Zou Xiaobo

Rapid detecting total acid content and classifying different types of vinegar based on near infrared spectroscopy and least-squares support vector machine.

More than 3.2 million litres of vinegar is consumed every day in China. There are many types of vinegar in China. How to control the quality of vinegar is problem. Near infrared spectroscopy (NIR) transmission technique was applied to achieve this purpose. Ninety-five vinegar samples from 14 origins covering 11 provinces in China were collected. They were classified into mature vinegar, aromatic vinegar, rice vinegar, fruit vinegar, and white vinegar. Fruit vinegar and white vinegar were separated from the other traditional categories in the two-dimension principal component space of NIR after principle component analysis (PCA). Least-squares support vector machine (LS-SVM) as the pattern recognition was firstly applied to identify mature vinegar, aromatic vinegar, rice vinegar in this study. The top two principal components (PCs) were extracted as the input of LS-SVM classifiers by principal component analysis (PCA). The best experimental results were obtained using the radial basis function (RBF) LS-SVM classifier with σ=0.8. The accuracies of identification were more than 85% for three traditional vinegar categories. Compared with the back propagation artificial neural network (BP-ANN) approach, LS-SVM algorithm showed its excellent generalisation for identification results. As total acid content (TAC) is highly connecting with the quality of vinegar, NIR was used to prediction the TAC of samples. LS-SVM was applied to building the TAC prediction model based on spectral transmission rate. Compared with partial least-square (PLS) model, LS-SVM model gave better precision and accuracy in predicting TAC. The determination coefficient for prediction (R(p)) of the LS-SVM model was 0.919 and root mean square error for prediction (RMSEP) was 0.3226. This work demonstrated that near infrared spectroscopy technique coupled with LS-SVM could be used as a quality control method for vinegar.

In vivo noninvasive detection of chlorophyll distribution in cucumber (Cucumis sativus) leaves by indices based on hyperspectral imaging.

The objective of this study was to investigate the spectral behavior of the relationship between reflectance and chlorophyll content and to develop a technique for non-destructive chlorophyll estimation and distribution in leaves using hyperspectral imaging. The hyperspectral imaging data cube of cucumber (Cucumis sativus) leaves in the range of 450-850 nm was investigated and preprocessed. Sixty optical signatures or indices as a function of the associated reflectance (R(λ)) at the special wavelength (λ) nm which proposed in the literatures were used to predict the total chlorophyll content in cucumber leaves. Finally, R(710)/R(760), (R(780)-R(710))/(R(780)-R(680)), (R(750)-R(705))/(R(750)+R(705)), (R(680)-R(430))/(R(680)+R(430)), R(860)/(R(550)×R(708)), (R(695-705))(-1)-(R(750-800))(-1), and REP-LEM (a index based on red edge position and estimated with a linear extrapolation method) were identified as optimum indices. Red-edge waveband (680-780 nm) appeared in all these optimum indices, indicating the importance of REP (red edge position) in chlorophyll estimation. When (R(695-705))(-1)-(R(750-800))(-1), the best index was applied to an independent validation set, chlorophyll content (r=0.8286) were reasonably well predicted, indicating model robustness. Depending on the sample, this technique enables to identify and characterize the relative content of various chlorophyll that distribution in the cucumber leaves. The map shows a relatively low level of chlorophyll at margins. Higher level can be noticed in the regions along the main veins and in some areas exhibiting dark green tissue. Our results indicate that hyperspectral imaging has considerable promise for predicting pigments in leaves and, the pigments can be detected in situ in living plant samples non-destructively.

Genetic Algorithm Interval Partial Least Squares Regression Combined Successive Projections Algorithm for Variable Selection in Near-Infrared Quantitative Analysis of Pigment in Cucumber Leaves

Variable (or wavelength) selection plays an important role in the quantitative analysis of near-infrared (NIR) spectra. A method based on a genetic algorithm interval partial least squares regression (GAiPLS) combined successive projections algorithm (SPA) was proposed for variable selection in NIR spectroscopy. GAiPLS was used to select informative interval regions among the spectrum, and then SPA was employed to select the most informative variables and to minimize collinearity between those variables in the model. The performance of the proposed method was compared with the full-spectrum model, conventional interval partial least squares regression (iPLS), and backward interval partial least squares regression (BiPLS) for modeling the NIR data sets of pigments in cucumber leaf samples. The multiple linear regression (MLR) model was obtained with eight variables for chlorophylls and five variables for carotenoids selected by SPA. When the SPA model was applied to the prediction of the validation set, the correlation coefficients of the predicted value by MLR and the measured value for the validation data set (rp) of chlorophylls and carotenoids were 0.917 and 0.932, respectively. Results show that the proposed method was able to select important wavelengths from the NIR spectra and makes the prediction more robust and accurate in quantitative analysis.Variable (or wavelength) selection plays an important role in the quantitative analysis of near-infrared (NIR) spectra. A method based on a genetic algorithm interval partial least squares regression (GAiPLS) combined successive projections algorithm (SPA) was proposed for variable selection in NIR spectroscopy. GAiPLS was used to select informative interval regions among the spectrum, and then SPA was employed to select the most informative variables and to minimize collinearity between those variables in the model. The performance of the proposed method was compared with the full-spectrum model, conventional interval partial least squares regression (iPLS), and backward interval partial least squares regression (BiPLS) for modeling the NIR data sets of pigments in cucumber leaf samples. The multiple linear regression (MLR) model was obtained with eight variables for chlorophylls and five variables for carotenoids selected by SPA. When the SPA model was applied to the prediction of the validation set, the correlation coefficients of the predicted value by MLR and the measured value for the validation data set (r(p)) of chlorophylls and carotenoids were 0.917 and 0.932, respectively. Results show that the proposed method was able to select important wavelengths from the NIR spectra and makes the prediction more robust and accurate in quantitative analysis.

Measurement of total anthocyanins content in flowering tea using near infrared spectroscopy combined with ant colony optimization models

Flowering tea has become a popular beverage consumed across the world. Anthocyanins content is considered as an important quality index of flowering tea. The feasibility of using near infrared (NIR) spectra at the wavelength range of 10,000-4000 cm(-1) for rapid and nondestructive determination of total anthocyanins content in flowering tea was investigated. Ant colony optimization interval partial least squares (ACO-iPLS) and Genetic algorithm interval partial least squares (GA-iPLS) were used to develop calibration models for total anthocyanins content. Two characteristic wavelength regions (4590-4783, 5770-5,963 cm(-1)), which corresponding to the ultraviolet/visible absorption bands of anthocyanins, were selected by ACO-iPLS. The optimal ACO-iPLS model for total anthocyanins content (R=0.9856, RMSECV=0.1,198 mg/g) had better performance than full-spectrum PLS, iPLS, and GA-iPLS models. It could be concluded that NIR spectroscopy has significant potential in the nondestructive determination of total anthocyanins content in flowering tea.

Detection of meat-borne trimethylamine based on nanoporous colorimetric sensor arrays

Trimethylamine (TMA) is a key measurement indicator for meat spoilage. In order to develop simple, cheap, and sensitive sensors for TMA detection, a nanoporous colorimetric sensor array (NCSA) was developed. A sol-gel method has been used to obtain TiO2 nanoporous film as substrate material to improve the sensitivity and stability of the CSA. The sensor enabled the visual detection of TMA gas from the permissible exposure limits (PEL) 10 ppm to 60 ppb concentrations with significant response. Principal component analysis (PCA) was used to characterize the functional relationship between the color difference data and TMA concentrations. Furthermore, the NCSA was used to predict the presence of TMA in Yao-meat. A partial least square (PLS) prediction model was obtained with the correlation coefficients of 0.896 and 0.837 in calibration and prediction sets, respectively. This research suggested that the NCSA offers a useful technology for quality evaluation of TMA in meat.

Discrimination of honeys using colorimetric sensor arrays, sensory analysis and gas chromatography techniques.

Aroma profiles of six honey varieties of different botanical origins were investigated using colorimetric sensor array, gas chromatography-mass spectrometry (GC-MS) and descriptive sensory analysis. Fifty-eight aroma compounds were identified, including 2 norisoprenoids, 5 hydrocarbons, 4 terpenes, 6 phenols, 7 ketones, 9 acids, 12 aldehydes and 13 alcohols. Twenty abundant or active compounds were chosen as key compounds to characterize honey aroma. Discrimination of the honeys was subsequently implemented using multivariate analysis, including hierarchical clustering analysis (HCA) and principal component analysis (PCA). Honeys of the same botanical origin were grouped together in the PCA score plot and HCA dendrogram. SPME-GC/MS and colorimetric sensor array were able to discriminate the honeys effectively with the advantages of being rapid, simple and low-cost. Moreover, partial least squares regression (PLSR) was applied to indicate the relationship between sensory descriptors and aroma compounds.

The study of gas sensor array signal processing with new genetic algorithms

Abstract In the field of gas sensor array signal processing, one of the most important and the most difficult procedures is the identification of the feature parameters (FP). Then we can use the optimum FP to distinguish different odours sensitively. Currently, however, there is no acceptable method for extracting the optimum FP. Therefore, a new method called organization feature parameter based on formulae expression tree by using genetic algorithms has been proposed in this paper. It could solve the problem how to getting optimum FP, and make the genetic algorithm more convenient and straight. The formulae expression tree for the fusion of feature parameters has been discussed and then the selection, crossover and mutation for the genetic algorithm were studied in depth. In order to prove the advantage of the method, some experiments adopting the new method have been carried out to recognize vinegar odours by using gas sensor array. The result demonstrated that the new method is a very useful and effective method for pattern recognition.

Rapid prediction of phenolic compounds and antioxidant activity of Sudanese honey using Raman and Fourier transform infrared (FT-IR) spectroscopy

Fourier transform infrared with attenuated total reflectance (FTIR-ATR) and Raman spectroscopy combined with partial least square regression (PLSR) were applied for the prediction of phenolic compounds and antioxidant activity in honey. Standards of catechin, syringic, vanillic, and chlorogenic acids were used for the identification and quantification of the individual phenolic compounds in six honey varieties using HPLC-DAD. Total antioxidant activity (TAC) and ferrous chelating capacity were measured spectrophotometrically. For the establishment of PLSR model, Raman spectra with Savitzky-Golay smoothing in wavenumber region 1500-400cm-1 was used while for FTIR-ATR the wavenumber regions of 1800-700 and 3000-2800cm-1 with multiplicative scattering correction (MSC) and Savitzky-Golay smoothing were used. The determination coefficients (R2) were ranged from 0.9272 to 0.9992 for Raman while from 0.9461 to 0.9988 for FTIT-ART. The FTIR-ATR and Raman demonstrated to be simple, rapid and nondestructive methods to quantify phenolic compounds and antioxidant activities in honey.

A new room temperature gas sensor based on pigment-sensitized TiO2 thin film for amines determination

A new room temperature gas sensor was fabricated with pigment-sensitized TiO2 thin film as the sensing layer. Four natural pigments were extracted from spinach (Spinacia oleracea), red radish (Raphanus sativus L), winter jasmine (Jasminum nudiflorum), and black rice (Oryza sativa L. indica) by ethanol. Natural pigment-sensitized TiO2 sensor was prepared by immersing porous TiO2 films in an ethanol solution containing a natural pigment for 24h. The hybrid organic-inorganic formed films here were firstly exposed to atmospheres containing methylamine vapours with concentrations over the range 2-10 ppm at room temperature. The films sensitized by the pigments from black-rice showed an excellent gas-sensitivity to methylamine among the four natural pigments sensitized films due to the anthocyanins. The relative change resistance, S, of the films increased almost linearly with increasing concentrations of methylamine (r=0.931). At last, the black rice pigment sensitized TiO2 thin film was used to determine the biogenic amines generated by pork during storage. The developed films had good sensitivity to analogous gases such as putrscine, and cadaverine that will increase during storage.

Using Genetic Algorithm Interval Partial Least Squares Selection of the Optimal near Infrared Wavelength Regions for Determination of the Soluble Solids Content of “Fuji” Apple

A near infrared (NIR) spectroscopy acquisition device was developed in this study using an apple as the test sample. With this device, the apple was rolled while collecting the NIR spectra. The feasibility of using efficient selection of wavelength regions in Fourier transform NIR for a rapid and conclusive determination of the inner qualities of fruit such as soluble solids content (SSC) of apples was investigated. Graphically-oriented local multivariate calibration modelling procedures called genetic algorithm interval partial least-squares (GA-iPLS) were applied to select efficient spectral regions that provide the lowest prediction error, in comparison to the full-spectrum model. The optimal SSC predictions were obtained from a seven-factor model using five intervals among 40 intervals selected by GA-iPLS. In the determination, a root mean square error of prediction of 0.42 °Brix for SSC of apples was obtained. The result demonstrated that the new method is a very useful and effective method for developing high precision PLS models based on optimal wavelength regions.