A new approach to predict the missing values of algae during water quality monitoring programs based on a hybrid moth search algorithm and the random vector functional link network

摘要: Abstract Here, we propose a new alternative machine learning method that combines the advantage of Random Vector Functional Link Network (RVFL) with Moth Search Algorithm (MSA) to predict missing values total algal count during water quality monitoring surface waters providing drinking treatment plants in Fayoum, Egypt. Total 34 parameters was measured 270 samples period 2015–2017. The MSA algorithm used for optimal selection input features improve performance RVFL. predicted count, by proposed MSA-RVFL method, were strongly correlated real observed ones. results better than Support Machine (SVM) and Adaptive Neural Fuzzy Inference System (ANFIS) models at different sizes training tests. Compared GA-RVFL PSO-RVFL methods, using relevant minimize variables reduce processing time. model could number from thirty-four eighteen eventually four variables. most significant selected pH, NO3, P Ca. Based on these variables, algae significantly matching observations (R2 = 0.9594). Accordingly, this makes be useful cost-efficient tool programs. Finally, showed higher whenever inputs is large or small gives our suggested more advantages traditional ANN models.