The overall objective of this research was to investigate the feasibility of using artificial neural networks to detect the incidence of clinical bovine mastitis and to determine the major factors influencing it. The first part of this research was devoted to a general examination of the learning ability of artificial neural networks by training them with relatively small data sets. These data sets (a total of 460,474 records) contained suspected indicators of mastitis such as milk production, stage of lactation and somatic cell count, and it was hoped that artificial neural networks would be able to detect what statistical modelling had already established elsewhere in the literature. The second part of this research was extended to examine the roles of more information resources such as conformation traits and their genetic values---factors that have not been studied extensively, with either conventional approaches or emerging technologies like artificial neural networks. (Abstract shortened by UMI.)

No description available.

Bovine mastitis is the most important economic disease to the dairy industry with losses estimated at 2 billion dollars per year in the United States. Staphylococcus aureus (.§.. aureus) is the primary cause of contagious mastitis. Conventional culture methods (National Mastitis Council) were used as a basis for comparing the ability of the enzyme linked immunosorbent assay. ProStaph Iâ ¢, to identify s. aureus. The test had an accuracy of 96%, with a sensitivity of 90% and a specificity of 97%. Results indicated that rinsing teat-cup liners with a 25 ppm iodophor or 100 ppm chlorine solution reduced the presence of S. aureus on the liners by 97%. ProStaph I was used to rapidly screen DHIA preserved milk samples in 10 Virginia cooperator herds. Herds were classified as high (>10% infected) or low prevalence (<10% infected). There were six high prevalence herds after the first test. Average prevalence of cows scoring Ab +2 and +3 was 11.9% ± 7.9. Over the seven month study, prevalence of positive cows declined significantly (P<.OI), but somatic cell count remained relatively unchanged (P>.lO). Four herds continued to have >10% of the animals infected. Incidence of new infection averaged 3.6% ± 2.8 from the first to the last test. Chronic cows averaged 6.9% ± 4.8 over the seven month study. Analysis of variance showed significant (P<.Ol) effects of herd on ProStaph I score J milk yield, and see. Elevated ProStaph I scores were highly correlated (P <.01) with increases in lactation number. ProStaph I changed quadratically (P<.Ol) with increasing SCC. Somatic cell count increased (P<.OI) as ProStaph I score increased. / Master of Science