Interval Partial Least Squares Research Articles

Spectral fingerprints during sun injury development on the tree in Granny Smith apples: A potential non-destructive prediction tool during the growing season

Sun-injury (=sunburn) on apples, as well as in other species, is a physiological disorder that develops in the field when high irradiance combines with elevated temperature during the growing season. This causes photooxidative and heat stress that finally leads to symptoms in sun-exposed fruit tissue. The objective of this study was to assess metabolite profiles changes, as a consequence of these abiotic stresses, using VIS/NIR reflectance in Granny Smith apples. Individual fruit was tagged and weekly monitored from 60 until 151 DAFB. Vis/NIR reflectance measurements (350–1100nm) were taken on the fruit surface on apples unexposed to direct sunlight (NE, class 0), exposed to direct sunlight (EX, class 1) and those that developed sunburn in the categories of Mild (class 2), Moderate (class 3), and Severe (class 4). Spectral curves were analyzed using discriminant partial least square models (PLS-DA) and interval PLS discriminant analysis (iPLS-DA). PLS-DA analysis was able to separate fruit with and without visible sun injury with a classification error of 22.5% and 35.7% for class 3 and 2, respectively. Class 3 and 4 observed at 129 DAFB was predicted through reflectance spectra captured 87 DAFB by PLS-DA, with 550–570nm, 715–750nm, and 810–850nm spectral intervals responsible ranges for discrimination. Such changes in Vis/NIR reflectance among classes would be related to changes in pigments (carotenoids and flavonoids) and apple tissue structural properties. These findings indicate that the method offers potential for nondestructive prediction of sunburn occurrence on apples in the orchard, that could lead to development of an automated system to forecast sunburn occurrence.

Spectroscopic quantitation of tetrazolium formazan in nano-toxicity assay with interval-based partial least squares regression and genetic algorithm

Spectrophotometric quantitation of formazan in tetrazolium-based nanoparticle (NP) toxicity assay requires a robust calibration model immune to optical interference. For the first time, variant of partial least squares (PLS) regression models, such as, full-spectrum (250–700nm) PLS, interval PLS (iPLS), backward interval PLS (biPLS), and synergy interval PLS (siPLS) models have been adopted for formazan quantitation. Models were evaluated based on root mean square error of cross-validation (RMSECV), and prediction (RMSEP). The spectral variables in optimal iPLS, biPLS and siPLS models, as well as variables retained above a selection frequency threshold (for all intervals), were further refined in a genetic algorithm (GA). The results suggest that the optimal biPLS (140 variables, 5 LVs, RMSECV: 0.4438, RMSEP: 0.2936) and siPLS (88 variables, 5 LVs, RMSECV: 0.4401, RMSEP: 0.316) models were superior either to the full-spectrum PLS (4 LVs, RMSECV: 0.9674, RMSEP: 0.4618) or traditional single wavelength calibration (414nm, RMSECV: 2.0864, RMSEP: 2.1628). Minimum RMSEP (0.2976) was observed when GA was performed on spectral variables retained (above a threshold frequency) from the cumulative frequency distribution of all siPLS models. Finally, applicability of the selected PLS regression models in real NP toxicity assay is demonstrated.

Source Attribution of Cyanides Using Anionic Impurity Profiling, Stable Isotope Ratios, Trace Elemental Analysis and Chemometrics.

Chemical attribution signatures (CAS) for chemical threat agents (CTAs), such as cyanides, are being investigated to provide an evidentiary link between CTAs and specific sources to support criminal investigations and prosecutions. Herein, stocks of KCN and NaCN were analyzed for trace anions by high performance ion chromatography (HPIC), carbon stable isotope ratio (δ(13)C) by isotope ratio mass spectrometry (IRMS), and trace elements by inductively coupled plasma optical emission spectroscopy (ICP-OES). The collected analytical data were evaluated using hierarchical cluster analysis (HCA), Fisher-ratio (F-ratio), interval partial least-squares (iPLS), genetic algorithm-based partial least-squares (GAPLS), partial least-squares discriminant analysis (PLSDA), K nearest neighbors (KNN), and support vector machines discriminant analysis (SVMDA). HCA of anion impurity profiles from multiple cyanide stocks from six reported countries of origin resulted in cyanide samples clustering into three groups, independent of the associated alkali metal (K or Na). The three groups were independently corroborated by HCA of cyanide elemental profiles and corresponded to countries each having one known solid cyanide factory: Czech Republic, Germany, and United States. Carbon stable isotope measurements resulted in two clusters: Germany and United States (the single Czech stock grouped with United States stocks). Classification errors for two validation studies using anion impurity profiles collected over five years on different instruments were as low as zero for KNN and SVMDA, demonstrating the excellent reliability associated with using anion impurities for matching a cyanide sample to its factory using our current cyanide stocks. Variable selection methods reduced errors for those classification methods having errors greater than zero; iPLS-forward selection and F-ratio typically provided the lowest errors. Finally, using anion profiles to classify cyanides to a specific stock or stock group for a subset of United States stocks resulted in cross-validation errors ranging from 0 to 5.3%.

Interval partial least squares and moving window partial least squares in determining the enantiomeric composition of tryptophan by using UV-Vis spectroscopy

The application of interval partial least squares (IPLS) and moving window partial least squares (MWPLS) to the enantiomeric analysis of tryptophan (Trp) was investigated. A UV-Vis spectroscopy method for determining the enantiomeric composition of Trp was developed. The calibration model was built by using partial least squares (PLS), IPLS and MWPLS respectively. Leave-one-out cross validation and external test validation were used to assess the prediction performance of the established models. The validation result demonstrates the established full-spectrum PLS model is impractical for quantifying the relationship between the spectral data and enantiomeric composition of L-Trp. On the contrary, the developed IPLS and MWPLS model are both practicable for modeling this relationship. For the IPLS model, the root mean square relative error (RMSRE) of external test validation and leave-one-out cross validation is 4.03 and 6.50 respectively. For the MWPLS model, the RMSRE of external test validation and leave-one-out cross validation is 2.93 and 4.73 respectively. Obviously, the prediction accuracy of the MWPLS model is higher than that of the IPLS model. It is demonstrated UV-Vis spectroscopy combined with MWPLS is a commendable method for determining the enantiomeric composition of Trp. MWPLS is superior to IPLS for selecting spectral region in UV-Vis spectroscopy analysis.

球磨机信号分析和关键参数预报系统

为了实现磨矿过程球磨机负荷参数的在线检测，采用MATLAB和C#.net混合编程方式，开发实现了球磨机振动、振声信号分析和关键参数预报的软测量系统。该系统基于集合经验模态分解(Ensemble Empirical Mode Decomposition, EEMD)技术和区间偏最小二乘(interval partial least-squares, iPLS)技术提取与磨机负荷参数密切相关的本征模态函数(intrinsic mode functions, IMF)频域特征，构建基于本征模态函数特征空间的选择性集成模型，实现磨机负荷参数的测量。MATLAB的Deploytool工具将信号EEMD分解、IMF频谱变换、iPLS特征选择、关键参数模型训练和模型预测一系列m函数编译生成DLL程序集合，在C#.net编程环境中，通过调用上述程序实现球磨机信号分析和关键参数预报软件系统的快速开发。系统测试结果表明该系统能够有效选择筒体振动和振声信号IMF频谱特征，系统准确性和可靠性较高，对改进磨矿过程控制和优化具有重要意义。 Due to the difficult of the ball mill load to measure directly, we combined matlab language with c#.net programming to develop a signal analysis and key parameters prediction system of ball mill. The vibration and acoustic signals are decomposed a series of Intrinsic Mode Functions (IMFs) by using Ensemble Empirical Mode Decomposition (EEMD). The frequency domain characteristics of the IMFs were chosen based on interval Partial Least-Squares (iPLS) and forecast model of key load parameters were built based on extreme learning machine ensemble modeling. In order to solve the problem of monitoring and estimating the critical parameters of the ball mill’s running state. Use the Deploytool tool of Matlab to compile a series of M function of signal EEMD decomposition, IMF transform spectrum, iPLS feature selection and the model training and prediction of the key parameters into C#.NET DLL assemblies, and then call them in C#. The software system of signal analysis and key parameters prediction of ball mill is developed, which has the function of signal decomposition, feature selection, model training and parameter prediction. System test results show that the system can effectively select the cylinder vibration and noise signal IMF spectrum characteristics closely related to the ratio of material ball, grinding concentration and filling rate. In addition, the mill load parameters forecasting system based on spectral characteristics has good generalization performance.

Rapid detection of total nitrogen content in soy sauce using NIR spectroscopy

Xu J., Huang F., Li Y., Chen Z., Wang Y. (2015): Rapid detection of total nitrogen content in soy sauce using NIR spectroscopy. Czech J. Food Sci., 33: 518–522. A method for the rapid and nondestructive determination of total nitrogen content in soy sauce was explored. Pre diction models were established using near-infrared spectroscopy combined with each of the following techniques: partial least squares (PLS), interval PLS, synergy interval PLS (siPLS), and backward interval PLS. Results showed that each improved forecast model was better than the PLS model. The siPLS method exhibited the best performance. The full spectrum of light soy sauce was divided into 20 subintervals. The combination of four subintervals, namely, 6, 11, 13, and 18, showed the best effect, with a correlation coefficient of 0.9977 and an RMSECV of 0.0198. The full spectrum of dark soy sauce was divided into 20 subintervals. The combination of three subintervals, namely, 14, 17, and 19, showed the best effect, with a correlation coefficient of 0.9818 and an RMSECV of 0.0640. Therefore, the siPLS method can realise a rapid and accurate detection of total nitrogen content in soy sauce.

Online near-infrared analysis coupled with MWPLS and SiPLS models for the multi-ingredient and multi-phase extraction of licorice (Gancao).

BackgroundThis study aims to analyze the active pharmaceutical ingredients (APIs) of licorice (Radix Glycyrrhizae; gancao), including glycyrrhizic acid, liquiritin, isoliquiritin and total flavonoids, in multi-ingredient and multi-phase extraction by online near-infrared technology with fiber optic probes and chemometric analysis.MethodsHigh-performance liquid chromatography and ultraviolet spectrophotometry determined the APIs content in different extraction phases by online near-infrared analysis, which included sample set selection by the Kennard–Stone algorithm, optimization of spectral pretreatment methods (i.e., orthogonal signal correction and wavelet denoising spectral correction), and model calibration by the partial least-squares algorithm, moving-window partial least-squares algorithm and synergy interval partial least-squares (SiPLS) algorithm. The relative errors and F values were used to assess the models in different extraction phases.ResultsThe root-mean-square error of correction, root-mean-square error of cross-validation and root-mean-square error of prediction of APIs in the SiPLS model was less than 0.07. The F values of glycyrrhizic acid, liquiritin, isoliquiritin and total flavonoids were 10,765, 32,431, 649 and 6080, respectively, which were larger than 6.90 (P < 0.01).ConclusionThe study demonstrated the feasibility of online NIR analysis in the multi-ingredient and multi-phase extraction of APIs from licorice.Electronic supplementary materialThe online version of this article (doi:10.1186/s13020-015-0069-2) contains supplementary material, which is available to authorized users.

Efficient wavenumber selection based on spectral fluctuation dividing and correlation-based clustering for calibration modeling

This study proposes an efficient wavenumber selection method to develop calibration models based on near-infrared (NIR) spectroscopy. First, spectral fluctuation dividing (SFD) divides a whole NIR spectrum into multiple spectral intervals based on a spectral fluctuation profile, which consists of the standard deviation of spectral intensities at each wavenumber. Then, nearest correlation spectral clustering (NCSC) clusters those spectral intervals into spectral interval groups based on the correlation of the spectral intensities among the spectral intervals. Finally, the proposed method builds a partial least squares (PLS) model using the spectral intensities in each spectral interval group, and selects several spectral interval groups based on the estimation accuracy of each PLS model. This method was named SFD–NCSC–PLS. In developing calibration models to estimate water and drug contents in granules, SFD–NCSC–PLS achieved higher estimation accuracy than the commonly-used interval PLS, searching combination moving window PLS, and the methods using either SFD or NCSC. The results show that SFD–NCSC–PLS can properly select wavenumbers that reflect the target response. In addition, SFD–NCSC–PLS took only less than half the computation time compared with the wavenumber selection methods using either SFD or NCSC. Thus, the proposed SFD–NCSC–PLS is a promising wavenumber selection method.

Molecular descriptor subset selection in theoretical peptide quantitative structure-retention relationship model development using nature-inspired optimization algorithms.

In this work, performance of five nature-inspired optimization algorithms, genetic algorithm (GA), particle swarm optimization (PSO), artificial bee colony (ABC), firefly algorithm (FA), and flower pollination algorithm (FPA), was compared in molecular descriptor selection for development of quantitative structure-retention relationship (QSRR) models for 83 peptides that originate from eight model proteins. The matrix with 423 descriptors was used as input, and QSRR models based on selected descriptors were built using partial least squares (PLS), whereas root mean square error of prediction (RMSEP) was used as a fitness function for their selection. Three performance criteria, prediction accuracy, computational cost, and the number of selected descriptors, were used to evaluate the developed QSRR models. The results show that all five variable selection methods outperform interval PLS (iPLS), sparse PLS (sPLS), and the full PLS model, whereas GA is superior because of its lowest computational cost and higher accuracy (RMSEP of 5.534%) with a smaller number of variables (nine descriptors). The GA-QSRR model was validated initially through Y-randomization. In addition, it was successfully validated with an external testing set out of 102 peptides originating from Bacillus subtilis proteomes (RMSEP of 22.030%). Its applicability domain was defined, from which it was evident that the developed GA-QSRR exhibited strong robustness. All the sources of the model's error were identified, thus allowing for further application of the developed methodology in proteomics.

Assessment of Interval PLS (iPLS) Calibration for the Determination of Peroxide Value in Edible Oils

AbstractPartial least squares (PLS) is a commonly used (and sometimes misused) chemometric technique for calibrating Fourier transform infrared spectroscopy, and allows the analysis of a variety of quality parameters associated with edible oils. Peroxide value (PV) is a typical parameter of interest; however, developing a robust, optimal, and reliable calibration method can be a daunting task. This paper examines and compares the use of interval PLS as a tool to develop a PLS PV calibration method for a single‐bounce attenuated total reflectance accessory relative to full spectrum PLS and experienced PLS, making use of correlation, variance, and pure component spectra. Using mixtures of fresh and oxidized oil covering a PV range of 1–20 meq/kg, backward interval PLS could systematically produce quality calibrations without the need to resort to experienced PLS. The experienced PLS requires a degree of spectral knowledge as well as diligent and tedious spectral examination, including largely unstructured iterative calibrations and cross‐validations to improve calibration performance. The backward interval PLS is also better than the full spectrum PLS in terms of model performance. In addition, the general model developed could account for the errors caused by oil types.

Comparison between ATR-IR, Raman, concatenated ATR-IR and Raman spectroscopy for the determination of total antioxidant capacity and total phenolic content of Chinese rice wine

The application of attenuated total reflectance infrared spectroscopy (ATR-IR), Raman spectroscopy (RS) and combination of ATR-IR and RS for measurements of total antioxidant capacity (TAC) and total phenolic content (TPC) of Chinese rice wine (CRW) were investigated in this study. Synergy interval partial least-squares (SiPLS), support vector machine (SVM) and principal component analysis (PCA) were applied to process the merged data from two individual instruments. It was observed that the performances of models based on the RS spectra were better than those based on the ATR-IR spectra. In addition, SVM models based on the efficient information extracted from ATR-IR and RS spectra were superior to PLS models based on the same information and PLS models based on ATR-IR or RS spectra. The overall results demonstrated that integrating ATR-IR and RS was possible and could improve the prediction accuracy of TAC and TPC in CRWs.

Selection of the most informative near infrared spectroscopy wavebands for continuous glucose monitoring in human serum

By controlling the blood glucose levels of diabetics permanent diabetes-related problems such as blindness and loss of limbs can be delayed or even avoided. Therefore, many researchers have aimed at the development of a non-invasive sensor to monitor the blood glucose level continuously. As non-invasive measurements through the skin, the ear lobe or the gums have proven to be either unreliable or impractical, attention has recently shifted to minimally invasive sensors which measure the glucose content in serum or interstitial fluid. Thanks to the development of on-chip spectrometers minimally invasive, implantable devices are coming within reach. However, this technology does not allow to acquire a large number of wavelengths over a broad range. Therefore, the most informative combination of a limited number of variables should be selected. In this study, Interval PLS (iPLS), Variable Importance in Projection (VIP), Uninformative Variable Elimination (UVE), Bootstrap-PLS coefficients, Moving window, CorXyPLS, Interval Random Frog-PLS and combinations of these methods were used in order to address the question whether the short wave band (800–1500nm), first overtone band (1500–1800nm), the combination band (2050–2300nm) or a combination of them is the most informative region for glucose measurements and which wavebands should be measured within these wavelength ranges. The three different data sets employed focus on the determination of (1) glucose in aqueous solutions over the 1–30mM range in presence of urea and sodium D-lactate, (2) glucose in aqueous solutions over the 2–16mM range in presence of icodextrin and urea and (3) glucose in human serum samples. The best results for the first, second and third data sets were obtained by selecting 40, 130 and 20 variables resulting in a PLS model with an RMSEP of 0.56, 0.59 and 1.5mM, respectively. It was found that the first overtone band is most informative for aqueous solutions, while for glucose measurement of serum samples the combination band was found to be the better choice.

On-line monitoring the extract process of Fu-fang Shuanghua oral solution using near infrared spectroscopy and different PLS algorithms

An on-line near infrared (NIR) spectroscopy monitoring method with an appropriate multivariate calibration method was developed for the extraction process of Fu-fang Shuanghua oral solution (FSOS). On-line NIR spectra were collected through two fiber optic probes, which were designed to transmit NIR radiation by a 2mm flange. Partial least squares (PLS), interval PLS (iPLS) and synergy interval PLS (siPLS) algorithms were used comparatively for building the calibration regression models. During the extraction process, the feasibility of NIR spectroscopy was employed to determine the concentrations of chlorogenic acid (CA) content, total phenolic acids contents (TPC), total flavonoids contents (TFC) and soluble solid contents (SSC). High performance liquid chromatography (HPLC), ultraviolet spectrophotometric method (UV) and loss on drying methods were employed as reference methods. Experiment results showed that the performance of siPLS model is the best compared with PLS and iPLS. The calibration models for AC, TPC, TFC and SSC had high values of determination coefficients of (R2) (0.9948, 0.9992, 0.9950 and 0.9832) and low root mean square error of cross validation (RMSECV) (0.0113, 0.0341, 0.1787 and 1.2158), which indicate a good correlation between reference values and NIR predicted values. The overall results show that the on line detection method could be feasible in real application and would be of great value for monitoring the mixed decoction process of FSOS and other Chinese patent medicines.

Characterization of wheat varieties using terahertz time-domain spectroscopy.

Terahertz (THz) spectroscopy and multivariate data analysis were explored to discriminate eight wheat varieties. The absorption spectra were measured using THz time-domain spectroscopy from 0.2 to 2.0 THz. Using partial least squares (PLS), a regression model for discriminating wheat varieties was developed. The coefficient of correlation in cross validation (R) and root-mean-square error of cross validation (RMSECV) were 0.985 and 1.162, respectively. In addition, interval PLS was applied to optimize the models by selecting the most appropriate regions in the spectra, improving the prediction accuracy (R = 0.992 and RMSECV = 0.967). Results demonstrate that THz spectroscopy combined with multivariate analysis can provide rapid, nondestructive discrimination of wheat varieties.

An improved ensemble model for the quantitative analysis of infrared spectra

Spectroscopy is widely applied in fast and non-destructive quantitative analysis fields. However, the translation of raw spectra into a final analysis remains a complex challenge. This paper presents a derivative spectra modeling method based on a singular perturbation technique, termed ensemble derivative spectra partial least squares (EDSPLS), for the quantitative analysis of infrared spectra. EDSPLS focuses on obtaining a final ensemble model by making full use of derivative spectra information. The algorithm combines the advantages of derivative spectra, interval PLS and fusion modeling. The process of EDSPLS includes two steps of stacked PLS. First, the inner-stack step is performed on the candidate sub-interval spectra of the zero-order, first-order and second-order derivative spectra space. Second, in the outer-stack step, three stacked models generated from the different derivative spectra space are integrated by certain weighting rules to obtain the final model. Experimental results on two public infrared spectra datasets demonstrate that the proposed EDSPLS provides superior predictive power and outperforms the conventional PLS method. Compared with the single model, the new ensemble model can provide more robust prediction results and can be considered to be an alternative choice for quantitative analytical applications.

Real-time monitoring of process parameters in rice wine fermentation by a portable spectral analytical system combined with multivariate analysis

A portable and low-cost spectral analytical system was developed and used to monitor real-time process parameters, i.e. total sugar content (TSC), alcohol content (AC) and pH during rice wine fermentation. Various partial least square (PLS) algorithms were implemented to construct models. The performance of a model was evaluated by the correlation coefficient (Rp) and the root mean square error (RMSEP) in the prediction set. Among the models used, the synergy interval PLS (Si-PLS) was found to be superior. The optimal performance by the Si-PLS model for the TSC was Rp=0.8694, RMSEP=0.438; the AC was Rp=0.8097, RMSEP=0.617; and the pH was Rp=0.9039, RMSEP=0.0805. The stability and reliability of the system, as well as the optimal models, were verified using coefficients of variation, most of which were found to be less than 5%. The results suggest this portable system is a promising tool that could be used as an alternative method for rapid monitoring of process parameters during rice wine fermentation.

Comparison of multivariate linear regression methods in micro-Raman spectrometric quantitative characterization

Chemical imaging was used in this study as a powerful analytical tool to characterize pharmaceuticals in solid form. The majority of analyses are evaluated with bilinear modelling using only the pure component spectra or just the chemical images themselves to estimate the concentrations in each pixel, which are far from true quantitative determination. Our aim was to create more accurate concentration images using regression methods. For the first time in chemical imaging, variable selections with interval partial least squares (PLS) and with genetic algorithms (PLS-GA) were applied to increase the efficiency of the models. These were compared to numerous bilinear modelling and multivariate linear regression methods such as univariate regression, classical least squares (CLS), multivariate curve resolution–alternating least squares (MCR-ALS), principal component regression (PCR) and partial least squares (PLS). Two component spray-dried pharmaceuticals were used as a model. The paper is shown that, in contrast to the usual way of using either external validation or cross-validation, both should be performed simultaneously in order to get a clear picture of the prediction errors and to be able to select the appropriate models. Using PLS with variable selection, the root mean square errors were reduced to 3% per pixel by keeping only those peaks that are truly necessary for the estimation of concentrations. It is also shown that interval PLS can point out the best peak for univariate regression, and can thereby be of great help even when regulations allow only univariate models for product quality testing. Variable selection, besides yielding more accurate overall concentrations across a Raman map, also reduces the deviation among pixel concentrations within the images, thereby increasing the sensitivity of homogeneity studies. Copyright © 2015 John Wiley & Sons, Ltd.

Rapid Measurement of Antioxidant Activity and γ-Aminobutyric Acid Content of Chinese Rice Wine by Fourier-Transform Near Infrared Spectroscopy

In this study, Fourier-transform near infrared (FT-NIR) spectroscopy in combination with chemometrics was utilized to determine the antioxidant capacity and γ-aminobutyric acid (GABA) content of Chinese rice wine (CRW). Interval partial least-squares (iPLS) and extreme learning machine (ELM) were used to improve the performances of partial least-squares (PLS) models. In total, four different calibration models, namely PLS, iPLS, ELM, and ELM models based on the subintervals selected by iPLS (iELM), were developed in this study. It was observed that the performances of models based on the efficient spectra intervals selected by iPLS were much better than those based on the full spectrum. In addition, nonlinear models were superior to linear models. After systemically comparison and discussion, it was found that for all of the four parameters determined, iELM model achieved the best result with excellent prediction precision. The coefficient of determination for the prediction set (R2 (pre)), and the residual predictive deviation for the prediction set were 0.932 and 4.07 for 1,1-diphenyl-2-picrylhydrazyl assay, 0.970 and 6.21 for 2,2-azino-bis-(3-ethylbenzothiazoline-6-sulfonic acid) diammonium salt assay, 0.974 and 6.29 for total reducing antioxidant power assay and 0.952 and 4.75 for GABA, respectively. The overall results demonstrated that FT-NIR combined with efficient variable selection algorithm and nonlinear regression tool could be used as a rapid alternative method for the prediction of the antioxidant capacity and GABA content of Chinese rice wine.

Evaluation of sugar content in potatoes using NIR reflectance and wavelength selection techniques

Near-infrared (NIR) diffuse reflectance has been extensively and successfully applied on quality assurance for fruits, vegetables, and food products. This study is principally aimed to extract the primary wavelengths related to the prediction of glucose and sucrose for potato tubers (of Frito Lay 1879 (FL), a chipping cultivar, and Russet Norkotah (RN), a table use cultivar, and investigating the potential of classification of potatoes based on sugar levels important to the frying industry. Whole tubers, as well as 12.7mm slices, were scanned using a NIR reflectance spectroscopic system (900–1685nm). To extract the most influential wavelength in the studied range, interval partial least squares (IPLS), and genetic algorithm (GA) were utilized. Partial least squares regression (PLSR) was applied for building prediction models. Prediction models for RN showed stronger correlation than FL with r(RPD) (correlation coefficient (ratio of reference standard deviation to root mean square error of the model)) values for whole tubers for glucose being as high as 0.81(1.70), and 0.97(3.91) for FL and RN; in the case of sliced samples the values were 0.74(1.49) and 0.94(2.73) for FL and RN. Lower correlation was obtained for sucrose with r(RPD) for whole tubers as high as 0.75(1.52), 0.92(2.57) for FL and RN; and the values for sliced samples were 0.67(1.31) and 0.75(1.41) for FL and RN respectively. Classification of potatoes based on sugar levels was conducted and training models were built using different classifiers (linear discriminant analysis (LDA), K-nearest neighbor (Knn), partial least squares discriminant analysis (PLSDA), and artificial neural network (ANN)), in addition to classifier fusion. To obtain more robust classification models for the training data, 4-fold cross validation was used and results were tested using separate sets of data. Classification rates of the testing set for whole tubers, based on glucose, were as high as 81% and 100% for FL and RN. For sliced samples, the rates were 83% and 81% for FL and RN. Generally, lower classification rates were obtained based on sucrose with values of whole tubers of 71%, and 79% for FL and RN, and for sliced samples the rates were 75%, and 82% which follows a similar trend as PLSR results. This study presents a potential of using selected wavelengths and NIR reflectance spectroscopy to effectively evaluate the sugar content of potatoes and classify potatoes based on thresholds that are crucial for the frying industry.

Identifying bioactive components in natural products through chromatographic fingerprint

Bioactive component identification is a crucial issue in search for new drug leads. We provide a new strategy to search for bioactive components based on Sure Independence Screening (SIS) and interval PLS (iPLS). The method, which is termed as SIS–iPLS, is not only able to find out the chief bioactive components, but also able to judge how many components should be there responsible for the total bioactivity. The method is totally “data-driven” with no need for prior knowledge about the unknown mixture analyzed, therefore especially suitable for effect-directed work like bioassay-guided fractionation. Two data sets, a synthetic mixture system of twelve components and a suite of Radix Puerariae Lobatae extracts samples, are used to test the identification ability of the SIS–iPLS method.