APPLICATION OF A NEURAL-NETWORK TO ANALYZE ONLINE MILKING PARLOR DATAFOR THE DETECTION OF CLINICAL MASTITIS IN DAIRY-COWS

As part of research towards an on-line mastitis detection system, stan dard back-propagation neural networks to classify healthy and clinical mastitic quarters were explored. The usage of back-propagation neural networks is discussed. A neural network for clinical mastitis detecti on is presented. This network used automatically collected quarter ele ctrical conductivity data as input. The network was trained with 17 he althy and 13 clinical mastitic quarters. All healthy and 12 of 13 mast itic quarters were classified correctly after training. The trained ne ural network predicted 34 of 38 healthy quarters correctly in differen t evaluation data sets. For mastitic quarters, related data had to be used, and 21 of 38 mastitic quarters were classified correctly. We con cluded that a back-propagation neural network could indeed separate he althy from clinical quarters in an experimental setting. Further devel opment should include the use of different input parameters and compar isons with other analysis techniques.