The objective ofthis work was to evaluate the precision of Artificial Neural Networks (ANNs)to estimate zootechnical indexes, based on thermal and physiological variablesof pregnant sows. This study was carried out from January to April 2005, ina swine industrial production farm in the gestation section with 27 primiparousgilts, allocated in individual pens and after on farrowing pens where it wasquantified animal production indexes of piglets from the study. Therefore, anANN backpropagation was implemented, with one input layer, one hidden layer,and one output layer with tangent sigmoidal transference functions. Air temperatureand respiratory frequency were considered as input variables and weight of pigletat birth and the number of mummified piglets as output variables. The trainedANN presented a great generalization power, which enabled the prediction ofthe answer-variables. Characterization of the environment of gestation and maternitywas appropriated if compared to the real data, with few under or overestimatedtendencies of some values. The use of this specialist system to predict zootechnicalindexes is viable because the system shows a good performance for this use.
