• The Journal of the Acoustical Society of Korea
• /
• v.22 no.7
• /
• pp.539-544
• /
• 2003

This paper describes how to reduce the effect of an occupation threshold by that the transform of mixture components of HMM parameters is controlled in hierarchical tree structure to prevent from over-adaptation. To reduce correlations between data elements and to remove elements with less variance, we employ PCA (Principal component analysis) and ICA (independent component analysis) that would give as good a representation as possible, and decline the effect of over-adaptation. When we set lower occupation threshold and increase the number of transformation function, ordinary MLLR adaptation algorithm represents lower recognition rate than SI models, whereas the proposed MLLR adaptation algorithm represents the improvement of over 2% for the word recognition rate as compared to performance of SI models.

• Asian-Australasian Journal of Animal Sciences
• /
• v.17 no.7
• /
• pp.914-918
• /
• 2004

The random regression model methodology was applied into the estimation of genetic parameters for body weights in Chinese Simmental cattle to replace the traditional multiple trait models. The variance components were estimated using Gibbs sampling procedure on Bayesion theory. The data were extracted for Chinese Simmental cattle born during 1980 to 2000 from 6 national breeding farms, where records from 3 months to 36 months were only used in this study. A 3 orders Legendre polynomial was defined as the submodel to describe the general law of that body weight changing with months of age in population. The heritabilities of body weights from 3 months to 36 months varied between 0.31 and 0.48, where the heritabilities from 3 months to 12 months slightly decreased with months of age but ones from 13 months to 36 months increased with months of age. Specially, the heritabilities at eighteenth and twenty-fourth month of age were 0.33 and 0.36, respectively, which were slightly greater than 0.30 and 0.31 from multiple trait models. In addition, the genetic and phenotypic correlations between body weights at different month ages were also obtained using regression model.

• Journal of the Korea Safety Management & Science
• /
• v.11 no.3
• /
• pp.209-216
• /
• 2009

A development in method of evaluating the measurement precisions using approximate F tests and variance components from expected mean square (EMS) is investigated. The research proposes three-factor mixed measurement models with the fixed and random factors. Unrestricted and unconstrained design work was rarely studied, while restricted and constrained designs have been significantly discussed. The unrestricted and unconstrained designs assume to be an independence of interaction. The proposed evaluation method about the measurement precisions can be extended to four-factor random measurement model or mixed measurement model. The study also presents the three evaluation indexes of precisions such as R&RTR (Reproducibility & Repeatability-To-Total Precision Ratio), PTR (Precision-To-Tolerance Ratio), and SNR (Signal-To-Noise Ratio). Numerical examples are proposed to evaluate the approximate F tests with Satterthwaite degrees of freedom and three indexes using the measurement precisions from EMS.

• Communications for Statistical Applications and Methods
• /
• v.26 no.4
• /
• pp.371-383
• /
• 2019

Panel data sets have been developed in various areas, and many recent studies have analyzed panel, or longitudinal data sets. Maximum likelihood (ML) may be the most common statistical method for analyzing panel data models; however, the inference based on the ML estimate will have an inflated Type I error because the ML method tends to give a downwardly biased estimate of variance components when the sample size is small. The under estimation could be severe when data is incomplete. This paper proposes the restricted maximum likelihood (REML) method for a random effects panel data model with a censored dependent variable. Note that the likelihood function of the model is complex in that it includes a multidimensional integral. Many authors proposed to use integral approximation methods for the computation of likelihood function; however, it is well known that integral approximation methods are inadequate for high dimensional integrals in practice. This paper introduces to use the moments of truncated multivariate normal random vector for the calculation of multidimensional integral. In addition, a proper asymptotic standard error of REML estimate is given.

• Structural Engineering and Mechanics
• /
• v.81 no.5
• /
• pp.565-574
• /
• 2022

The infrastructures such as offshore, bridges, power plant, oil and gas piping and aircraft operate in a harsh environment during their service life. Structural integrity of engineering components used in these industries is paramount for the reliability and economics of operation. Two regression models based on the concept of Gaussian process regression (GPR) and Minimax probability machine regression (MPMR) were developed to predict stress intensity factor range (𝚫K). Both GPR and MPMR are in the frame work of probability distribution. Models were developed by using the fatigue crack growth data in MATLAB by appropriately modifying the tools. Fatigue crack growth experiments were carried out on Eccentrically-loaded Single Edge notch Tension (ESE(T)) specimens made of API 5L X65 Grade steel in inert and corrosive environments (2.0% and 3.5% NaCl). The experiments were carried out under constant amplitude cyclic loading with a stress ratio of 0.1 and 5.0 Hz frequency (inert environment), 0.5 Hz frequency (corrosive environment). Crack growth rate (da/dN) and stress intensity factor range (𝚫K) values were evaluated at incremental values of loading cycle and crack length. About 70 to 75% of the data has been used for training and the remaining for validation of the models. It is observed that the predicted SIF range is in good agreement with the corresponding experimental observations. Further, the performance of the models was assessed with several statistical parameters, namely, Root Mean Square Error (RMSE), Mean Absolute Error (MAE), Coefficient of Efficiency (E), Root Mean Square Error to Observation's Standard Deviation Ratio (RSR), Normalized Mean Bias Error (NMBE), Performance Index (ρ) and Variance Account Factor (VAF).

• Journal of the Korean Data and Information Science Society
• /
• v.22 no.2
• /
• pp.287-296
• /
• 2011

Thirty six female students participated in the experiment of the fat mass weight loss. they kept diary for foods they ate every day, took a picture of the foods, transmitted the picture to the experimenter by the camera phone, and consulted him about fat mass loss once a week for 8 weeks period. Fat mass weight and its related factors of the students had been measured repeatedly every week during 8 weeks, The repeated measurement data were used for applying various random coefficient models. And hence optimal random coefficient model was selected. From the optimal model, the baseline, body mass index, diastolic blood pressure, total cholesterol and time of the fixed factors were very significant. The fixed quadratic time effect existed. The variance components corresponding to the subject effect, linear time effect of the random coefficients were all positive. Thus random coefficients up to the linear terms were considered as the optimal model. The treatment effect reduced the weight loss to an average of 2.1kg at the end of the period.

• Asian-Australasian Journal of Animal Sciences
• /
• v.15 no.7
• /
• pp.944-948
• /
• 2002

The aim of this study was to estimate heritability and repeatability for the number of embryos and transferable embryos collected per flush in Holstein population in Hokkaido, Japan. Data consisted of 306 MOET (Multiple Ovulation and Embryo Transfer) treatments on 224 Holstein cows from 1997 to 2000. Variance components for these traits were estimated using the REML procedure. The model included only non-genetic factors that were significant at the 0.05 level, through using generalized linear models, maximum likelihood methods, and stepwise regression procedure as fixed effects and sire and residual for heritabilities, donor and residual for repeatabilities as random effects. The factor identified as important in determining the results was the donor''s estrous condition after superovulation. Heritabilities for the number of embryos and transferable embryos collected per flush were 0.14 and 0.09, respectively. The corresponding repeatabilities were 0.43 and 0.32, respectively. These results show that it was difficult to genetically improve these traits, thus, environmental and physical factors affecting the donor must be improved. These results also show that it is necessary to take the donor''s estrous condition after superovulation and repeatabilities for the number of embryos and transferable embryos collected per flush into account when the genetic gains and inbreeding rates for MOET breeding schemes are predicted by a computer simulation.

• Journal of the Korea Institute of Military Science and Technology
• /
• v.25 no.5
• /
• pp.501-512
• /
• 2022

The purpose of the weapon live test during the phase of development is to provide essential information to decision makers that verify and validate the performance capabilities of weapons. Due to varying allocation and high variance of test resources with an increase in the weapon system's capability, the test environment can get highly complex, which can lead to a decrease in the reliability of test results. This issue can be addressed by applying a decision support system that provides various timely information collected by resources during the test process. The decision support system can be designed by applying the concept of digital twins, that are defined as digital replicas of components, systems and processes. This paper describes a design methodology of the decision support system that consists of digital models and service functions using digital twin architecture. A case study illustrates the feasibility of the proposed methodology in supporting the weapon live test process.

• Animal Bioscience
• /
• v.35 no.10
• /
• pp.1499-1511
• /
• 2022

Objective: This study was aimed to estimate the genetic parameters, including genetic and phenotypic correlations, of milk yield, lactation curve traits and milk composition of Thai dairy cattle from three government research farms. Methods: The data of 25,789 test-day milk yield and milk composition records of 1,468 cattle from lactation 1 to 3 of Holstein Friesian (HF) and crossbred HF dairy cattle calved between 1990 and 2015 from three government research farms in Thailand were analysed. 305-day milk yield was estimated by the Wood model and a test interval method. The Wood model was used for estimating cumulative 305-day milk yield, peak milk yield, days to peak milk yield and persistency. Genetic parameters were estimated using linear mixed models with herd, breed group, year and season of calving as fixed effects, and animals linked to a pedigree as random effects, together with a residual error. Univariate models were used to estimate variance components, heritability, estimated breeding values (EBVs) and repeatability of each trait, while pairwise bivariate models were used to estimate covariance components and correlations between traits in the same lactation and in the same trait across lactations. Results: The heritability of 305-day milk yield, peak milk yield and protein percentage have moderate to high estimates ranging from 0.19 to 0.45 while days to peak milk yield, persistency and fat percentage have low heritability ranging from 0.08 to 0.14 in lactation 1 cows. Further, heritability of most traits considered was higher in lactation 1 compared with lactations 2 and 3. For cows in lactation 1, high genetic correlations were found between 305-day milk yield and peak milk yield (0.86±0.07) and days to peak milk yield and persistency (0.99±0.02) while estimates of genetic correlations between the remaining traits were imprecise due to the high standard errors. The genetic correlations within the traits across lactation were high. There was no consistent trend of EBVs for most traits in the first lactation over the study period. Conclusion: Both the Wood model and test interval method can be used for milk yield estimates in these herds. However, the Wood model has advantages over the test interval method as it can be fitted using fewer test-day records and the estimated model parameters can be used to derive estimates of other lactation curve parameters. Milk yield, peak milk yield and protein percentage can be improved by a selection and mating program while days to peak milk yield, persistency and fat percentage can be improved by including into a selection index.

• Journal of Microbiology and Biotechnology
• /
• v.17 no.12
• /
• pp.1996-2004
• /
• 2007

In this study, the optimization of culture medium using a Sterigmatomyces elviae mutant was investigated using statistical analysis to increase the cell mass and lactosucrose ($^4G-{\beta}$-D-galactosylsucrose) production. In basal medium, the cell mass and lactosucrose production were 4.12 g/l and 140.91 g/l, respectively. However, because of the low cell mass and lactosucrose production, optimization of culture medium was carried out to increase the cell mass and lactosucrose production. Culture media were optimized by the S. elviae mutant using analysis of variance (ANOVA) and response surface methodology (RSM). Central composite designs using RSM were utilized in this investigation. Quadratic models were obtained for cell mass and lactosucrose production. In the case of cell mass, optimal components of the medium were as follows: sucrose 1.13%, yeast extract 0.99%, bactopeptone 2.96%, and ammonium sulfate 0.40%. The predicted maximum value of cell mass was about 5.20 g/l and its experimental value was 5.08 g/l. In the case of lactosucrose production, optimal components of the medium were as follows: sucrose 0.96%, yeast extract 1.2%, bactopeptone 3.0%, and ammonium sulfate 0.48%. Then, the predicted maximum value of lactosucrose production was about 194.12 g/l and the corresponding experimental value was about 183.78 g/l. Therefore, by culturing using predicted conditions, the real cell mass and lactosucrose production increased to 23.3% and 30.42%, respectively.