Yidan Bao

Determination of Calcium Content in Powdered Milk Using Near and Mid-Infrared Spectroscopy with Variable Selection and Chemometrics

Near infrared (NIR) and mid-infrared (MIR) spectroscopy techniques were evaluated to determine calcium content in powdered milk. A hybrid spectral variable selection algorithm combined with uninformation variable elimination (UVE) and successive projections algorithm (SPA) selected 11 NIR and 15 MIR variables from full 2,756 NIR and 3,727 MIR variables, respectively. Predicted results of least-squares support vector machine models for the samples in the prediction set show that the 15 MIR variables obtained much better results (0.930 for coefficient of determination (r2), 3.703 for residual predictive deviation (RPD), 30.162 for root mean square error of prediction set (RMSEP) and 5.22% for relative errors of prediction (RSEP)) than 11 NIR variables did (0.636 for r2, 1.587 for RPD, 78.815 for RMSEP, and 13.40% for RSEP). The overall results indicate that MIR spectroscopy could be applied as a precision and rapid method to determine calcium content in powdered milk. The good performance shows a potential application using UVE-SPA to select NIR and MIR effective variables.

Measurement of Soluble Solid Contents and pH of White Vinegars Using VIS/NIR Spectroscopy and Least Squares Support Vector Machine

Visible and near-infrared (VIS/NIR) spectroscopy combined with least squares support vector machine (LS-SVM) was employed to determine soluble solid contents (SSC) and pH of white vinegars. Three hundred twenty vinegar samples were distributed into a calibration set (240 samples) and a validation set (80 samples). Partial least squares (PLS) analysis was implemented for the regression model and extraction of latent variables (LVs). The selected LVs were used as LS-SVM input variables. Finally, LS-SVM models with radial basis function kernel were achieved with the comparison of PLS models. The results indicated that LS-SVM outperformed PLS models. The correlation coefficient (r), root mean square error of prediction, bias, and residual prediction deviation for the validation set were 0.988, 0.207°Brix, 0.183, and 6.4 for SSC whereas these were 0.988, 0.041, −0.002, and 6.5 for pH, respectively. The overall results indicated that VIS/NIR spectroscopy and LS-SVM could be used as a rapid alternative method for the prediction of SSC and pH of white vinegars, and the results could be helpful for the fermentation process and quality control monitoring of white vinegar production.

Potential of Visible and Near Infrared Spectroscopy and Pattern Recognition for Rapid Quantification of Notoginseng Powder with Adulterants

Notoginseng is a classical traditional Chinese medical herb, which is of high economic and medical value. Notoginseng powder (NP) could be easily adulterated with Sophora flavescens powder (SFP) or corn flour (CF), because of their similar tastes and appearances and much lower cost for these adulterants. The objective of this study is to quantify the NP content in adulterated NP by using a rapid and non-destructive visible and near infrared (Vis-NIR) spectroscopy method. Three wavelength ranges of visible spectra, short-wave near infrared spectra (SNIR) and long-wave near infrared spectra (LNIR) were separately used to establish the model based on two calibration methods of partial least square regression (PLSR) and least-squares support vector machines (LS-SVM), respectively. Competitive adaptive reweighted sampling (CARS) was conducted to identify the most important wavelengths/variables that had the greatest influence on the adulterant quantification throughout the whole wavelength range. The CARS-PLSR models based on LNIR were determined as the best models for the quantification of NP adulterated with SFP, CF, and their mixtures, in which the rP values were 0.940, 0.939, and 0.867 for the three models respectively. The research demonstrated the potential of the Vis-NIR spectroscopy technique for the rapid and non-destructive quantification of NP containing adulterants.

Pattern recognition of visible and near-infrared spectroscopy from bayberry juice by use of partial least squares and a backpropagation neural network

Visible and near-infrared reflectance (visible-NIR) spectroscopy is applied to discriminate different varieties of bayberry juices. The discrimination of visible-NIR spectra from samples is a matter of pattern recognition. By partial least squares (PLS), the spectrum is reduced to certain factors, which are then taken as the input of the backpropagation neural network (BPNN). Through training and prediction, three different varieties of bayberry juice are classified based on the output of the BPNN. In addition, a mathematical model is built and the algorithm is optimized. With proper parameters in the training set, 100% accuracy is obtained by the BPNN. Thus it is concluded that the PLS analysis combined with the BPNN is an alternative for pattern recognition based on visible and NIR spectroscopy.

Fast detection of peroxidase (POD) activity in tomato leaves which infected with Botrytis cinerea using hyperspectral imaging

Tomatoes are cultivated around the world and gray mold is one of its most prominent and destructive diseases. An early disease detection method can decrease losses caused by plant diseases and prevent the spread of diseases. The activity of peroxidase (POD) is very important indicator of disease stress for plants. The objective of this study is to examine the possibility of fast detection of POD activity in tomato leaves which infected with Botrytis cinerea using hyperspectral imaging data. Five pre-treatment methods were investigated. Genetic algorithm-partial least squares (GA-PLS) was applied to select optimal wavelengths. A new fast learning neural algorithm named extreme learning machine (ELM) was employed as multivariate analytical tool in this study. 21 optimal wavelengths were selected by GA-PLS and used as inputs of three calibration models. The optimal prediction result was achieved by ELM model with selected wavelengths, and the r and RMSEP in validation were 0.8647 and 465.9880 respectively. The results indicated that hyperspectral imaging could be considered as a valuable tool for POD activity prediction. The selected wavelengths could be potential resources for instrument development.

Quantitative Analysis of Total Amino Acid in Barley Leaves under Herbicide Stress Using Spectroscopic Technology and Chemometrics

Visible and near infrared (Vis/NIR) spectroscopy were employed for the fast and nondestructive estimation of the total amino acid (TAA) content in barley (Hordeum vulgare L.) leaves. The calibration set was composed of 50 samples; and the remaining 25 samples were used for the validation set. Seven different spectral preprocessing methods and six different calibration methods (linear and nonlinear) were applied for a comprehensive prediction performance comparison. Successive projections algorithm (SPA) and regression coefficients (RC) were applied to select effective wavelengths (EWs). The results indicated that the latent variables-least-squares-support vector machine (LV-LS-SVM) model achieved the optimal performance. The prediction results by LV-LS-SVM with raw spectra were achieved with a correlation coefficients (r) = 0.937 and root mean squares error of prediction (RMSEP) = 0.530. The overall results showed that the NIR spectroscopy could be used for determination of TAA content in barley leaves with an excellent prediction precision; and the results were also helpful for on-field monitoring of barley growing status under herbicide stress during different growth stages.

Image Detection of Rice Fissures Using Biorthogonal B-Spline Wavelets in Multi-resolution Spaces

An image analysis method was developed with higher detection accuracy for rice fissures compared with using the classical Canny and Sobel methods. The rice images are obtained using a common scanning machine with resolution of 600 dpi. The scanning images are enhanced by the gamma correction and smoothed using the anisotropic nonlinear diffusion PDEs. The diffusion process is stopped when the peak signal to noise ratio is lower than 30 dB or changes slowly. After that the wavelet coefficients of the smoothed images are calculated using continuous wavelet transform with the biorthogonal B-spline wavelets bior1.5 in multi-resolution spaces. The wavelet coefficients in y forward direction are used as the magnitudes. Finally, the magnitudes are standardized and used for the judgment of the fissures as the local maxima. Two different kinds of rice kernels are used for the test of the effectiveness of the proposed algorithm, including 30 long- and 20 medium-cracked grains with 1, 2, 3, or 4 fissures. The results demonstrate a satisfying performance of the fissure detecting systems, and even the faint lines of the fissures can also be detected.

Detection of Glutamic Acid in Oilseed Rape Leaves Using Near Infrared Spectroscopy and the Least Squares-Support Vector Machine

Amino acids are quite important indices to indicate the growth status of oilseed rape under herbicide stress. Near infrared (NIR) spectroscopy combined with chemometrics was applied for fast determination of glutamic acid in oilseed rape leaves. The optimal spectral preprocessing method was obtained after comparing Savitzky-Golay smoothing, standard normal variate, multiplicative scatter correction, first and second derivatives, detrending and direct orthogonal signal correction. Linear and nonlinear calibration methods were developed, including partial least squares (PLS) and least squares-support vector machine (LS-SVM). The most effective wavelengths (EWs) were determined by the successive projections algorithm (SPA), and these wavelengths were used as the inputs of PLS and LS-SVM model. The best prediction results were achieved by SPA-LS-SVM (Raw) model with correlation coefficient r = 0.9943 and root mean squares error of prediction (RMSEP) = 0.0569 for prediction set. These results indicated that NIR spectroscopy combined with SPA-LS-SVM was feasible for the fast and effective detection of glutamic acid in oilseed rape leaves. The selected EWs could be used to develop spectral sensors, and the important and basic amino acid data were helpful to study the function mechanism of herbicide.

Fast discrimination of juicy peach varieties by Vis/NIR spectroscopy based on Bayesian-SDA and PCA

Visible/Near-infrared reflectance spectroscopy (Vis/NIRS) was applied to variety discrimination of juicy peach. A total of 75 samples were investigated for Vis/NIRS using a field spectroradiometer. Chemometrics was used to build the relationship between the absorbance spectra and varieties. Principle component analysis (PCA) was executed to reduce numerous wavebands into 8 principle components (PCs) as variables of stepwise discrimination analysis (SDA). After execution of SDA through variables selection with 21 samples as validation set, the final results shown an excellent performance of 100% varieties discrimination which was better than the one only predicted by using partial least squares (PLS) model. The results showed the potential ability of Vis/NIRS coupled with SDA-PCA algorithm to discriminate the varieties of juicy peach. The analysis model was rapid, objective and accurate.

Discrimination of rapeseed and weeds under actual field conditions based on principal component analysis and artificial neural network by VIS/NIR spectroscopy

The study documented successful discrimination between five weed species and rapeseed plants under actual field conditions using visible and near infrared (Vis/NIR) spectroscopy. A hybrid recognition model, BP artificial neural networks (BP-ANN) combined with principal component analysis (PCA), had been established for discrimination of weeds in rapeseed field. Spectra tests were performed on the rapeseed and five-weed species canopy of 180 samples in the field using a spectrophotometer (325-1075 nm). 6 optimal PCs were selected as the input of BP neural networks to build the prediction model. Rapeseed samples were marked as 1, while the five weed species marked as 2, 3, 4, 5, 6, which were used as output set of BP-ANN. 120 samples were randomly selected as the training set, and the remainder as prediction set. It showed excellent predictions with the correlation value of 0.9745, and the relative standard deviation (RSD) was under 5% thus 100% of prediction accuracy was achieved. The results are promising for further work in real-time identification of weed patches in rapeseed fields for precision weed management.