• Journal of the Korean Data and Information Science Society
• /
• v.27 no.2
• /
• pp.565-575
• /
• 2016

In this paper, we develop the noninformative priors for the linear combinations of means in the exponential distributions. We develop the matching priors and the reference priors. The matching priors, the reference prior and Jeffreys' prior for the linear combinations of means are developed. It turns out that the reference prior and Jeffreys' prior are not a matching prior. We show that the proposed matching prior matches the target coverage probabilities much more accurately than the reference prior and Jeffreys' prior in a frequentist sense through simulation study, and an example based on real data is given.

• Communications for Statistical Applications and Methods
• /
• v.19 no.6
• /
• pp.799-808
• /
• 2012

It is known that human disease and the economic traits of livestock are significantly affected by a gene combination effect rather than a single gene effect. Existing methods to study this gene combination effect have disadvantages such as heavy computing, cost and time; therefore, to overcome those drawbacks, the SNPHarvester was developed to find the main gene combinations. In this paper, we looked for gene combinations using an adjusted linear regression model. This research finds that superior gene combinations which are related to the quality of the Korean beef cattle among sets of SNPs using SNPHarvester. We also identify the superior genotypes using a decision tree that can enhance the various qualities of Korean beef among selected a SNP combination.

• Journal of Communications and Networks
• /
• v.12 no.6
• /
• pp.577-581
• /
• 2010

We introduce a novel packet retransmission technique which improves the efficiency of automatic retransmission query (ARQ) protocols in the context of satellite broadcast/multicast systems. The proposed coded ARQ technique, similarly to fountain coding, performs transmission of redundant packets, which are made by linear combinations of the packets composing the source block. Differently from fountain codes, the packets for the linear combinations are selected on the basis of the retransmission requests coming from the user terminals. The selection is performed in a way that, at the terminals, the source packets can be recovered iteratively by means of simple back-substitutions. This work aims at providing a simple and efficient alternative to reliable multicast protocols based on erasure correction coding techniques.

• Asian-Australasian Journal of Animal Sciences
• /
• v.15 no.7
• /
• pp.925-931
• /
• 2002

Gibbs sampling algorithms were implemented to the multi-trait threshold animal models with any combinations of multiple binary, ordered categorical, and linear traits and investigate the amount of bias on these models with two kinds of parameterization and algorithms for generating underlying liabilities. Statistical models which included additive genetic and residual effects as random and contemporary group effects as fixed were considered on the models using simulated data. The fully conditional posterior means of heritabilities and genetic (residual) correlations were calculated from 1,000 samples retained every 10th samples after 15,000 samples discarded as "burn-in" period. Under the models considered, several combinations of three traits with binary, multiple ordered categories, and continuous were analyzed. Five replicates were carried out. Estimates for heritabilities and genetic (residual) correlations as the posterior means were unbiased when underlying liabilities for a categorical trait were generated given by underlying liabilities of the other traits and threshold estimates were rescaled. Otherwise, when parameterizing threshold of zero and residual variance of one for binary traits, heritability estimates were inflated 7-10% upward. Genetic correlation estimates were biased upward if positively correlated and downward if negatively correlated when underling liabilities were generated without accounting for correlated traits on prior information. Residual correlation estimates were, consequently, much biased downward if positively correlated and upward if negatively correlated in that case. The more categorical trait had categories, the better mixing rate was shown.

• Structural Engineering and Mechanics
• /
• v.30 no.1
• /
• pp.77-97
• /
• 2008

In this paper, a strut-and-tie model approach has been proposed to directly calculate the amount of reinforcements in deep beams, and the force transfer mechanisms for this approach were investigated using linear finite element analysis. The proposed strut-and-tie model provides quite similar force transfer mechanisms to the results of linear finite element analysis for the 28 deep beams. The load-carrying capacities calculated from the proposed method are both accurate and conservative with little scatter or trends for the 214 deep beams. The deep beams have different concrete strengths including high-strength, various combinations of web reinforcements, and wide range of and a/d ratios. Good accuracy was also obtained using VecTor2, nonlinear finite element analysis tool based on the Modified Compression Field Theory. Since the proposed method provides a safe and reliable means for design of deep beams, this can serve to improve design provisions in future adjustments and development of design guidelines.

• Journal of Korea Multimedia Society
• /
• v.14 no.8
• /
• pp.965-980
• /
• 2011

In this paper, the use of conditional Fuzzy C-Means (CFCM) aimed at estimation of desired states of an unknown digital communication channel is investigated for blind channel equalization. In the proposed CFCM, a collection of clustered centers is treated as a set of pre-defined desired channel states, and used to extract channel output states. By considering the combinations of the extracted channel output states, all possible sets of desired channel states are constructed. The set of desired states characterized by the maximal value of the Bayesian fitness function is subsequently selected for the next fuzzy clustering epoch. This modification of CFCM makes it possible to search for the optimal desired channel states of an unknown channel. Finally, given the desired channel states, the Bayesian equalizer is implemented to reconstruct transmitted symbols. In a series of simulations, binary signals are generated at random with Gaussian noise, and both linear and nonlinear channels are evaluated. The experimental studies demonstrate that the performance (being expressed in terms of accuracy and speed) of the proposed CFCM is superior to the performance of the existing method exploiting the "conventional" Fuzzy C-Means (FCM).

• 제어로봇시스템학회:학술대회논문집
• /
• 2000.10a
• /
• pp.20-20
• /
• 2000

Back-propagation neural network (BPNN) is the most prevalently used paradigm in modeling semiconductor manufacturing processes, which as a neuron activation function typically employs a bipolar or unipolar sigmoid function in either hidden and output layers. In this study, applicability of another linear function as a neuron activation function is investigated. The linear function was operated in combination with other sigmoid functions. Comparison revealed that a particular combination, the bipolar sigmoid function in hidden layer and the linear function in output layer, is found to be the best combination that yields the highest prediction accuracy. For BPNN with this combination, predictive performance once again optimized by incrementally adjusting the gradients respective to each function. A total of 121 combinations of gradients were examined and out of them one optimal set was determined. Predictive performance of the corresponding model were compared to non-optimized, revealing that optimized models are more accurate over non-optimized counterparts by an improvement of more than 30%. This demonstrates that the proposed gradient-optimized teaming for BPNN with a linear function in output layer is an effective means to construct plasma models. The plasma modeled is a hemispherical inductively coupled plasma, which was characterized by a 24 full factorial design. To validate models, another eight experiments were conducted. process variables that were varied in the design include source polver, pressure, position of chuck holder and chroline flow rate. Plasma attributes measured using Langmuir probe are electron density, electron temperature, and plasma potential.

• Coupled systems mechanics
• /
• v.8 no.4
• /
• pp.351-375
• /
• 2019

The present work investigates the use of a rigid rocking block as a tool to reduce vibrations in a frame structure. The study is based on a simplified model composed by a 2-DOF linear system, meant to represent a general M-DOF frame structure, coupled with a rocking rigid block through a linear visco-elastic device, which connects only the lower part of the 2-DOF system. The possibility to restrain the block directly to the ground, by means of a second visco-elastic device, is investigated as well. The dynamic response of the model under an harmonic base excitation is then analysed in order to evaluate the effectiveness of the coupling in reducing the displacements and the drift of the 2-DOF system. The nonlinear equations of motion of the coupled assemblage 2-DOF-block are obtained by a Lagrangian approach and then numerically integrated considering some reference mechanical and geometrical quantities as variable parameters. It follows an extensive parametric analysis, whose results are summarized through behaviour maps, which portray the ratio between the maximum displacements and drifts of the system, with and without the coupling with the rigid block, for several combinations of system's parameters. When the ratio of the displacements is less than unity, the coupling is considered effective. Results show that the presence of the rocking rigid block improves the dynamics of the system in large ranges of the characterizing parameters.

• The Korean Journal of Ecology
• /
• v.8 no.3
• /
• pp.127-132
• /
• 1985

In this study, the competitive development of leaf in Amaranthus and Chenopodium were invesitgated by the complemented plastochron index. The value of PI for Amaranthus was not varied with competional ratios, while for Chenopodium it was varied. Namely in Chenopodium, the plastochron 1 was increased as competitional combinations, the plastochron 2 was decreased. These results indicated Amaranthus had advantage in competition over Chenopodium. It is surmised that these results were exhibited differences in photosynthetic pathway between Amaranthus (C4 plant) and Chenopodium (C3 plant). The linear patterns were clearly demonstrated by the differences in leaf arrangement between Amaranthus (alternate type) and Chenopodium (opposite type). From these resultss, use of plastochron seems to a useful means of evaluating plat response to various environments.

• Journal of the Earthquake Engineering Society of Korea
• /
• v.1 no.4
• /
• pp.1-9
• /
• 1997

This paper examined various aspects of a linear and a nonlinear response spectrum method in seismic response analysis of multi-story building structures. The response spectrum method that has been widely used in the analysis of linear structures was proposed different mode superposition method by several ivestigators, and the differences between combinations with an elastic modal analysis reviwed closely. It seems, however, that this method is not used to nonlinear seismic analysis. It is the purpose of this paper to propose an alternative method by means of which a nonlinear MDOF structure with long period may be analysed by an extention of response spectrum method. For nonlinear seismic analysis of high-rise building structures using technique proposed in this study, it is intended to serve primarily as a tool in preliminary designs instead of time history analysis.