Browsing by Author "Hsu, YL"

Now showing 1 - 6 of 6

Bayesian analysis of Box-Cox transformed linear mixed models with ARMA(p, q) dependence
(2005-08-01)
Lee, JC
;
Lin, TI
;
Lee, KJ
;
Hsu, YL
;
統計學研究所
In this paper, we present a Bayesian inference methodology for Box-Cox transformed linear mixed model with ARMA(p, q) errors using approximate Bayesian and Markov chain Monte Carlo methods. Two priors are proposed and put into comparisons in parameter estimation and prediction of future values. The advantages of Bayesian approach over maximum likelihood method are demonstrated by both real and simulated data. (c) 2004 Elsevier B.V. All rights reserved.
Bayesian analysis of growth curves with AR(1) dependence
(1997-11-15)
Lee, JC
;
Hsu, YL
;
統計學研究所
;
Institute of Statistics
In this paper we consider Bayesian analysis of the generalized growth curve model when the covariance matrix Sigma = sigma(2)C where C=(rho(i-j)), sigma(2) > 0 and -1 < rho < 1 are unknown. We consider both parameter estimation and prediction of future values. Results are illustrated with real and simulated data. (C) 1997 Elsevier Science B.V.
Derivation of variable soft sphere model parameters in direct-simulation Monte Carlo method using quantum chemistry computation
(2003-12-01)
Wu, JS
;
Hsu, YL
;
機械工程學系
;
Department of Mechanical Engineering
A practical procedure for deriving parameters of the variable soft sphere (VSS) molecular model for the Lennard-Jones potential of gas species in the direct-simulation Monte Carlo (DSMC) method is introduced. Intermolecular potential energy is fitted through the Lennard-Jones (L-J) potential, which is obtained by quantum chemistry computation. Computed L-J potentials are then used to compute viscosity and diffusivity coefficients for like and unlike molecules, respectively, based on gas kinetics theory. Related parameters of the VSS molecular model are derived by fitting these computed coefficients to those derived from the VSS model. Test results for O-2-H-2 Mixtures using this procedure are in good agreement with existing data. VSS parameters for silicon-based species frequently encountered in the chemical vapor deposition process are derived as an example to illustrate the importance of this procedure in extending the applicability of the DSMC computation to gas species other than air-related species.
Estimation and prediction of generalized growth curve with grouping variances in AR(q) dependence structure
(2003)
Lee, JC
;
Hsu, YL
;
統計學研究所
;
Institute of Statistics
In this paper we consider maximum likelihood analysis of generalized growth curve model with the Box-Cox transformation when the covariance matrix has AR(q) dependence structure with grouping variances. The covariance matrix under consideration is Sigma = DsigmaCDsigma where C is the correlation matrix with stationary autoregression process of order q, q < p and D-σ is a diagonal matrix with p elements divided into g(&LE; p) groups, i.e., D-σ is a function of {σ(1),..., σ(g)} and -1 < p < 1 and σ(l), l = 1,...g, are unknown. We consider both parameter estimation and prediction of future values. Results are illustrated with real and simulated data.
Molecular dynamics simulation of microscopic droplet spread on rough surfaces
(2001-09-01)
Hwang, CC
;
Jeng, YR
;
Hsu, YL
;
Chang, JG
;
機械工程學系
This study uses molecular dynamics simulations to elucidate the spreading behaviour of a liquid droplet oil a rough solid surface. The Lennard-Jones potential energy model is adopted as the interaction model between the liquid and the solid molecules. The paper considers two typos of rough surface: periodic and random. These surfaces are characterized by their roughness height and their spatial variation. For a periodic surface, the roughness height is defined by the amplitude, A, while for a random surface, it is defined in terms of the standard deviation of the roughness height, sigma. Regarding the spatial variation of the surface, a periodic surface is characterized by the wavelength, lambda, while the random surface is characterized by its autocorrelation length, L. Simulation results indicate that the characteristics of the rough surface can significantly influence spreading behaviour, in terms of final equilibrium time, spreading radius, and spreading topography. It is observed that the effects of roughness height and spatial variation are broadly similar for both periodic and random surfaces. It is found that increasing roughness height and decreasing spatial periodicity both prolong the final equilibrium time, and that the filial spreading radius decreases with increasing roughness height and increases with larger spatial periodicity.
Parallel implementation of molecular dynamics simulation for short-ranged interaction
(2005-08-01)
Wu, JS
;
Hsu, YL
;
Lee, YM
;
機械工程學系
;
Department of Mechanical Engineering
A parallel molecular dynamics simulation method, designed for large-scale problems, employing dynamic spatial domain decomposition for short-ranged molecular interactions is proposed. In this parallel cellular molecular dynamics (PCMD) simulation method, the link-cell data structure is used to reduce the searching time required for forming the cut-off neighbor list as well as for domain decomposition, which utilizes the multi-level graph-partitioning technique. A simple threshold scheme (STS), in which workload imbalance is monitored and compared with some threshold value during the runtime, is proposed to decide the proper time for repartitioning the domain. The simulation code is implemented and tested on the memory-distributed parallel machine, e.g., PC-cluster system. Parallel performance is studied using approximately one million L-J atoms in the condensed, vaporized and supercritical states. Results show that fairly good parallel efficiency at 49 processors can be obtained for the condensed and supercritical states (similar to 60%), while it is comparably lower for the vaporized state (-40%). (c) 2005 Elsevier B.V. All rights reserved.