Short-Term Prediction of Ammonia Levels In Geese Houses Based On Combined Feature Selector and Random Forest

Abstract

Ammonia concentration (NH3) is a dominant source of environmental pollution in geese housing and profoundly affects the healthy growth of geese. Accurately forecasting NH3 and analyzing its change trends in geese houses is crucial for the survival of geese. To improve the prediction accuracy of NH3, we propose a novel forecasting model by the combination of feature selector (CFS) and random forest (RF). The developed model integrated two modules. First, combining mutual information (MI) and relief-F, we propose CFS quantify the importance values of each feature and eliminate the low-relation or unrelated features. Second, we built a random forest model and used the K-fold cross-validation grid search algorithm (CVGS) to obtain the RF hyper-parameters to predict NH3. The simulation results show that the prediction accuracy was improved when feature selection after quantification based on the CFS was used. The mean square error (MSE), root mean square error (RMSE) and mean absolute percent error (MAPE) for the proposed model were 0.5072, 0.6583, 2.88%, respectively. The NH3 prediction model based on CFS-GS-RF exhibited best prediction accuracy, and generalization performance compared with other parallel forecasting models and is a suitable and useful tool for predicting NH3 in geese houses.