Misclassification in Size-Biased Modified Power Series Distribution and Its Applications

Anwar Hassan,Peer Bilal Ahmad 한국산업응용수학회(구 한국산업정보응용수학회) 2009 한국산업정보응용수학회 Vol.13 No.1

A misclassified size-biased modified power series distribution (MSBMPSD) where some of the observations corresponding to x=c+1 are misclassified as x = c with probability α, is defined. We obtain its recurrence relations among the raw moments, the central moments and the factorial moments. Discussion of the effect of the misclassification on the variance is considered. To illustrate the situation under consideration some of its particular cases like the size-biased generalized negative binomial (SBGNB), the size-biased generalized Poisson (SBGP) and size-biased Borel distributions are included. Finally, an example is presented for the size-biased generalized Poisson distribution to illustrate the results.

MISCLASSIFICATION IN SIZE-BIASED MODIFIED POWER SERIES DISTRIBUTION AND ITS APPLICATIONS

ANWAR HASSAN,PEER BILAL AHMAD 한국산업응용수학회 2009 Journal of the Korean Society for Industrial and A Vol.13 No.1

A misclassified size-biased modified power series distribution (MSBMPSD) where some of the observations corresponding to x = c + 1 are misclassified as x = c with probability α, is defined. We obtain its recurrence relations among the raw moments, the central moments and the factorial moments. Discussion of the effect of the misclassification on the variance is considered. To illustrate the situation under consideration some of its particular cases like the size-biased generalized negative binomial (SBGNB), the size-biased generalized Poisson (SBGP) and sizebiased Borel distributions are included. Finally, an example is presented for the size-biased generalized Poisson distribution to illustrate the results.

영상 정규화 기반 영상 워터마킹 기법

姜渙一 명지대학교 산업기술연구소 2006 産業技術硏究所論文集 Vol.25 No.-

This paper proposes an image watermarking method based on the XYS image normalization. Through the experiments, the watermarking method using the XYS image normalization is superior to the method proposed by the work[3]. The proposed method is robust to the geometrical attack. In addition, the flipping and aspect ratio can be shown to be expressible by the central moments.

Recurrence Formula for the Central Moments of Number of Successes with n Poisson Trials

Moon, Myung-Sang The Korean Data and Information Science Society 2003 한국데이터정보과학회지 Vol.14 No.2

A sequence of n Bernoulli trials which violates the constant success probability assumption is termed as "Poisson trials". In this paper, the recurrence formula for the r-th central moment of number of successes with n Poisson trials is derived. Romanovsky's method, based on the differentiation of characteristic function, is used in the derivation of recurrence formula for the central moments of conventional binomial distribution. Romanovsky's method is applied to that of Poisson trials in this paper. Some central moment calculation results are given to compare the central moments of Poisson trials with those of conventional binomial distribution.

Recurrence Formula for the Central Moments of Number of Successes with n Poisson Trials

Myung Sang Moon 한국데이터정보과학회 2003 한국데이터정보과학회지 Vol.14 No.2

A sequence of n Bernoulli trials which violates the constant success probability assumption is termed as "Poisson trials". In this paper, the recurrence formula for the ??-th central moment of number of successes with n Poisson trials is derived. Romanovsky`s method, based on the differentiation of characteristic function, is used in the derivation of recurrence formula for the central moments of conventional binomial distribution. Romanovsky`s method is applied to that of Poisson trials in this paper. Some central moment calculation results are given to compare the central moments of Poisson trials with those of conventional binomial distribution.

한국어 치조마찰음 /ㅅ/의 모음 환경에 따른 음향 특성

허혜정(Hye Jeong Heo),성철재(Cheol Jae Seong) 사단법인 한국언어학회 2015 언어학 Vol.0 No.72

This study presents the acoustic characteristics of Korean alveolar fricative /s/, articulated by 2 groups of children. The subjects were 18 three-year-old children and 18 seven-year-olds reportedly without articulation problems. They have lived in Daejeon. The test material was comprised of 14 categories: 7 CV syllables /si, se, sa, s?, so, su, s?/ and 7 VCV syllables /isi, ese, asa, ?s?, oso, usu, ?s?/. By using spectral moment variables such as skewness, center of gravity(c.o.g., hereafter), kurtosis and central moment, the spectral characteristics of the [pure noise + aspiration] of [s] was measured. As a result, the values of all of the variables taken from each subject group(3-year-olds and 7-year-olds) showed a statistically meaningful difference among 7 vowel environments and syllable structures. Regardless of the syllable structures, when the high vowels /i, u, ?/ and /s/ combined, both 3-year-olds and 7-year-olds showed no significant distinction with respect to the skewness and c.o.g.. But in case of /se, sa, s?, so/, a meaningful difference was observed. This explains that 3-year-olds" articulation was imperfect compared with that of 7-year-olds.. This is because that when pronouncing high-vowel combined /si, su, s?/, one simply has to control lips from the articulation /s/ while /se, sa, s?, so/ require more complex chin movement for the following vowels. When compared by vowel environment, both 3-year-old and 7-year-old groups showed a statistitically meaningful difference between /si/ and /se, sa, s?, so, su/. The fact that the combination of vowel /i/ and /s/ is comparatively easy articulation seems to lead to the uniqueness of /si/. In case of the 3-year-old group, /so-su/ and /so-s?/, and /su-s?/ relations showed meaningful differences. /so/ shows lower spectral distribution compared with /su & s?/. Although the labialization process of /su/ has the front cavity lengthened, /s?/ shows much lower spectral distribution compared to that of /su/. The 3-year-olds’ immatured articulation seems to make this happen.

Tutorial: Dimension reduction in regression with a notion of sufficiency

Yoo, Jae Keun The Korean Statistical Society 2016 Communications for statistical applications and me Vol.23 No.2

In the paper, we discuss dimension reduction of predictors ${\mathbf{X}}{\in}{{\mathbb{R}}^p}$ in a regression of $Y{\mid}{\mathbf{X}}$ with a notion of sufficiency that is called sufficient dimension reduction. In sufficient dimension reduction, the original predictors ${\mathbf{X}}$ are replaced by its lower-dimensional linear projection without loss of information on selected aspects of the conditional distribution. Depending on the aspects, the central subspace, the central mean subspace and the central $k^{th}$-moment subspace are defined and investigated as primary interests. Then the relationships among the three subspaces and the changes in the three subspaces for non-singular transformation of ${\mathbf{X}}$ are studied. We discuss the two conditions to guarantee the existence of the three subspaces that constrain the marginal distribution of ${\mathbf{X}}$ and the conditional distribution of $Y{\mid}{\mathbf{X}}$. A general approach to estimate them is also introduced along with an explanation for conditions commonly assumed in most sufficient dimension reduction methodologies.

정보 삽입률을 위한 영상 정규화 기법 비교

全石環,姜渙一 명지대학교 산업기술연구소 2005 産業技術硏究所論文集 Vol.24 No.-

In this paper we propose the preprocessing method for the watermarking against the general affine transformation. To tackle the general affine transformation attack, we use the image normalization before the watermark is inserted into the original image. We compare the three image normalization methods[4,9,10] for the watermark embedding rate. All the three method are based on the x-shearing, y-shearing, and the scaling decomposition using the central moments Through the experiment, we show that the second method given by Zhang et. al[4] is superior to the other two methods given by Zhang et. al[9] and Dons et. al[10].

모멘트 기반 영상 정보 예측에 관한 연구

姜渙一 明知大學校 産業技術硏究所 2005 産業技術硏究所論文集 Vol.24 No.-

In this paper we propose the estimation method for the image affine information. The first method is based on the eigenvalues and eigenvectors for the covariance matrix of the given image, The second method is based on the x-shearing, y-shearing and the scaling decomposition using the specific relationships of the central moments for the specific transformation matrix. In addition we estimate the rotation and the aspect ratio information using the central moments of the reference image and the sensed image. Through the experiment, the second method has better performance than the first method.

COMPARISON OF CENTRALIZED AND MULTI-LAYER ARCHITECTURES FOR NONLINEAR MODEL PREDICTIVE TORQUE-VECTORING AND TRACTION CONTROL

Rini Gabriele,De Bernardis Martino,Bottiglione Francesco,Hartavi Ahu Ece,Sorniotti Aldo 한국자동차공학회 2023 International journal of automotive technology Vol.24 No.4

A significant body of literature discusses direct yaw moment controllers for vehicle stability control and torque-vectoring (TV), based on model predictive control. However, the available references lack an analysis of the effect of including or excluding the wheel dynamics in the prediction model in combined longitudinal and lateral acceleration conditions, which is related to the control system architecture. In fact, in the first case, the controller can also fulfill the wheel slip control function, according to a centralized architecture, while in the second case, the tire slip limitation has to be implemented externally, in a multi-layer approach. This study addresses the identified gap by proposing and comparing – through simulations with a high-fidelity vehicle model – centralized and multilayer real-time implementable architectures using nonlinear model predictive control (NMPC) for the TV and traction control (TC) of an electric vehicle with front in-wheel motors. An optimization routine calibrates the main controller parameters, to ensure fairness in the comparison during extreme accelerating-while-cornering maneuvers with transient steering inputs. The results show that the real-time implementable multi-layer architecture with wheel dynamics in the NMPC prediction model, and considering the externally generated TC torque reduction in the TV layer, provides equivalent performance to a centralized set-up.