• Animal Bioscience
• /
• v.35 no.5
• /
• pp.648-658
• /
• 2022

Objective: The identification of nonlinear mixed models that describe the growth trajectory of New Zealand rabbits was performed based on weight records and carcass measures obtained using ultrasonography. Methods: Phenotypic records of body weight (BW) and loin eye area (LEA) were collected from 66 animals raised in a didactic-productive module of cuniculture located in the southern Piaui state, Brazil. The following nonlinear models were tested considering fixed parameters: Brody, Gompertz, Logistic, Richards, Meloun 1, modified Michaelis-Menten, Santana, and von Bertalanffy. The coefficient of determination (R²), mean squared error, percentage of convergence of each model (%C), mean absolute deviation of residuals, Akaike information criterion (AIC), and Bayesian information criterion (BIC) were used to determine the best model. The model that best described the growth trajectory for each trait was also used under the context of mixed models, considering two parameters that admit biological interpretation (A and k) with random effects. Results: The von Bertalanffy model was the best fitting model for BW according to the highest value of R² (0.98) and lowest values of AIC (6,675.30) and BIC (6,691.90). For LEA, the Logistic model was the most appropriate due to the results of R² (0.52), AIC (783.90), and BIC (798.40) obtained using this model. The absolute growth rates estimated using the von Bertalanffy and Logistic models for BW and LEA were 21.51g/d and 3.16 cm², respectively. The relative growth rates at the inflection point were 0.028 for BW (von Bertalanffy) and 0.014 for LEA (Logistic). Conclusion: The von Bertalanffy and Logistic models with random effect at the asymptotic weight are recommended for analysis of ponderal and carcass growth trajectories in New Zealand rabbits. The inclusion of random effects in the asymptotic weight and maturity rate improves the quality of fit in comparison to fixed models.

• Journal of Ecology and Environment
• /
• v.48 no.2
• /
• pp.196-206
• /
• 2024

Background: Most of the biomass equations were developed using sample trees collected mainly from pan-tropical and tropical regions that may over- or underestimate biomass. Site-specific models would improve the accuracy of the biomass estimates and enhance the country's measurement, reporting, and verification activities. The aim of the study is to develop site-specific biomass estimation models and validate and evaluate the existing generic models developed for pan-tropical forest and newly developed allometric models. Total of 140 trees was harvested from each diameter class biomass model development. Data was analyzed using SAS procedures. All relevant statistical tests (normality, multicollinearity, and heteroscedasticity) were performed. Data was transformed to logarithmic functions and multiple linear regression techniques were used to develop model to estimate aboveground biomass (AGB). The root mean square error (RMSE) was used for measuring model bias, precision, and accuracy. The coefficient of determination (R² and adjusted [adj]-R²), the Akaike Information Criterion (AIC) and the Schwarz Bayesian information Criterion was employed to select most appropriate models. Results: For the general total AGB models, adj-R² ranged from 0.71 to 0.85, and model 9 with diameter at stump height at 10 cm (DSH₁₀), ρ and crown width (CW) as predictor variables, performed best according to RMSE and AIC. For the merchantable stem models, adj-R² varied from 0.73 to 0.82, and model 8) with combination of ρ, diameter at breast height and height (H), CW and DSH₁₀ as predictor variables, was best in terms of RMSE and AIC. The results showed that a best-fit model for above-ground biomass of tree components was developed. AGB_Stem = exp {-1.8296 + 0.4814 natural logarithm (Ln) (ρD²H) + 0.1751 Ln (CW) + 0.4059 Ln (DSH₃₀)} AGB_Branch = exp {-131.6 + 15.0013 Ln (ρD²H) + 13.176 Ln (CW) + 21.8506 Ln (DSH₃₀)} AGB_Foliage = exp {-0.9496 + 0.5282 Ln (DSH₃₀) + 2.3492 Ln (ρ) + 0.4286 Ln (CW)} AGB_Total = exp {-1.8245 + 1.4358 Ln (DSH₃₀) + 1.9921 Ln (ρ) + 0.6154 Ln (CW)} Conclusions: The results demonstrated that the development of local models derived from an appropriate sample of representative species can greatly improve the estimation of total AGB.

• Proceedings of the International Microelectronics And Packaging Society Conference
• /
• 2001.11a
• /
• pp.165-170
• /
• 2001

AIC$_3$:$^{t}$ BuNH$_2$단일 전구체를 이용하여 MOCVD방법에 의해 상압하에서 1$\mu\textrm{m}$의 두께로 증착하였다. 증착된 AIN 박막을 XRD, SEM, RBS 그리고 AES로 분석했으며 IDT전극을 형성하기 위해 1500＋ 의 두께로 증착했다. 중심주파수 1.5GHz를 갖고 입출력 개수가 각각 500개이며 IDT선폭이 l$\mu\textrm{m}$인 전송형의 SAW filter를 제작하고자 하였다.

• Annual Conference on Human and Language Technology
• /
• 2017.10a
• /
• pp.163-166
• /
• 2017

딥러닝은 모델이 복잡해질수록 Train 시간이 오래 걸리는 작업이다. Layer Normalization은 Train 시간을 줄이고, layer를 정규화 함으로써 성능을 개선할 수 있는 방법이다. 본 논문에서는 한국어 의미역 결정을 위해 Layer Normalization이 적용 된 Bidirectional LSTM CRF 모델을 제안한다. 실험 결과, Layer Normalization이 적용 된 Bidirectional LSTM CRF 모델은 한국어 의미역 결정 논항 인식 및 분류(AIC)에서 성능을 개선시켰다.

• The Korean Journal of Applied Statistics
• /
• v.22 no.1
• /
• pp.197-204
• /
• 2009

In the model selection problem, the main objective is to choose the true model from a manageable set of candidate models. An information criterion gauges the validity of a statistical model and judges the balance between goodness-of-fit and parsimony; "how well observed values ran approximate to the true values" and "how much information can be explained by the lower dimensional model" In this study, we introduce some information criteria modified from the Akaike Information Criterion (AIC) and the Bayesian Information Criterion(BIC). The information criteria considered in this study are compared via simulation studies and real application.

• 한국어정보학회:학술대회논문집
• /
• 2017.10a
• /
• pp.163-166
• /
• 2017

딥러닝은 모델이 복잡해질수록 Train 시간이 오래 걸리는 작업이다. Layer Normalization은 Train 시간을 줄이고, layer를 정규화 함으로써 성능을 개선할 수 있는 방법이다. 본 논문에서는 한국어 의미역 결정을 위해 Layer Normalization이 적용 된 Bidirectional LSTM CRF 모델을 제안한다. 실험 결과, Layer Normalization이 적용 된 Bidirectional LSTM CRF 모델은 한국어 의미역 결정 논항 인식 및 분류(AIC)에서 성능을 개선시켰다.

• Journal of the Korean Statistical Society
• /
• v.27 no.4
• /
• pp.397-405
• /
• 1998

We develop parametric bootstrap model selection criteria in an example to fit a random sample to either a general normal distribution or a normal distribution with prespecified mean. We apply the bootstrap methods in two ways; one considers the direct substitution of estimated parameter for the unknown parameter, and the other focuses on the bias correction. These bootstrap model selection criteria are compared with AIC. We illustrate that all the selection rules reduce to the one sample t-test, where the cutoff points converge to some certain points as the sample size increases.

• Communications for Statistical Applications and Methods
• /
• v.8 no.3
• /
• pp.589-601
• /
• 2001

Probabilities of overfilling for model selection criteria are derived for several different situations. First, one candidate model with one extra variable is compared to the current model. This is expanded to m candidate models. We show that these comparisons are not independent and discuss ovefitting probabilities. Correlation between two F-tests is derived. Finally, probabilities are computed using the dependent F distributions and F distributions based on order statistics of independent Chi-squares.

• 제어로봇시스템학회:학술대회논문집
• /
• 1994.10a
• /
• pp.106-111
• /
• 1994

We proposed a new variable sampling rate model which expresses the phenomena with both rapid and slow components. A method for determining the variable sampling rate and the older of the time series model was explained. The proposed variable sampling rate model was evaluated based oil an information criterion(AIC). Tile variable sampling rate model brought smaller an information criterion than one of a constant sampling rate model of conventional type, and was proved to be effective as a prediction model of the system with both rapid and slow components.

• 제어로봇시스템학회:학술대회논문집
• /
• 1988.10a
• /
• pp.289-294
• /
• 1988

This paper describes tbe design and implementation of the adaptive controller to maintain the glood weld quality in gas metal arc welding process. The weld torch travel speed and the surface temperature are taken, respectively, as an input and an output of the welding control system. Because of the very complex phenomena of the process, the input-output dynamic model was experimentally identified by AIC (Akiake Information Criterion). Based on the model structure, the explicit model reference adaptive controller is simulated in order to regulate the output tempernture to the desired level.