Development of neuro-fuzzifiers for qualitative description of milk yield

Dairy yield prediction is a current challenge which has been improving by using different statistical methods. Recently, fuzzy logic has been employed as an alternative method of milk yield prediction. However, one of the problems with fuzzy logic is the timeliness of heuristic approaches in the calibration of membership functions and determination of the degrees of membership to various fuzzy sets. Objective The objective of this study was to use artificial neural networks (ANNs) for the fuzzification of milkyield with an aim to providing a less troublesome approach than heuristic techniques. The proposed method uses the learning ability of ANNs to mimic the dairy experts in classification of test-day records into fuzzy milk-yield sets, and prediction of the corresponding degrees of memberships.[...