Tilapia feeding decision system based on adaptive neuro-fuzzy inference

In industrial recirculating aquaculture, the feed required by fish accounts for a major part of total expenditure. this paper, multi-factor decision making system based on aggregation FIFFB feeding behavior, water temperature T environmental factors and biomass weight W was proposed to solve problem waste under traditional mode. To verify performance model, fuzzy inference FIS model is constructed comparison. The experimental results show that root mean square error (RMSE) absolute (MAE) between predicted actual amount ANFIS triplet are 0.78 0.19, respectively, which much lower than more suitable predicting decision. At same time, growth parameters such as WGR, FMAE, K FCR were compared. specifications fatter economic benefits higher, conversion rate increased 12.35%. Therefore, prediction decision-making degree, body effective has guiding significance precise design unmanned aquaculture.