Yazar "Kozakli, Ozge" seçeneğine göre listele

Listeleniyor 1 - 3 / 3
  • Küçük Resim Yok
    Öğe
    Comparison of machine learning algorithms and multiple linear regression for live weight estimation of Akkaraman lambs
    (Springer, 2024) Kozakli, Ozge; Ceyhan, Ayhan; Noyan, Mevlut
    This study was designed to predict the post-weaning weights of Akkaraman lambs reared on different farms using multiple linear regression and machine learning algorithms. The effect of factors the age of the dam, gender, type of lambing, enterprise, type of flock, birth weight, and weaning weight was analyzed. The data was collected from a total of 25,316 Akkaraman lambs raised at multiple farms in the & Ccedil;iftlik District of Ni & gbreve;de province. Comparative analysis was conducted by using multiple linear regression, Random Forest, Support Vector Machines (and Support Vector Regression), Extreme Gradient Boosting (XGBoost) (and Gradient Boosting), Bayesian Regularized Neural Network, Radial Basis Function Neural Network, Classification and Regression Trees, Exhaustive Chi-squared Automatic Interaction Detection (and Chi-squared Automatic Interaction Detection), and Multivariate Adaptive Regression Splines algorithms. In this study, the test dataset was divided into five layers using the K-fold cross-validation method. The performance of models was compared using performance criteria such as Adjusted R-squared (Adj-\documentclass[12pt]{minimal} \usepackage{amsmath} \usepackage{wasysym} \usepackage{amsfonts} \usepackage{amssymb} \usepackage{amsbsy} \usepackage{mathrsfs} \usepackage{upgreek} \setlength{\oddsidemargin}{-69pt} \begin{document}$${R}<^>{2}$$\end{document}), Root Mean Square Error (RMSE), Mean Absolute Deviation (MAD), and Mean Absolute Percentage Error (MAPE) by utilizing test populations in the predicted models. Additionally, the presence of low standard deviations for these criteria indicates the absence of an overfitting problem. \documentclass[12pt]{minimal} \usepackage{amsmath} \usepackage{wasysym} \usepackage{amsfonts} \usepackage{amssymb} \usepackage{amsbsy} \usepackage{mathrsfs} \usepackage{upgreek} \setlength{\oddsidemargin}{-69pt} \begin{document}$${R}<^>{2}$$\end{document}The comparison results showed the Random Forest algorithm had the best predictive performance compared to other algorithms with Adj-\documentclass[12pt]{minimal} \usepackage{amsmath} \usepackage{wasysym} \usepackage{amsfonts} \usepackage{amssymb} \usepackage{amsbsy} \usepackage{mathrsfs} \usepackage{upgreek} \setlength{\oddsidemargin}{-69pt} \begin{document}$${R}<^>{2}$$\end{document}, RMSE, MAD, and MAPE values of 0.75, 3.683, 2.876, and 10.112, respectively. In conclusion, the results obtained through Multiple Linear Regression for the live weights of Akkaraman lambs were less accurate than the results obtained through artificial neural network analysis.
  • Küçük Resim Yok
    Öğe
    Modelling of Growth Curve Models According to Sex in Akkaraman Lambs with Different Methods: Logistik and Gompertz Modeling Example
    (Kahramanmaras Sutcu Imam Univ Rektorlugu, 2022) Kozakli, Ozge; Ceyhan, Ayhan; Ziya-Firat, Mehmet
    In this study, the live weight data of Akkaraman lambs reared in Nigde Omer Halisdemir University Ayhan Sahenk Agricultural Research Application and Research Center were analyzed. Among the growth curve models, Logistic and Gompertz growth models were estimated using Least Squares Estimation (LSE), Maximum Likelihood Estimation and Bayesian methods. LSE and Maximum Likelihood methods, which are from the frequency methods, were compared with other AIC, AICC and BIC values and the results suggested that the best model for both genders was LSE Gompertz model. For the Bayesian method, LSE estimation information used as a priori. The Gompertz model was selected for the two genders by comparing the models estimated with the Bayesian method according to their DIC values. At the end of the study, parameter point estimates of Gompertz Model for male Akkaraman lambs were beta(0) = 86.296, beta(1) = 2.778, beta(2) = 0.014; while parameter point values for female Akkaraman lambs were beta(0) = 54.784 beta(1) = 2.453, beta(2) = 0.014. In addition, the distributions of the model parameters with the Bayesian approach were estimated by the Markov Chain Monte Carlo (MCMC) method, and it was decided that the expected adult body weight of male Akkaraman lambs was higher than that of female Akkaraman lambs.
  • Küçük Resim Yok
    Öğe
    The survival analysis of some environmental factors associated with lamb mortality in Awassi sheep
    (Springer, 2023) Ceyhan, Ayhan; Kozakli, Ozge
    Most of the economic losses in the Turkish sheep industry are due to lamb deaths between birth and weaning period. Survival analysis is an essential step in the understanding of the lamb's survival function and the hazards that have an impact on mortality. The lamb records were accessed from 2013 to 2019, with the information of 11,523 lambs from birth to weaning at 90 days of age. The Kaplan-Meier method was used for the estimation of the survival function of the lambs. The Cox proportional hazards survival analysis was performed to evaluate the factors influencing Awassi lamb mortality in the central Anatolian region of Turkiye. A multivariable Cox regression was fitted to the data after checking the assumptions of the regression. Year of birth, lambing season, lamb sex, method of birth, and birth weight groups were used as explanatory variables. The overall survival of the lambs to weaning was 75.7%, and the Kaplan-Meier estimate of the average survival time to weaning was 62.25 days. Cox proportional hazards modeling showed that the hazard rate of death before weaning was higher in male lambs (1.205 and 95% CI, 1.119-1.300) compared to female lambs. It was also noted that the hazard rate of death (HR = 0.956 and 95% CI, 0.937-0.974) had significant years. The single-born lambs had a lower risk of death among the lambs. The summer and autumn seasons had a very highly advanced effect on the survival rate of the lambs. The hazard rate for the categorical birth weight group was 0.703 (95% CI, 0.667-0.741). This indicates that the risk of pre-weaning mortality decreased with increasing birth weight > 3.5 kg. The results of this study showed that lamb survival can be increased by paying more attention to winter born lambs, male sex, twin births, and lambs about birth weight (< 3.5 kg).