APPLICATION OF NEURAL NETWORK AND TIME SERIES TECHNIQUES IN WOOL GROWTH MODELING
F. Hong, Jianbin Tan, David G. McCall · Transactions of the ASAE · 2000
An application of neural network and time series techniques in animal system modeling is presented, whichsheds lights on strategies to deal with some typical peculiarities in biological system data. A neural network model wasdeveloped to describe the multi-input and multi-output relationship from live weight gain, age, breed, and rearing statusto monthly wool growth rates of sheep. Constrained synaptic weights were imposed to avoid logically unrealisticfunctional relationships. ARMAX models were developed to describe the dynamics in wool growth rate and to analyze thetime relationship between live weight gain and wool growth rate. The recursive least-squares parameter estimationalgorithm was employed for effective use of short-term and multi-subject data in developing time series models.