Qualitative prediction of Thymoquinone in the high‐performance liquid chromatography optimization method development using artificial intelligence models coupled with ensemble machine learning

Abstract In this study, three various artificial intelligence‐based models were employed including two non‐linear namely; Hammerstein–Wiener, the neuro‐fuzzy model, and a trivial linear multi‐linear regression analysis for the qualitative prediction of Thymoquinone in high‐performance liquid chromatography optimization method development. Various parameters which include mobile phase composition, flow rate, and concentration of the standard are used as the independent variables. Whereby, the Thymoquinone retention time is simulated to be the dependent variable. The predicted and experimental results were further estimated by using dual indices to assess the performances, which include the determination coefficient as the goodness of fit and mean squared error. The obtained results depicted the promising capacity of the non‐linear models; Hammerstein–Wiener and neuro‐fuzzy model over multi‐linear regression analysis. For the ensemble machine learning techniques, the results obtained from the non‐linear ensemble paradigm (neuro‐fuzzy ensemble) showed its ability in boosting the efficiency of the single model's performance up to 28%. The results illustrated the robustness and validity of the artificial intelligence‐based models and further confirmed the potential of ensemble techniques for the prediction of Thymoquinone.