Research Information System
ANIMALS, vol.14, no.20, 2024 (SCI-Expanded)
Simple Summary With rapid technological advances, the use of machine learning in the poultry sector has increased significantly. The estimation of ammonia concentration with machine learning can greatly impact environmental protection as well as human and animal health. In this paper, an innovative hybrid approach combining machine learning with wavelet transform for ammonia estimation in poultry houses is presented. The results of the study show that these hybrid models are very promising for accurate and efficient ammonia estimation.Abstract Ammonia (NH3) is a major pollutant in poultry farms, negatively impacting bird health and welfare. High NH3 levels can cause poor weight gain, inefficient feed conversion, reduced viability, and financial losses in the poultry industry. Therefore, accurate estimation of NH3 concentration is crucial for environmental protection and human and animal health. Three widely used machine learning (ML) algorithms-extreme learning machine (ELM), k-nearest neighbor (KNN), and random forest (RF)-were initially used as base algorithms. The wavelet transform (WT) with ten levels of decomposition was then applied as a preprocessing method. Three statistical metrics, including the mean absolute error (MAE) and the correlation coefficient (R), were used to evaluate the predictive accuracies of algorithms. The results indicate that the RF algorithms perform robustly individually and in combination with the WT. The RF-WT algorithm performed best using the air temperature, relative humidity, and air velocity inputs with a MAE of 0.548 ppm and an R of 0.976 for the testing dataset. In summary, applying WT to the inputs significantly improved the predictive power of the ML algorithms, especially for inputs that initially had a low correlation with the NH3 values.