Application of fuzzy logic in automated cow status monitoring

Sensors that measure yield, temperature, electrical conductivity of milk, a nd animal activity can be used for automated cow status monitoring. The occ urrence of false-positive alerts, generated by a detection model, creates p roblems in practice. We used fuzzy logic to classify mastitis and estrus al erts; our objective was to reduce the number of false-positive alerts and n ot to change the level of detected cases of mastitis and estrus. Inputs for the fuzzy logic model were alerts from the detection model and additional information, such as the reproductive status. The output was a classificati on, true or false, of each alert. Only alerts that mere classified true sho uld be presented to the herd manager. Additional information was used to ch eck whether deviating sensor measurements were caused by mastitis or estrus , or by other influences. A fuzzy logic model for the classification of mas titis alerts was tested on a data set from cons milked in an automatic milk ing system. All clinical cases without measurement errors were classified c orrectly. The number of false-positive alerts over time from a subset of 25 cows was reduced from 1266 to 64 by applying the fuzzy logic model. A fuzz y logic model for the classification of estrus alerts was tested on two dat a sets. The number of detected cases decreased slightly after classificatio n, and the number of false-positive alerts decreased considerably. Classifi cation by a fuzzy logic model proved to be very useful in increasing the ap plicability of automated cow status monitoring.