Artificial Neural Networks on Eggs Production Data Management

Abstract

Background: Eggs have acquired a greater importance as an inexpensive and high-quality protein. The Brazilian egg industry has been characterized by a constant production expansion in the last decade, increasing the number of housed animals and facilitating the spread of many diseases. In order to reduce the sanitary and financial risks, decisions regard­ing the production and the health status of the flock must be made based on objective criteria. The use of Artificial Neural Networks (ANN) is a valuable tool to reduce the subjectivity of the analysis. In this context, the aim of this study was at validating the ANNs as viable tool to be employed in the prediction and management of commercial egg production flocks.Materials, Methods & Results: Data from 42 flocks of commercial layer hens from a poultry company were selected. The data refer to the period between 2010 and 2018 and it represents a total of 600,000 layers. Six parameters were selected as “output” data (number of dead birds per week, feed consumption, number of eggs, weekly weight, weekly egg produc­tion and flock uniformity) and a total of 13 parameters were selected as “input” data (flock age, flock identification, total hens in the flock, weekly weight, flock uniformity, lineage, weekly mortality, absolute number of dead birds, eggs/hen, weekly egg production, feed consumption, flock location, creation phase). ANNs were elaborated by software programs NeuroShell Predictor and NeuroShell Classifier. The programs identified input variables for the assembly of the networks seeking the prediction of the variables called outgoing that are subsequently validated. This validation goes through the comparison between the predictions and the real data present in the database that was the basis for the work. Validation of each ANN is expressed by the specific statistical parameters multiple determination (R2) and Mean Squared Error (MSE). For instance, R2 above 0.70 expresses a good validation. ANN developed for the output variable “number of dead birds per week” presented R2= 0.9533 and MSE= 256.88. For “feed consumption”, the results were R2= 0.7382 and MSE= 274.56. For “number of eggs (eggs/hen)”, the results were R2= 0.9901 and MSE= 172.26. For “weekly weight”, R2= 0.9712 and MSE= 11154.41. For “weekly egg production”, R2= 0.8015 and MSE= 72.60. For “flock uniformity”, R2= -2.9955 and MSE= 431.82.Discussion: From the six ANN designed in this study, in five it was possible to validate the predictions by comparing predictions with the real data. In one output parameter (“flock uniformity”), it was not possible to have adequate validation due to insufficient data in our database. For “number of dead birds per week”, “feed consumption”, “weekly weight” and “uniformity”, the most important variable was “flock age” (27.5%, 52.5%, 55.2% and 37.9%, respectively). For “number of eggs (eggs/hen)”, “uniformity” (52.1%) was the most relevant variable for prediction. For “weekly egg production”, “flock age” and “number of eggs (eggs/hen)” were the most important zootechnical parameters, both with a relative contribution of 38.2%. The results showed that even with the use of a robust tool such as ANNs, it is necessary to have well-noted and clear information that expresses the reality of the flocks. In any case, the results presented allow us to state that ANNs are capable for the management of data generated in a commercial egg production facility. The process of evaluation of these data would be improved if ANNs were routinely used by the professionals linked to this activity.

Artificial Neural Networks to Predict Egg-Production Traits in Commercial Laying Breeder Hens

“…The significant increase in egg production, leading to a large number of housed birds and consequently of data for management, motivated the development of the first studies on the use of ANNs in the commercial laying chain by our research team. Recently, Almeida et al (2020) showed that ANN was capable of managing six parameters selected as "output" data in a commercial egg production facility. The current…”

“…MSE is used in regression analysis to show how close a regression line is to a set of points (the distance from the regression line). An assessment of uniform scatter in the residual plots was also used (Salle et al, 2003;Almeida et al, 2020). These statistical parameters were obtained in the training stage, when the predicted values were compared to the actual values of the respective output variables.…”

“…In this study, it was possible to build models for eight different outputs by selecting a variable number of egg production traits as input variables. However, it is important to emphasize that all egg production traits may be selected as output variables, depending on companies' interests (Almeida et al, 2020). R 2 and MSE were used to evaluate the fit of the models, and their values for each model (training and validation) are listed in Tables 1 and 2.…”

“…R 2 is an indicator of how efficiently the model fits the data (Salle et al, 2003;Savegnago et al, 2011). Values of R 2 near "1" indicate a higher quality in the validation of the network, whereas those that are more distant present a lower quality (Salle et al, 2003;Almeida et al, 2020). Previous studies in the same area have already shown that R 2 values above 0.70, in the ANN training processes, indicate a good quality of networks for prediction (Salle et al, 2003;Reali, 2004;Salle, 2005;Spohr, 2011;Tedeschi, 2019;Almeida et al, 2020).…”

“…Values of R 2 near "1" indicate a higher quality in the validation of the network, whereas those that are more distant present a lower quality (Salle et al, 2003;Almeida et al, 2020). Previous studies in the same area have already shown that R 2 values above 0.70, in the ANN training processes, indicate a good quality of networks for prediction (Salle et al, 2003;Reali, 2004;Salle, 2005;Spohr, 2011;Tedeschi, 2019;Almeida et al, 2020). Furthermore, MSE values indicate the error in the prediction of a specific variable, and smaller values indicate better fitting of the models (Savegnago et al, 2011).…”