Determination of Amino Acid Nitrogen in Soy Sauce Using Near Infrared Spectroscopy Combined with Characteristic Variables Selection and Extreme Learning Machine

Effect of Sequential Inoculation of Tetragenococcus halophilus and Wickerhamomyces anomalus on the Flavour Formation of Early-Stage Moromi Fermented at a Lower Temperature

Microbial inoculation in moromi fermentation has a great influence on the physicochemical and flavour properties of soy sauces. This work investigated the effect of inoculating Tetragenococcus halophilus and Wickerhamomyces anomalus on the flavour formation of early-stage moromi (30 days) fermented at a lower temperature (22 °C) by determining their physicochemical and aroma changes. The results showed that single yeast or LAB inoculation increased the production of amino nitrogen, lactic acid and acetic acid, as well as free amino acids and key flavour components. Particularly, the sequential inoculation of T. halophilus and W. anomalus produced more free amino acids and aromatic compounds, and there might be synergistic effects between these two strains. More characteristic soy sauce flavour compounds, such as benzaldehyde, HEMF, guaiacol and methyl maltol were detected in the sequentially inoculated moromi, and this sample showed higher scores in savoury, roasted and caramel intensities. These results confirmed that sequential inoculation of T. halophilus and W. anomalus could be a choice for the future production of moromi with good flavour and quality under a lower temperature.

Properties investigations of rape stalks fermented by different salt concentration: Effect of volatile compounds and physicochemical indexes

In order to find out the effect of salt concentration on fermented rape stalks, the physicochemical quality and volatile components was investigated using high performance liquid chromatography (HPLC) and headspace solid phase microextraction gas chromatography-mass spectrometry (HS-SPME-GC-MS). The results showed that there were abundant kinds of free amino acids (FAAs) in all samples, mainly presenting sweet, umami and bitter taste. Through taste activity value (TAV), His, Glu, and Ala contributed significantly to the taste of the sample. 51 volatile components were identified, of which the relative contents of ketones and alcohols were high. By the relative odor activity value (ROAV) analysis, the main components that had a great impact on the flavor were phenylacetaldehyde, β-Ionone, ethyl palmitate and furanone. Adjusting the appropriate salt concentration for fermentation could improve the comprehensive quality of fermented rape stalks and promote the development and utilization of rape products.

Selection of a Fermentation Strategy for the Preparation of Clam Sauce with Acceptable Flavor Perception

Flavor, which mainly depends on volatile compounds, is an important index for evaluating the quality of clam sauce. This study investigated the volatile compounds in clam sauce prepared using four different methods and the influence of aroma characteristics. Fermenting a mixture of soybean koji and clam meat improved the flavor of the final product. Solid-phase microextraction (SPME) combined with gas chromatography-mass spectrometry (GC-MS) identified 64 volatile compounds. Nine key flavor compounds, namely, 3-methylthio-1-propanol, 2-methoxy-4-vinylphenol, phenylethyl alcohol, 1-octen-3-ol, α-methylene phenylacetaldehyde, phenyl-oxirane, 3-phenylfuran, phenylacetaldehyde, and 3-octenone, were selected using variable importance in projection (VIP). The results of the electronic nose and tongue detection of the aroma characteristics of the samples prepared by four different fermentation methods were consistent with those of GC-MS analysis. The clam sauce prepared by mixing soybean koji with fresh clam meat possessed better flavor and quality than that prepared via other methods.

Analysis of the Composition of Different Instars of Tenebrio molitor Larvae using Near-Infrared Reflectance Spectroscopy for Prediction of Amino and Fatty Acid Content

Insects are a sustainable protein source for food and feed. The yellow mealworm (Tenebrio molitor L.) is a promising candidate for industrial insect rearing and was the focus of this study. This research revealed the diversity of Tenebrio molitor larvae in the varying larval instars in terms of the nutritional content. We hypothesized that water and protein are highest in the earlier instar, while fat content is very low but increases with larval development. Consequently, an earlier instar would be a good choice for harvest, since proteins and amino acids content decrease with larval development. Near-infrared reflectance spectroscopy (NIRS) was represented in this research as a tool for predicting the amino and fatty acid composition of mealworm larvae. Samples were scanned with a near-infrared spectrometer using wavelengths from 1100 to 2100 nm. The calibration for the prediction was developed with modified partial least squares (PLS) as the regression method. The coefficient for determining calibration (R²_C) and prediction (R²_P) were >0.82 and >0.86, with RPD values of >2.20 for 10 amino acids, resulting in a high prediction accuracy. The PLS models for glutamic acid, leucine, lysine and valine have to be improved. The prediction of six fatty acids was also possible with the coefficient of the determination of calibration (R²_C) and prediction (R²_P) > 0.77 and >0.66 with RPD values > 1.73. Only the prediction accuracy of palmitic acid was very weak, which was probably due to the narrow variation range. NIRS could help insect producers to analyze the nutritional composition of Tenebrio molitor larvae fast and easily in order to improve the larval feeding and composition for industrial mass rearing.

Effect of Salt Concentration on Flavor Characteristics and Physicochemical Quality of Pickled Brassica napus

This study aimed to elaborate on the role of salt concentration on pickled Brassica napus leaf and stem (BLS); it also contributed to the development of low-salt and healthy Brassica napus products in the harvest period. Five sets of pickled BLS samples were prepared, and the physicochemical parameters, free amino acids (FAAs), and the volatile flavor components (VFCs) were analyzed after fermentation. Results showed that some antioxidants, FAAs, and VFCs underwent dynamic changes during fermentation. Nitrite increased with an increase in the salt concentration used for fermentation. Pickled BLS contained a wide range of FAAs; a total of 23 were detected, which might be used as a source of amino acid supplementation. The VFCs were analyzed via headspace solid-phase micro-extraction (HS-SPME) combined with gas chromatography and mass spectrometry (GC-MS). A total of 51 VFCs were tentatively identified. The contribution to flavor could be expressed by the relative odor activity value (ROAV). Salt is one of the important factors affecting the quality of vegetable fermentation. Therefore, for large-scale pickled BLS production, a key issue is to balance the low salt concentration and high fermentation quality. Under the action of salt and microorganisms, the fresh BLS fermented via dry pickling, which not only improved its FAAs and VFCs, endowed the production with a unique flavor, but also prolonged the shelf life.

A review on extreme learning machine

Extreme learning machine (ELM) is a training algorithm for single hidden layer feedforward neural network (SLFN), which converges much faster than traditional methods and yields promising performance. In this paper, we hope to present a comprehensive review on ELM. Firstly, we will focus on the theoretical analysis including universal approximation theory and generalization. Then, the various improvements are listed, which help ELM works better in terms of stability, efficiency, and accuracy. Because of its outstanding performance, ELM has been successfully applied in many real-time learning tasks for classification, clustering, and regression. Besides, we report the applications of ELM in medical imaging: MRI, CT, and mammogram. The controversies of ELM were also discussed in this paper. We aim to report these advances and find some future perspectives.

Rapid and Nondestructive Detection of Proline in Serum Using Near-Infrared Spectroscopy and Partial Least Squares

Proline is an important amino acid that widely affects life activities. It plays an important role in the occurrence and development of diseases. It is of great significance to monitor the metabolism of the machine. With the great advantages of deep learning in feature extraction, near-infrared analysis technology has great potential and has been widely used in various fields. This study explored the potential application of near-infrared spectroscopy in the detection of serum proline. We collected blood samples from clinical sources, separated the serum, established a quantitative model, and determined the changes in proline. Four algorithms of SMLR, PLS, iPLS, and SA were used to model proline in serum. The root mean square errors of prediction were 0.00111, 0.00150, 0.000770, and 0.000449, and the correlation coefficients (Rp) were 0.84, 0.67, 0.91, and 0.97, respectively. The experimental results show that the model is relatively robust and has certain guiding significance for the clinical monitoring of proline. This method is expected to replace the current mainstream but time-consuming HPLC, or it can be applied to rapid online monitoring at the bedside.

Modeling method and miniaturized wavelength strategy for near-infrared spectroscopic discriminant analysis of soy sauce brand identification

The identification of soy sauce brands can avoid adulteration and fraud, which is meaningful for food safety screening. Using visible and near-infrared (Vis-NIR) spectroscopy combined with k-nearest neighbor (kNN), the four-category discriminant models of soy sauce brands were established. The soy sauce of three brands (identification) and the other ten brands (interference) were collected, and a total of four categories of samples were obtained. The spectral datasets of two measurement modals (1 mm, 10 mm) were obtained. Based on moving-window (MW) waveband screening and wavelength step-by-step phase-out (WSP), the MW-WSP-kNN algorithm was proposed and applied to the wavelength optimization for the four-category discriminant analysis. Using calibration-prediction-validation experiment design, various high accuracy models with a small number of wavelengths located in NIR region were determined. In the independent validation, for the 1 mm measurement modal, the selected thirty-five dual-wavelength models and one three-wavelength model were located in NIR combined and overtone frequency regions respectively, all achieved 100% total recognition accuracy rate (RAR_Total); for the 10 mm measurement modal, the selected seven three-wavelength models located in NIR overtone frequency region all reached more than 96.8% RAR_Total, and the optimal RAR_Total was 97.8%. The results showed the feasibility of small number of wavelengths' NIR spectroscopy applied to multi-category discriminant of soy sauce brands, with the advantages of rapid, simple and miniaturized. The proposed various small number of wavelengths' models provided a valuable reference for the design of small dedicated spectrometer with different measurement modals. The integrated optimization method and wavelength selection strategy here are also expected to be applied to other fields.

The fermentation properties and microbial diversity of soy sauce fermented by germinated soybean

BACKGROUND

The quality of commercial soy sauce is variable at present. Technical work is needed to improve the quality and flavor of soy sauce, especially in China. Material is a factor for influencing soy sauce characters in fermentation.

RESULTS

Germinated soybean sauce (fermented by germinated soybean) had a gamma aminobutyric acid (GABA) concentration of 6.83 μg mL-1 , whereas a control (a soy sauce fermented by soybean) had a GABA concentration of less than 2.42 μg mL-1 . Germinated soybean sauce also contained significantly higher levels of isoflavones, total polyphenol, and amino acid nitrogen than the control soy sauce. Microbial diversity results showed that Bacillus was the dominant bacteria in germinated soy sauce compared with the control. Aldehydes, alcohols, esters, and phenols were the major flavor components of germinated soybean sauce.

CONCLUSION

A soy sauce with high levels of GABA, isoflavones, and total polyphenol was developed using germinated soybean. Stenotrophomonas, the typical pathogen found in the control, was reduced dramatically and replaced by Bacillus during fermentation with the germinated soybean. The germinated soybean sauce exhibited a better aroma and taste than the control. Soy sauce fermented by soybeans that germinated for 48 h exhibited greater advantages than soy sauce that germinated for 24 and 72 h. © 2020 Society of Chemical Industry.

M3GPSpectra: A novel approach integrating variable selection/construction and MLR modeling for quantitative spectral analysis

Quantitative analysis of the physical or chemical properties of various materials by using spectral analysis technology combined with chemometrics has become an important method in the field of analytical chemistry. This method aims to build a model relationship (called prediction model) between feature variables acquired by spectral sensors and components to be measured. Feature selection or transformation should be conducted to reduce the interference of irrelevant information on the prediction model because original spectral feature variables contain redundant information and massive noise. Most existing feature selection and transformation methods are single linear or nonlinear operations, which easily lead to the loss of feature information and affect the accuracy of subsequent prediction models. This research proposes a novel spectroscopic technology-oriented, quantitative analysis model construction strategy named M3GPSpectra. This tool uses genetic programming algorithm to select and reconstruct the original feature variables, evaluates the performance of selected and reconstructed variables by using multivariate regression model (MLR), and obtains the best feature combination and the final parameters of MLR through iterative learning. M3GPSpectra integrates feature selection, linear/nonlinear feature transformation, and subsequent model construction into a unified framework and thus easily realizes end-to-end parameter learning to significantly improve the accuracy of the prediction model. When applied to six types of datasets, M3GPSpectra obtains 19 prediction models, which are compared with those obtained by seven linear or non-linear popular methods. Experimental results show that M3GPSpectra obtains the best performance among the eight methods tested. Further investigation verifies that the proposed method is not sensitive to the size of the training samples. Hence, M3GPSpectra is a promising spectral quantitative analytical tool.

In situ monitoring of grape seed protein hydrolysis by Raman spectroscopy

Raman spectroscopy was used to monitor the enzymatic hydrolysis process of grape seed protein. The degree of hydrolysis (DH), IC₅₀ of the ACE inhibitory activity, and peptide content of the digestive products of grape seed protein were analyzed offline. The partial least squares (PLS), interval partial least squares (IPLS), and joint interval partial least squares (Si-PLS) models of DH, IC₅₀ , and peptide content were established and the optimal pretreatment method was selected. In the optimal model, the corrected model r of the grape seed protein hydrolysis degree is 0.997, the Root Mean Square Error of Cross Validation (RMSECV) is 0.507%. The predicted model r value is 0.9932, the Root Mean Square Error of Prediction (RMSEP) is 1.15%. The corrected model r value of the IC₅₀ is 0.9965, the RMSECV is 11.9%. The r value and RMSEP of predicted model are 0.9978 and 9.64%. The corrected model r value of the peptide content is 0.9955, the RMSECV is 12.7%, the predicted model r value is 0.9953, and the RMSEP is 15.4%. These results showed that in situ real-time monitoring of grape seed protein hydrolysis process can be achieved by Raman spectroscopy. PRACTICAL APPLICATIONS: This study uses Raman spectroscopy method to establish the quantification of proteolysis, IC50, and peptide content of the simulated digestive products during grape seed proteolysis. Analyze the model to monitor and evaluate the target parameters during the entire grape seed proteolysis process. In situ real-time monitoring of grape seed proteolysis is of great significance to the entire grape seed active peptide industry.

Development of a novel wavelength selection method VCPA-PLS for robust quantification of soluble solids in tomato by on-line diffuse reflectance NIR

This work was attempted to evaluate the feasibility of a constructed on-line NIR platform coupled with efficient algorithms for rapid and robust quantification of quality parameter in cherry tomato. Specifically, a system was developed based on shortwave NIR spectroscopy for on-line quality inspection of cherry tomatoes. The spectra were recorded in diffuse reflectance mode from 900 to 1700 nm, and the conveyor belt speed was fixed to five samples per second. Three novel methods, namely variable combination population analysis (VCPA), uninformative variable elimination (UVE) and competitive adaptive reweighed sampling algorithm (CARS) were coupled with partial least square (PLS) for selecting optimal dataset, and modeling. The obtained results showed that under the optimal tuning parameters (N = 100, k = 500, ω = 14, σ = 10%), a total of 512 original variables, only 9 variables (1.75%) were extracted by VCPA. Subsequently, VCPA-PLS yielded outstanding performance in predicting soluble solid content in cherry tomatoes, with a higher correlation coefficient (R_P = 0.9053), and lower root mean square errors (RMSEP = 0.382) in prediction set. This methodology demonstrated the versatile potential of the proposed installation coupled with VCPA methods for on-line detection of total soluble solids in cherry tomatoes.

Rapid detection of quality of Japanese fermented soy sauce using near-infrared spectroscopy

This study investigated the feasibility of rapidly evaluating the final quality of Japanese fermented soy sauce (shoyu) using NIR spectroscopy and partial least-squares (PLS) regression. In total, 110 shoyu samples that had been entered in the annual soy sauce competition from 2016 to 2018 were collected and analyzed. The transmittance spectra (400-1800 nm) and the transflectance spectra (680-2500 nm) of these samples were acquired and processed by different pre-treatments. PLS regression was applied to the raw and processed spectra to construct models based on a calibration set (76 shoyu samples from 2016 and 2017) and to evaluate these models using a validation set (34 shoyu samples from 2018), according to their values for bias and root mean square error of prediction (RMSEP). The results showed that the models constructed using the full spectra of transflectance performed better than those using transmittance spectra. Comparing the influence of different regions in the transflectance spectra enabled the accuracy of the models to be improved. The model constructed from transflectance spectra from the 1800 to 2500 nm region using pre-treatment of second derivative was superior to the other models, with a bias value of -2 and the lowest RMSEP value of 13 in the validation set. To further narrow the wavelength range, the models constructed using the spectral region from 2050 to 2400 nm also showed a better performance for predicting the sensory quality of soy sauce products. This study has demonstrated that the NIR spectroscopy technique could be used as an alternative routine quality control procedure, which can rapidly and economically classify the quality of soy sauce products.

Determination of Adulteration Content in Extra Virgin Olive Oil Using FT-NIR Spectroscopy Combined with the BOSS-PLS Algorithm

This work applied the FT-NIR spectroscopy technique with the aid of chemometrics algorithms to determine the adulteration content of extra virgin olive oil (EVOO). Informative spectral wavenumbers were obtained by the use of a novel variable selection algorithm of bootstrapping soft shrinkage (BOSS) during partial least-squares (PLS) modeling. Then, a PLS model was finally constructed using the best variable subset obtained by the BOSS algorithm to quantitative determine doping concentrations in EVOO. The results showed that the optimal variable subset including 15 wavenumbers was selected by the BOSS algorithm in the full-spectrum region according to the first local lowest value of the root-mean-square error of cross validation (RMSECV), which was 1.4487 % v/v. Compared with the optimal models of full-spectrum PLS, competitive adaptive reweighted sampling PLS (CARS–PLS), Monte Carlo uninformative variable elimination PLS (MCUVE–PLS), and iteratively retaining informative variables PLS (IRIV–PLS), the BOSS–PLS model achieved better results, with the coefficient of determination (R²) of prediction being 0.9922, and the root-mean-square error of prediction (RMSEP) being 1.4889 % v/v in the prediction process. The results obtained indicated that the FT-NIR spectroscopy technique has the potential to perform a rapid quantitative analysis of the adulteration content of EVOO, and the BOSS algorithm showed its superiority in informative wavenumbers selection.

Stacked ensemble extreme learning machine coupled with Partial Least Squares-based weighting strategy for nonlinear multivariate calibration

With its simple theory and strong implementation, extreme learning machine (ELM) becomes a competitive single hidden layer feed forward networks for nonlinear multivariate calibration in chemometrics. To improve the generalization and robustness of ELM further, stacked generalization is introduced into ELM to construct a modified ELM model called stacked ensemble ELM (SE-ELM). The SE-ELM is to create a set of sub-models by applying ELM repeatedly to different sub-regions of the spectra and then combine the predictions of those sub-models according to a weighting strategy. Three different weighting strategies are explored to implement the proposed SE-ELM, such as the Winner-takes-all (WTA) weighting strategy, the constraint non-negative least squares (CNNLS) weighing strategy and the partial least squares (PLS) weighting strategy. Furthermore, PLS is suggested to be selected as the optimal weighting method that can handle the multi-colinearity among the predictions yielded by all the sub-models. The experimental assessment of the three SE-ELM models with different weighting strategies is carried out on six real spectroscopic datasets and compared with ELM, back-propagation neural network (BPNN) and Radial basis function neural network (RBFNN), statistically tested by the Wilcoxon signed rank test. The obtained experimental results suggest that, in general, all the SE-ELM models are more robust and more accurate than traditional ELM. In particular, the proposed PLS-based weighting strategy is at least statistically not worse than, and frequently better than the other two weighting strategies, BPNN, and RBFNN.

In Situ Monitoring of the Effect of Ultrasound on the Sulfhydryl Groups and Disulfide Bonds of Wheat Gluten

Ultrasound treatment can improve enzymolysis efficiency by changing the amounts of sulfhydryl groups (SH) and disulfide bonds (SS) in protein. This paper proposes an in-situ and real-time monitoring method for SH and SS during ultrasound application processes using a miniature near-infrared (NIR) optical fiber spectrometer and a chemometrics model to determine the endpoint of ultrasonic treatment. The results show that SH and SS contents fluctuated greatly with the extension of ultrasonic time. The optimal spectral intervals for SH content were 869–947, 1207–1284, 1458–1536 and 2205–2274 nm, the optimal spectral intervals of SS content were 933–992, 1388–1446, 2091–2148 and 2217–2274 nm. According to the optimal spectral intervals, the synergy interval partial least squares (Si-PLS) and error back propagation neural network (BP-ANN) for SH, SS contents were established. The BP-ANN model was better than the Si-PLS model. The correlation coefficient of the prediction set (R_p) and the root mean square error of prediction (RMSEP) for the BP-ANN model of SH were 0.9113 and 0.38 μmol/g, respectively, the R_p² and residual prediction deviation of SH were 0.8305 and 2.91, respectively. For the BP-ANN model of SS, the R_p and the RMSEP were 0.7523 and 6.56 μmol/g, respectively. The R_p² and residual prediction deviation (RPD) of SS were 0.8305 and 2.91, respectively. However, the R_p² and RPD of SS was 0.5660 and 1.64, respectively. This work demonstrated that the miniature NIR combined with BP-ANN algorithms has high potential for in-situ monitoring of SH during the ultrasonic treatment process, while the spectral prediction model of SS needs to be further developed.

Non-destructive detection for mold colonies in rice based on hyperspectra and GWO-SVR

BACKGROUND

Mold contamination of grains not only contributes to inedible food, resulting in economic losses, but also leads to mold in humans and livestock, and can even be carcinogenic to them. Rice, as one of the main grain varieties, if stored improperly, is easily susceptible to mildew. In order to detect the total number of mold colonies in rice more accurately, a method based on hyperspectral imaging technology was investigated.

RESULTS

In this paper, non-destructive detection for the total number of mold colonies in rice was performed from the angle of spectral analysis. A determination coefficient of 0.9621 for the calibration set and 0.9511 for the prediction set between the spectral data and number of mold colonies were eventually achieved by establishing the best support vector regression (SVR) model, optimized by the Gray Wolf Optimization (GWO) algorithm.

CONCLUSION

Hyperspectral imaging technology combined with the optimal model (GWO-SVR) is feasible for non-destructive detection of the total number of mold colonies in rice, providing a promising tool for the mold detection of other agricultural products. © 2017 Society of Chemical Industry.

Unraveling Metabolic Variation for Blueberry and Chokeberry Cultivars Harvested from Different Geo-Climatic Regions in Korea

Temporal geo-climatic variations are presumably vital determinants of phenotypic traits and quality characteristics of berries manifested through reconfigured metabolomes. We performed an untargeted mass spectrometry (MS)-based metabolomic analysis of blueberry (Vaccinium spp.) and chokeberry (Aronia melanocarpa) sample extracts harvested from different geo-climatic regions in Korea. The multivariate statistical analysis indicated distinct metabolite compositions of berry groups based on different species and regions. The amino acids levels were relatively more abundant in chokeberry than in blueberry, while the sugar contents were comparatively higher in blueberry. However, the metabolite compositions were also dependent on geo-climatic conditions, especially latitude. Notwithstanding the cultivar types, amino acids, and sucrose were relatively more abundant in berries harvested from 35°N and 36°N geo-climatic regions, respectively, characterized by distinct duration of sunshine and rainfall patterns. The present study showed the ability of a metabolomics approach for recapitulating the significance of geo-climatic parameters for quality characterization of commercial berry types.

Combination of the Manifold Dimensionality Reduction Methods with Least Squares Support vector machines for Classifying the Species of Sorghum Seeds

This study was carried out for rapid and noninvasive determination of the class of sorghum species by using the manifold dimensionality reduction (MDR) method and the nonlinear regression method of least squares support vector machines (LS-SVM) combing with the mid-infrared spectroscopy (MIRS) techniques. The methods of Durbin and Run test of augmented partial residual plot (APaRP) were performed to diagnose the nonlinearity of the raw spectral data. The nonlinear MDR methods of isometric feature mapping (ISOMAP), local linear embedding, laplacian eigenmaps and local tangent space alignment, as well as the linear MDR methods of principle component analysis and metric multidimensional scaling were employed to extract the feature variables. The extracted characteristic variables were utilized as the input of LS-SVM and established the relationship between the spectra and the target attributes. The mean average precision (MAP) scores and prediction accuracy were respectively used to evaluate the performance of models. The prediction results showed that the ISOMAP-LS-SVM model obtained the best classification performance, where the MAP scores and prediction accuracy were 0.947 and 92.86%, respectively. It can be concluded that the ISOMAP-LS-SVM model combined with the MIRS technique has the potential of classifying the species of sorghum in a reasonable accuracy.

Detection of early blight and late blight diseases on tomato leaves using hyperspectral imaging

This study investigated the potential of using hyperspectral imaging for detecting different diseases on tomato leaves. One hundred and twenty healthy, one hundred and twenty early blight and seventy late blight diseased leaves were selected to obtain hyperspectral images covering spectral wavelengths from 380 to 1023 nm. An extreme learning machine (ELM) classifier model was established based on full wavelengths. Successive projections algorithm (SPA) was used to identify the most important wavelengths. Based on the five selected wavelengths (442, 508, 573, 696 and 715 nm), an ELM model was re-established. Then, eight texture features (mean, variance, homogeneity, contrast, dissimilarity, entropy, second moment and correlation) based on gray level co-occurrence matrix (GLCM) at the five effective wavelengths were extracted to establish detection models. Among the models which were established based on spectral information, all performed excellently with the overall classification accuracy ranging from 97.1% to 100% in testing sets. Among the eight texture features, dissimilarity, second moment and entropy carried most of the effective information with the classification accuracy of 71.8%, 70.9% and 69.9% in the ELM models. The results demonstrated that hyperspectral imaging has the potential as a non-invasive method to identify early blight and late blight diseases on tomato leaves.

Measurement of non-sugar solids content in Chinese rice wine using near infrared spectroscopy combined with an efficient characteristic variables selection algorithm

The non-sugar solids (NSS) content is one of the most important nutrition indicators of Chinese rice wine. This study proposed a rapid method for the measurement of NSS content in Chinese rice wine using near infrared (NIR) spectroscopy. We also systemically studied the efficient spectral variables selection algorithms that have to go through modeling. A new algorithm of synergy interval partial least square with competitive adaptive reweighted sampling (Si-CARS-PLS) was proposed for modeling. The performance of the final model was back-evaluated using root mean square error of calibration (RMSEC) and correlation coefficient (Rc) in calibration set and similarly tested by mean square error of prediction (RMSEP) and correlation coefficient (Rp) in prediction set. The optimum model by Si-CARS-PLS algorithm was achieved when 7 PLS factors and 18 variables were included, and the results were as follows: Rc=0.95 and RMSEC=1.12 in the calibration set, Rp=0.95 and RMSEP=1.22 in the prediction set. In addition, Si-CARS-PLS algorithm showed its superiority when compared with the commonly used algorithms in multivariate calibration. This work demonstrated that NIR spectroscopy technique combined with a suitable multivariate calibration algorithm has a high potential in rapid measurement of NSS content in Chinese rice wine.

Transcriptome and Proteome Expression Analysis of the Metabolism of Amino Acids by the Fungus Aspergillus oryzae in Fermented Soy Sauce

Amino acids comprise the majority of the flavor compounds in soy sauce. A portion of these amino acids are formed from the biosynthesis and metabolism of the fungus Aspergillus oryzae; however, the metabolic pathways leading to the formation of these amino acids in A. oryzae remain largely unknown. We sequenced the transcriptomes of A. oryzae 100-8 and A. oryzae 3.042 under similar soy sauce fermentation conditions. 2D gel electrophoresis was also used to find some differences in protein expression. We found that many amino acid hydrolases (endopeptidases, aminopeptidases, and X-pro-dipeptidyl aminopeptidase) were expressed at much higher levels (mostly greater than double) in A. oryzae 100-8 than in A. oryzae 3.042. Our results indicated that glutamate dehydrogenase may activate the metabolism of amino acids. We also found that the expression levels of some genes changed simultaneously in the metabolic pathways of tyrosine and leucine and that these conserved genes may modulate the function of the metabolic pathway. Such variation in the metabolic pathways of amino acids is important as it can significantly alter the flavor of fermented soy sauce.

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.