Grey Wolf Optimizer for Variable Selection in Quantification of Quaternary Edible Blend Oil by Ultraviolet-Visible Spectroscopy.

A novel swarm intelligence algorithm, discretized grey wolf optimizer (GWO), was introduced as a variable selection tool in edible blend oil analysis for the first time. In the approach, positions of wolves were updated and then discretized by logical function. The performance of a wolf pack, the iteration number and the number of wolves were investigated. The partial least squares (PLS) method was used to establish and predict single oil contents in samples. To validate the method, 102 edible blend oil samples containing soybean oil, sunflower oil, peanut oil and sesame oil were measured by an ultraviolet-visible (UV-Vis) spectrophotometer. The results demonstrated that GWO-PLS models can provide best prediction accuracy with least variables compared with full-spectrum PLS, Monte Carlo uninformative variable elimination-PLS (MCUVE-PLS) and randomization test-PLS (RT-PLS). The determination coefficients (R2) of GWO-PLS were all above 0.95. Therefore, the research indicates the feasibility of using discretized GWO for variable selection in rapid determination of quaternary edible blend oil.

Variational Mode Decomposition Weighted Multiscale Support Vector Regression for Spectral Determination of Rapeseed Oil and Rhizoma Alpiniae Offcinarum Adulterants.

The accurate prediction of the model is essential for food and herb analysis. In order to exploit the abundance of information embedded in the frequency and time domains, a weighted multiscale support vector regression (SVR) method based on variational mode decomposition (VMD), namely VMD-WMSVR, was proposed for the ultraviolet-visible (UV-Vis) spectral determination of rapeseed oil adulterants and near-infrared (NIR) spectral quantification of rhizoma alpiniae offcinarum adulterants. In this method, each spectrum is decomposed into K discrete mode components by VMD first. The mode matrix Uk is recombined from the decomposed components, and then, the SVR is used to build sub-models between each Uk and target value. The final prediction is obtained by integrating the predictions of the sub-models by weighted average. The performance of the proposed method was tested with two spectral datasets of adulterated vegetable oils and herbs. Compared with the results from partial least squares (PLS) and SVR, VMD-WMSVR shows potential in model accuracy.

Near infrared spectroscopy combined with chemometrics for quantitative analysis of corn oil in edible blend oil.

In this study, near infrared (NIR) spectroscopy combined with chemometrics was used for the quantitative analysis of corn oil in binary to hexanary edible blend oil. Sesame oil, soybean oil, rice oil, sunflower oil and peanut oil were mixed with corn oil subsequently to form binary, ternary, quaternary, quinary and hexanary blend oil datasets. NIR spectra for the five order blend oil datasets were measured in a transmittance mode in the range of 12000-4000 cm-1. Partial least square (PLS) was used to build models for the five datasets. Six spectral preprocessing methods and their combinations were investigated to improve the prediction performance. Furthermore, the optimal preprocessing-PLS models were further optimized by uninformative variable elimination (UVE), Monte Carlo uninformative variable elimination (MCUVE) and randomization test (RT) variable selection methods. The optimal models acquire root mean square error of prediction (RMSEP) of 1.7299, 2.2089, 2.3742, 2.5608 and 2.6858 for binary, ternary, quaternary, quinary and hexanary blend oil datasets, respectively. The determination coefficients of prediction set (R2P) and residual predictive deviations (RPDs) for the five datasets are all above 0.93 and 3. Results show that the prediction accuracy is gradually decreased with the increasing of mixture order of blend oil. However, with proper spectral preprocessing and variable selection, the optimal models present good prediction accuracy even for the higher order blend oil. It demonstrates that NIR technology is feasible for determining the pure oil contents in binary to hexanary blend oil.

Weighted multiscale support vector regression for fast quantification of vegetable oils in edible blend oil by ultraviolet-visible spectroscopy.

Weighted multiscale support vector regression combined with ultraviolet-visible (UV-Vis) spectra for quantitative analysis of edible blend oil is proposed. In the approach, UV-Vis spectra of the training set are decomposed into a certain number of intrinsic mode functions (IMFs) and a residue by empirical mode decomposition (EMD) at first. Then support vector regression (SVR) sub-models are built on each IMF and residue. For prediction set, the spectra are decomposed as done on the training set and the final predictions are obtained by integrating SVR sub-model predictions by weighted average. The weight of the sub-model is the reciprocal of the fourth power of the root mean square error of cross-validation (RMSECV). For predicting peanut oil in binary blend oil and sesame oil in ternary blend oil, the proposed method has superiority in root mean square error of prediction (RMSEP) and correlation coefficient (R) compared with SVR and partial least squares (PLS).

Ultraviolet-visible diffuse reflectance spectroscopy combined with chemometrics for rapid discrimination of Angelicae Sinensis Radix from its four similar herbs.

Ultraviolet-visible diffuse reflectance spectroscopy (UV-Vis DRS) combined with chemometrics was used for the first time to differentiate Angelicae Sinensis Radix (ASR) from four other similar herbs (either from the same genus or of similar appearance). A total of 191 samples, including 40 ASR, 39 Angelicae Pubescentis Radix (APR), 38 Chuanxiong Rhizoma (CR), 35 Atractylodis Macrocephalae Rhizoma (AMR) and 39 Angelicae Dahuricae Radix (ADR), were collected and divided into the training and prediction sets. Principal component analysis (PCA) was used for observing the sample cluster tendency of the calibration set. Different preprocessing methods were investigated and the optimal preprocessing combination was selected according to spectral signal characteristics and three-dimensional PCA (3D PCA) clustering results. The final discriminant model was built using extreme learning machine (ELM). The exploratory studies on the raw spectra and their 3D PCA scores indicate that the classification of the five herbs cannot be achieved by PCA of the raw spectra. Autoscaling, continuous wavelet transform (CWT) and Savitzky-Golay (SG) smoothing can improve the clustering results to different degrees. Furthermore, their combination in the order of CWT + autoscaling + SG smoothing can enhance the spectral resolution and obtain the best clustering result. These results are also validated using ELM models of raw and different preprocessing methods. By using CWT + autoscaling + SG smoothing + ELM, 100% classification accuracy can be achieved in both the calibration set and the prediction set. Therefore, the developed method could be used as a rapid, economic and effective method for discriminating the five herbs used in this study.

Rapid identification and quantification of Panax notoginseng with its adulterants by near infrared spectroscopy combined with chemometrics.

Traditional methods for identification of Panax notoginseng (PN) such as high performance liquid chromatography (HPLC) and gas chromatography (GC) are time-consuming, laborious and difficult to realize rapid and online analysis. In this research, the feasibility of identification and quantification of PN with rhizoma curcumae (RC), Curcuma longa (CL) and rhizoma alpiniae offcinarum (RAO) are investigated by using near infrared (NIR) spectroscopy combined with chemometrics. Five chemical pattern recognition methods including hierarchical cluster analysis (HCA), partial least squares-discriminant analysis (PLS-DA), artificial neural networks (ANN), support vector machine (SVM) and extreme learning machine (ELM) are used to build identification model of the dataset with 109 samples of PN and its three adulterants. Then seven datasets of binary, ternary and quaternary adulterations of PN are designed, respectively. Five multivariate calibration methods, i.e., principal component regression (PCR), support vector regression (SVR), partial least squares regression (PLSR), ANN and ELM are used to build quantitative model and compared for each dataset, separately. Finally, in order to further improve the prediction accuracy, SG smoothing, 1st derivative, 2nd derivative, continuous wavelet transform (CWT), standard normal variate (SNV), multiple scatter correction (MSC) and their combinations are investigated. Results show that PLS-DA and SVM can achieve 100% classification accuracy for identification of 109 PN with its three adulterants. PLSR is an optimal calibration method by comprehensive consideration of prediction accuracy, over-fitting and efficiency for the quantitative analysis of seven adulterated datasets. Furthermore, the predictive ability of the PLSR model for PN contents can be improved obvious by pretreating the spectra by the optimal preprocessing method, with correlation coefficients of which all higher than 0.99.