Background: Statistical analyses have played a fundamental role in the scientific determination of production traits and environmental factors influencing meat productivity. In recent years, machine learning methods have been increasingly explored due to their potential to enhance the accuracy and efficiency of live weight prediction in sheep. 
 
Methods: In this study, the predictive performance of various machine learning algorithms for estimating body weight in Norduz sheep was comparatively evaluated. multilayer perceptron neural networks (MLPNN) and least squares support vector machines (LS-SVM) were employed, with various network configurations and hyperparameter combinations tested. Biometric measurements-namely age, height at withers (HW), body length (BL), chest width behind paddles (CW), chest depth (CD), chest girth (CG) and thigh circumference (TC)-were utilized as input variables, while body weight (BW) served as the target variable. 
 
Result: The MLPNN model configured using the Bayesian Regularization algorithm and the TanSig activation function yielded the lowest error rates and the highest generalization capability. Within the LS-SVM model, the most accurate predictions were obtained using the radial basis function (RBF) kernel, with optimal hyperparameters set at &sigma; = 5 and &gamma; = 10. Among the biometric traits, Chest Girth was identified as the most influential variable for predicting live weight across both models. Furthermore, Age and Height at Withers were found to be critical determinants in the neural network model, whereas Chest Depth and Chest Width were more prominent in the LS-SVM model.

Prediction of Norduz Sheep Live Weight using Multilayer Perceptron Neural Networks and Least Square Support Vector Machines

Background: Despite a remarkable growth track of the poultry industry over the last two decades, the challenges remain significantly dominant. The production decreased due to disease outbreaks. The stacking and confinements of fowl lead to widespread infections and a sharp decline in the productivity of farms. Rapid detection of diseases to prevent such outbreaks requires constant monitoring with minimum dependence on human intervention. Computer vision and the use of AI-enabled algorithms facilitate timely screening and surveillance of the flock to prevent disease spread. 
 
Methods: In this work, the sequential CNN model is used to explore the classification of diseases in poultry. The dataset is sourced from the Zenodo database and contains nearly 7,721 images. The preprocessing of the images is done via the Keras image dataset generator. The model focuses on the identification of three distinct classes of diseases from the faecal images of the chicken droppings. The use of a smaller convolutional filter minimises the network&rsquo;s tendency to overfit during training. 
 
Result: The study evaluated&nbsp;the efficacy of a classification model by considering many criteria such as dataset features, hyperparameters and model architecture. The model has a remarkable overall accuracy of 94.32%, indicating its strong categorisation capabilities across several categories. Although the model has a high overall accuracy, it exhibits differing degrees of performance across several classes, suggesting that there is potential for development in some areas.

Prediction of Norduz Sheep Live Weight using Multilayer Perceptron Neural Networks and Least Square Support Vector Machines

Exploration and Implementation of Computational Convolutional Neural Network Model for Poultry Disease Detection