Subclinical mastitis prediction in dairy cattle by application of fuzzy logic

The main purpose of this study was to detect subclinical mastitis in a large sized dairy herd milked using automated milking systems. Recording of data was performed on the private dairy farm Karapinar of the province of Konya, Turkey. A data set of 346 milkings from 170 cows was used. Mastitis alerts were generated via a Fuzzy Logic (FL) model with the input data of lactation rank (current lactation number), milk yield, electrical conductivity, average milking duration and season. The output variable was somatic cell counts obtained from milk samples collected monthly throughout the 15 months of the sampling period. Cattle were judged healthy or infected based on somatic cell counts. The evaluation of the model was carried out according to sensitivity, specificity and error rate. The FL model yielded 82% sensitivity, 74% specificity, and 60% error. Fuzzy logic seems one of the useful tools to develop a detection model for mastitis. With more informative parameters, the error rate can be decreased.