A Research on Identification and Predication of Sows' Oestrus Behavior Based on Hopfield Neural Network

摘要

With the increasing demand for breeding pigs, timely and accurately identification of sows' oestrus becomes increasingly important for swinery management. Based on a series of researches on sow oestrus identification, the neural network oestrus behavior identification model and prediction model were established through artificial intelligence (AI) with key sign parameters such as body temperature, movement time, total food intake, repose time and oestrus time as the input and with sows' behavior characteristics as the output in this paper. A stable mode corresponding to parameters of oestrous sows was obtained using relevant learning algorithms so as to identify sow's oestrus.