The application of artificial neural network and least square support vector machine methods based on spectrophotometry method for the rapid simultaneous estimation of triamcinolone, neomycin, and nystatin in skin ointment formulation

In this study, simultaneous measurement of triamcinolone (TA), neomycin (NEO) and nystatin (NYS) with artificial neural network (ANN) and least square support vector machine (LS-SVM) as artificial intelligence methods along with spectrophotometric technique in the formulation of skin ointment and synthetic mixtures was surveyed. The feed forward backpropagation neural network (FFBP-NN) with Levenberg-Marquardt (LM) and scaled conjugate gradient (SCG) algorithms was applied. The LM algorithm performed better than the other algorithm. Layer 2 with 8, 10 and 4 neurons with the least mean square error (MSE) were selected as the best layer and neurons for TA (MSE= 1.62 x 10-28), NEO (MSE= 3.20 x 10-28) and NYS (MSE=2.18 x 10-29), respectively. The root mean square error (RMSE) of LS-SVM model for TA, NEO, and NYS was achieved 0.409, 0.488 and 0.350, respectively. Also, the mean recovery was found to be 99.98%, 99.97% and 100.99% for the TA, NEO, and NYS, respectively. The results of the analysis of the ointment sample (Triamcinolone NN) with the proposed methods and high-performance liquid chromatography (HPLC) were compared with each other using one-way analysis of variance (ANOVA) test, which did not show a significant difference between these methods. The proposed method can be easily used to improve the quality of the mentioned pharmaceutical product due to its fast, low-cost, and no need for separation steps and expensive solvents.