\tau}_2}$ of two variables. Relevant connections of certain special cases of the main results presented here with some known identities are also pointed out.

X-means 확장을 통한 효율적인 집단 개수의 결정 (Extensions of X-means with Efficient Learning the Number of Clusters)

  • 허경용;우영운
    • 한국정보통신학회논문지
    • /
    • 제12권4호
    • /
    • pp.772-780
    • /
    • 2008
  • K-means는 알고리즘의 단순함과 효율적인 구현이 가능함으로 인해 군집화를 위해 현재까지 널리 사용되는 방법 중 하나이다. 하지만 K-means는 집단의 개수가 사전에 결정되어야 하는 근본적인 문제점이 있다. 이 논문에서는 BIC(Bayesian information criterion) 점수를 이용하여 효율적으로 집단의 개수를 추정할 수 있는 X-means 알고리즘을 확장한 두 가지 알고리즘을 제안한다. 제안한 방법은 기본적으로 X-means 방법을 따르면서 집단이 임의의 분산 행렬을 가질 수 있도록 함으로써 X-means 알고리즘이 원형 집단만을 허용함에 따른 over-fitting을 개선한다. 제안한 방법은 하나의 집단에서 시작하여 계속해서 집단을 나누어가는 하향식 방법으로, BIC score를 최대로 증가시키는 집단을 분할해 나간다. 제안한 알고리즘은 Modified X-means(MX-means)와 Generalized X-means(GX-means)의 두 가지로, 전자는 K-means 알고리즘을, 후자는 EM 알고리즘을 사용하여 현재 주어진 집단들에서 최적의 분할을 찾아낸다. MX-means는 GX-means보다 그 속도에서 앞서지만 집단들이 중첩 된 경우에는 올바른 집단을 찾아낼 수 없는 단점이 있다. GX-means는 실행 속도가 느린 단점이 있지만 집단들이 중첩된 경우에도 안정적으로 집단들을 찾아낼 수 있다. 이러한 점들은 일련의 실험을 통해서 확인할 수 있으며, 제안한 방법들이 기존의 방법들에 비해 나은 성능을 보임을 확인할 수 있다.

Exact stochastic solution of beams subjected to delta-correlated loads

  • Falsone, G.;Settineri, D.
    • Structural Engineering and Mechanics
    • /
    • 제47권3호
    • /
    • pp.307-329
    • /
    • 2013
  • The bending problem of Euler-Bernoulli discontinuous beams is dealt with, in which the discontinuities are due to the loads and eventually to essential constrains applied along the beam axis. In particular, the loads are modelled as random delta-correlated processes acting along the beam axis, while the ulterior eventual discontinuities are produced by the presence of external rollers applied along the beam axis. This kind of structural model can be considered in the static study of bridge beams. In the present work the exact expression of the response quantities are given in terms of means and variances, thanks to the use of the stochastic analysis rules and to the use of the generalized functions. The knowledge of the means and the variances of the internal forces implies the possibility of applying the reliability ${\beta}$-method for verifying the beam.

극수비교에 의한 GF(3)의 일반화된 Reed-Muller 계수 생성 방법 (The Generation Method to Generalized Reed-Muller Coefficients over GF(3) by means of the Comparison of the Polarity)

  • 이철우;김흥수
    • 전기전자학회논문지
    • /
    • 제3권2호
    • /
    • pp.285-294
    • /
    • 1999
  • 본 논문에서는 다치논리 함수의 GRM(Generalized Reed-Huller)계수 생성 방법에 관하여 제안하였다 일반적인 GRM계수의 생성 방법은 Reed-Muller(RM) 전개식를 이용하여 극수 P=0의 RM계수를 구하고 이를 확장하여 모든 GRM계수를 구하는 방법을 사용한다. 본 논문에서 제안한 알고리즘은 모든 극수의 GRM계수를 구하지 않고 극수의 0의 개수를 순차적으로 비교해가며 GRM계수를 구하는 방식이다.

  • PDF

ON A GENERALIZED UPPER BOUND FOR THE EXPONENTIAL FUNCTION

  • Kim, Seon-Hong
    • 충청수학회지
    • /
    • 제22권1호
    • /
    • pp.7-10
    • /
    • 2009
  • With the introduction of a new parameter $n{\geq}1$, Kim generalized an upper bound for the exponential function that implies the inequality between the arithmetic and geometric means. By a change of variable, this generalization is equivalent to exp $(\frac{n(x-1)}{n+x-1})\;\leq\;\frac{n-1+x^n}{n}$ for real ${n}\;{\geq}\;1$ and x > 0. In this paper, we show that this inequality is true for real x > 1 - n provided that n is an even integer.

  • PDF