Comparison of Artificial Neural Network and Multiple Regression Analysis for Prediction of Fat Tail Weight of Sheep

Abstract

A comparative study of artificial neural network (ANN) and multiple regression is made to predict the fat tail weight of Balouchi sheep from birth, weaning and finishing weights. A multilayer feed forward network with back propagation of error learning mechanism was used to predict the sheep body weight. The data (69 records) were randomly divided into two subsets. The first subset is the training set comprising of 75 percent data (52 records) to build the neural network model and test data set comprising of 25 percent (17 records), which is not used during the training and is used to evaluate performance of different models. The mean relative error was significantly (P<0.01) lower for ANN than the MLR model. The coefficient of determination (R²) values computed for the body measurements were generally higher (0.93) using ANN model than the multiple linear regression (MLR) model (0.81). The ANN model improved the mean squared error (MSE) of the MLR model by 59% and R² by 15% that the ANN represents a valuable tool for predicting of lamb fat tail weight from birth, weaning and finishing weights.