Abstract
In this study, reliable and quick methods based on ultraviolet-visible spectrophotometry (UV–Vis) for the simultaneous determination of Naphazoline (NAP) and Antazoline (ANT) were proposed. Feed-forward back-propagation neural network (FFBP-NN) as an artificial intelligence system as well as partial least squares (PLS) and principal component regression (PCR) as regression methods were used for this work. FFBP neural network with Levenberg–Marquardt (LM), scaled conjugate gradient (SCG), and gradient descent with momentum and adaptive learning rate backpropagation (GDX) algorithms with various layers and neurons were applied to select the best model. The lowest mean square error (MSE) related to the LM, SCG, and GDX algorithms was 3.44×10−14, 6.93×10-30- 1.13×10-7, 2.76×10-6, and 3.29×10-5, 9.63×10-3 for NAP and ANT, respectively. On the other hand, the mean recovery (%) and root mean square error (RMSE) of the PLS method were 100.03, 0.00032 and 100.03, 0.00326 for NAP and ANT, respectively. Also, the mean recovery and RMSE values corresponding to the PCR model were obtained 100.65 %, 0.00525 and 100.93 %, 0.06515 for NAP and ANT, respectively. Finally, a comparison between the proposed methods and high-performance liquid chromatography (HPLC) as a reference method was performed by analysis of variance (ANOVA). The results proved that there was no significant difference between them.
Sign-in/Register to access full text options 
Talk to us
Join us for a 30 min session where you can share your feedback and ask us any queries you have
Schedule a callDisclaimer: All third-party content on this website/platform is and will remain the property of their respective owners and is provided on "as is" basis without any warranties, express or implied. Use of third-party content does not indicate any affiliation, sponsorship with or endorsement by them. Any references to third-party content is to identify the corresponding services and shall be considered fair use under The CopyrightLaw.
