Non-linear regression methods in NIRS quantitative analysis

Classification of dry-cured hams according to the maturation time using near infrared spectra and artificial neural networks

“…Its usefulness has already been proven for the prediction of chemical and physical characteristics of meat and meat products and for various classification purposes (for review see Škorjanc, 2004 andPrieto, Roehe, Lavín, Batten, &Andrés, 2009). NIR spectral information demands multivariate data analysis due to its complexity (Pérez-Marín, Garrido-Varo, & Guerrero, 2007). Artificial intelligent methods are often applied for the classification since their primary target is to distinguish objects or groups or populations.…”

A nonlinear model for calibration of blood glucose noninvasive measurement using near infrared spectroscopy

“…KPLS differs from the previously mentioned nonlinear PLS algorithms [18][19][20], in that the original input data in space R are nonlinearly transformed into a feature space F of arbitrary dimensionality via nonlinear mapping UðxÞ, then a linear PLS model is created in feature space. The nonlinear transformation effect can be completed only by dot product as described in Eq.…”

“…(iii) According to the results shown in Tables 2 and 3, it is indicated that, even though SPLS has the best prediction performance to the NIR experiment data of simulated physiological solution samples in vitro, it seems that SPLS is not always has good performance, especially for the complex NIR data of human noninvasive measurement experiment in vivo. Under the hybrid nonlinear modeling strategy of mUVE-KPLS with Gaussian kernel, the best prediction accuracy is got and the RMSEP is 9.4 mg dL À1 , which is increased by19.7% compared with linear model. However, under the modeling strategy of mUVE-SPLS, the RMSEP is 11.4 mg dL À1 , which is increased slightly by 2.6% compared with linear model.…”

Application of near-infrared spectroscopy for the rapid quality assessment of Radix Paeoniae Rubra

“…In this study, more samples (101) from five different typical cultivated areas were collected to develop NIR models. Different regression methods were compared by PLS, PCR, and stepwise multivariate linear regression (SMLR) for NIR quantitative analysis [31]. Various pretreatment methods such as derivatives (1st and 2nd), multiplicative scatter correction (MSC), standard normal variate (SNV), Savitzky-Golay filter, and Norris derivative filter were used to obtain the optimized models for gallic acid, catechin, albiflorin, and paeoniflorin, respectively.…”