In this research, a powerful regression model coupled with FTIR spectroscopy (Mid, 800–1700 cm⁻¹) has been proposed as an efficient method for precise determination of Benzalkonium chloride (BAK) in aqueous samples. For this purpose, both partial least squares regression (PLS-R) and support vector regression (SVR) as methods of multivariate calibration were used for evaluation, and their results were compared. Accordingly, root mean square error of prediction, and leave-one-out cross-validation root mean square error, and correlation coefficients between the calculated (${\mathrm{R}}_{\mathit{cal}}^2$) and the predicted (${\mathrm{R}}_{\mathrm{p}\mathrm{r}\mathrm{e}\mathrm{d}}^2$) values were used. In comparison to PLS (${\mathrm{R}}_{\mathrm{p}\mathrm{r}\mathrm{e}\mathrm{d}}^2$ = 0.975; RMSEP = 0.321), SVR had a higher${\mathrm{R}}_{\mathrm{p}\mathrm{r}\mathrm{e}\mathrm{d}}^2$ (0.991) and a lower value of root mean square error of prediction (RMSEP = 0.218). The lower detection limit was 0.00068% w/w for PLS and 0.0011% w/w for SVR model in a concentration range from 0.013 to 1% w/w. Hence, FTIR spectroscopy combined with SVR can be considered an efficient approach for real-time determination of BAK in aqueous samples.

在这项研究中，已经提出了一种功能强大的回归模型与FTIR光谱法（中，800-1700 cm ^-1）相结合的方法，可以作为一种精确测定水性样品中苯扎氯铵（BAK）的有效方法。为此，使用偏最小二乘回归（PLS-R）和支持向量回归（SVR）作为多变量校准方法进行评估，并对它们的结果进行了比较。因此，预测的均方根误差和留一法交叉验证的均方根误差以及计算出的（${\mathrm{[R}}_{\mathit{校准}}^{\mathrm{2个}}$）和预测的（${\mathrm{[R}}_{\mathrm{p}\mathrm{[R}\mathrm{Ë}\mathrm{d}}^{\mathrm{2个}}$）值。与PLS（${\mathrm{[R}}_{\mathrm{p}\mathrm{[R}\mathrm{Ë}\mathrm{d}}^{\mathrm{2个}}$ = 0.975；RMSEP = 0.321），SVR较高${\mathrm{[R}}_{\mathrm{p}\mathrm{[R}\mathrm{Ë}\mathrm{d}}^{\mathrm{2个}}$（0.991）和较低的均方根预测值（RMSEP = 0.218）。在0.013至1％w / w的浓度范围内，PLS的检测下限为0.00068％w / w，SVR模型的检测下限为0.0011％w / w。因此，结合SVR的FTIR光谱可以被认为是实时测定水性样品中BAK的有效方法。