Multi-meteorological factors-based neural network model for broiler growth performance prediction

The purpose of this study is to investigate the prediction models for broiler growth performance. In this paper, a multi-meteorological factors-based neural network model (MMFNN) is proposed. We discuss the meteorological factors selection and the construction of MMFNN in detail. The influences of both air temperature and relative humidity to the rate for sale is taken for example to evaluate our approach. We use the broiler growth dataset of the most famous poultry raising company in China to evaluate our approach and the results show the effectiveness of our approach.