Least-Squares Support Vector Machine and its Application in the Simultaneous Quantitative Spectrophotometric Determination of Pharmaceutical Ternary Mixture

This paper proposes the least-squares support vector machine (LS-SVM) as an intelligent method applied on absorption spectra for the simultaneous determination of paracetamol (PCT), caffeine (CAF), and ibuprofen (IB) in Novafen. The signal to noise ratio (S/N) increased. Also, In the LS - SVM model, Kernel parameter (𝜎2) and capacity factor (C) were optimized. Excellent prediction was shown using LS-SVM, with lower root mean square error (RMSE) and relative standard deviation (RSD). In addition, Regression coefficient (R2), correlation coefficient (r), and mean recovery (%) of this method obtained for PCT, CAF, and IB. LS- SVM / spectrophotometry method is reliable for simultaneous quantitative analysis of components in commercial samples. The results obtained from analyzing the real sample by the proposed method compared to the high- performance liquid chromatography (HPLC) as a reference method. One-way analysis of variance (ANOVA) test at 95% confidence level used and results showed that there was no significant difference between suggested and reference methods.