Neural networks applied to a large biological database to analyse dairy breeding patterns

Abstract

The paper recounts the investigation of a dairy sire prediction capability based on Cascade Correlation neural networks to study influences relating the performance of offspring to their parents. The context of the problem is the artificial insemination breeding program for the Australian dairy industry. The networks are used to screen observed information in the database to relate it to best combinations of dam and sire. The voluminous data is quite noisy and is subject to genetic and environmental influences. The intention is to extract linear and nonlinear relationships from among the input variables without specifying their form. A number of scenarios are employed which recast the data into different forms. In particular, it was discovered that the problem could be restructured and the data supplemented with transformed data to produce succinct input patterns of manageable dimensionality, which allowed for a substantially improved predictive capability. It was then found that reasonable daughter predictions could be obtained of about 10%, as measured by her milk production. Results are compared with those obtained using two alternate neural network methods. Crude statistical methods are employed to evaluate the performance of the neural networks.