An optimized fuzzy inference system for oestrus detection in dairy cattle

Abstract

A fuzzy inference system has been developed as a tool for oestrus (heat) detection in dairy cattle. It uses signal, which are induced by hormone level changes during oestrus, resulting in physiological and behavioral effects like changes in activity, milk yield and milk temperature. A novelty in this approach is the use of a controlled random optimization method to tune the membership function shapes. Using routinely collected data, the system proves to detect cows in heat with acceptable results.