Search

Most existing studies have focused on identifying the origin of species with protected geographical indications while neglecting to determine the proximate geographical origin of different species. In this study, we investigated the feasibility of using near‐ and mid‐infrared spectroscopy to identify the origin of 156 Polygonatum kingianum samples from six regions in Yunnan, China. In this work, spectral images of different modes reveal more information about the P. kingianum. Comparing the performance of traditional machine learning models according to single spectrum and data fusion, the middle‐level data fusion‐principal component model has the best performance, and its sensitivity, specificity, and accuracy are all 1, and the model has the least number of variables. The residual convolutional neural network (ResNet) model constructed in the 1050–850 cm−1 band confirms that fewer variables are beneficial in improving the accuracy of the model. In conclusion, this study verifies the feasibility of the proposed strategy and establishes a practical model to determine the source of P. kingianum. [ABSTRACT FROM AUTHOR]

Genus Paris has numerous bioactive constituents such as steroid saponins, flavonoids, and polysaccharose which are responsible for antitumor, hemostatic, and anthelmintic, etc. In this study, ultrahigh performance liquid chromatography coupled to time-of-flight mass spectrometer (UHPLC-QTOF-MS) and Fourier transform infrared (FT-IR) spectroscopy in combination with multivariable analysis were employed to discriminate the different species of Paris including P. polyphylla var. yunnanensis (PPY), P. polyphylla var. alba, P. mairei (PM), P. vietnamensis, and P. polyphylla var. stenophylla. Partial least square discriminate analysis based on UHPLC, FT-IR, and midlevel data fusion was used to distinguish 43 batches of Paris. Chemical constituents of different species Paris were determined by UHPLC-QTOF-MS. The result indicated that midlevel data fusion had a good performance in the classification compared to a single analytical technology. A total of 47 compounds were identified in different species Paris. The similar results indicated that PM could be treated as a proposal substitute of PPY. [ABSTRACT FROM AUTHOR]

Dendrobium officinale Kimura & Migo (D. officinale) is a valuable medicinal and food plant, and accurate certification of its origin is a prerequisite to protect consumer interests and maintain the market. In order to realize the fast and effective authentication of D. officinale origin, a discrimination model based on attenuated total reflection-Fourier transform infrared (ATR-FTIR) and Fourier transform near-infrared (FT-NIR) was constructed and combined with individual spectra and data fusion strategies. The results showed that the PLS-DA and SVM models built by the fusion of FT-NIR and ATR-FTIR data processed in second-order derivatives all reach 100% in terms of test set and accuracy, respectively. The residual convolutional neural network (ResNet) model based on Two-dimensional correlation spectroscopy(2DCOS) constructed using FT-NIR spectra and spectral fusion of raw data achieves 100% accuracy on the training set, test set, and external test set. Due to the generalization ability of the ResNet model and the simplicity and efficiency of the subsequent validation, it is a powerful, non-destructive, fast, and feasible preferred tool for D. officinale geographic origin classification and brand protection. This work is expected to be a potential methodology for origin identification analysis and quality monitoring in the food and pharmaceutical industries. [Display omitted] • Primary data fusion strategies based on FT-NIR and ATR-FTIR improve the model performance. • The 2DCOS-ResNet model is the preferred choice for the identification of the geographical origin of D. officinale. • Machine learning combined with infrared spectroscopy provide a new approach for D. officinale origin traceability. [ABSTRACT FROM AUTHOR]

Poria originated from the dried sclerotium of Macrohyporia cocos is an edible traditional Chinese medicine with high economic value. Due to the significant difference in quality between wild and cultivated M. cocos, this study aimed to trace the origin of the fungus from the perspectives of wild and cultivation. In addition, there were quite limited studies about data fusion, a potential strategy, employed and discussed in the geographical traceability of M. cocos. Therefore, we traced the origin of M. cocos from the perspectives of wild and cultivation using multiple data fusion approaches. Supervised pattern recognition techniques, like partial least squares discriminant analysis (PLS-DA) and random forest, were employed in this study using. Five types of data fusion involving low-, mid-, and high-level data fusion strategies were performed. Two feature extraction approaches including the selecting variables by a random forest-based method—Boruta algorithm and producing principal components by the dimension reduction technique of principal component analysis—were considered in data fusion. The results indicate the following: (1) The difference between wild and cultivated samples did exist in terms of the content analysis of vital chemical components and fingerprint analysis. (2) Wild samples need data fusion to realize the origin traceability, and the accuracy of the validation set was 95.24%. (3) Boruta outperformed principal component analysis (PCA) in feature extraction. (4) The mid-level Boruta PLS-DA model took full advantage of information synergy and showed the best performance. This study proved that both geographical traceability and optimal identification methods of cultivated and wild samples were different, and data fusion was a potential technique in the geographical identification. [ABSTRACT FROM AUTHOR]

The plateau specialty agricultural products, wild porcini mushrooms, have great value both as a superb cuisine and as a potential medication. Due to quality different between species added with the fraud behavior in sales process, make poor quality or poisonous sample inflow into the market, which pose a health risk for consumers, but also disrupted the mushroom market. Traditional analysis way is time‐consuming and laborious. Therefore, the aim of this study is to develop a way using fourier transform mid‐infrared (FT‐MIR) spectrometry and data fusion strategies for the fast and accurate species discrimination and predict amount of total polyphenol in four porcini mushrooms. The t‐distributed stochastic neighbor embedding based on mid‐level data fusion showed two species of Boletus edulis and B. umbriniporus have been identified. The order of correct rate of PLS‐DA models was mid‐level data fusionq (100%) > mid‐level data fusione (97.06%) = mid‐level data fusionv (97.06%) = stipes (97.06%) > low‐level data fusion (94.12%) > caps (91.18%). The order of correct rate of grid‐search support vector machine models was low‐level data fusion (100%) > caps (94.12%) > stipes (91.18%), and the order of particle swarm optimization support vector machine was low‐level data fusion (100%) > caps (97.06%) > stipes (88.24%). The mid‐level data fusionq and low‐level data fusion had best discrimination accuracy (100%) allowing each mushroom classed into its real species, which could be used for accurate discrimination of samples. B. edulis mushrooms had highest total polyphenol, with 14.76 mg/g dw and 17.33 in caps and stipes mg/g dw, respectively. The phenols were easier to accumulate in the caps in Leccinum rugosiceps (1.03) and B. tomentipes (1.19), and the opposite phenomenon is observed in B. edulis (0.85) and B. umbriniporus (0.95). The correlation coefficient and residual predictive deviation of best prediction model were 86.76% and 2.40%, respectively, indicating that that there is good relevance between FT‐MIR and total polyphenol content, which could be used to predict roughly polyphenols content in mushrooms. [ABSTRACT FROM AUTHOR]

Gastrodia elata Blume (G. elata Bl.), with its excellent nutritional and medicinal value from Zhaotong, has been protected by geographical indication (GI). Accurate certification of its origin is a prerequisite to safeguard consumer interests and maintain the market. Four different regions and three varieties of G. elata Bl. from Zhaotong were used in this study (n = 262). Tri-step infrared spectroscopy was used for ATR-FTIR spectral analysis to filter out fingerprint regions for data fusion with FT-NIR spectra, after which conventional discriminant models (PLS-DA and GS-SVM) were built. The second derivative (SD), multiple scattering correction (MSC), and Savitzky-Golay (SG) preprocessing were also performed on the spectra, and it was found that the preprocessing improved the performance of the PLS-DA model. The optimal model results in GS-SVM, based on mid-level data fusion of principal components (PCs) and latent variables (LVs), with sensitivity, specificity, accuracy, and Matthews correlation coefficient (MCC) of 1 for the test set. Furthermore, the residual convolutional neural network (ResNet) models were built, based on FT-NIR full spectra, band 3600−2700 cm−1 (MFA) and band 1750−500 cm−1 (MFB). Their accuracy in both train and test sets exceeds 97%, and the loss function curve is close to 0, which indicates that these three bands can be used as a fingerprint area to verify the GI of Zhaotong G. elata Bl. This study provides a fast, non-invasive method for the authentication of food or medicinal plant GI. [Display omitted] • Vibrational spectroscopy to determine the feasibility of G. elata Bl. origin. • The utility of Tri-step infrared spectroscopy analyzes spectral fingerprint regions. • Mid-level data fusion excels in G. elata Bl. geographical indications determination. • Detecting spectral fingerprint region usability using the ResNet modal. [ABSTRACT FROM AUTHOR]

AbstractPanax notoginseng (Burk.) F.H. Chen (P. notoginseng), a precious medicinal herb, provides both considerable values. There is confusion in the market regarding the geographical origins of P. notoginseng. It is of paramount importance to authenticate geographical origins of P. notoginseng, which will facilitate the rational utilization of resources and sustainable development. Principal component analysis (PCA) and partial least squares discriminant analysis (PLS-DA) were employed to investigate the influence of the tissue and data fusion strategy for the authentication of P. notoginseng origins. The PLS-DA model employing the main root spectra demonstrated great potential for authenticating P. notoginseng origin. The PLS-DA training and test sets based on feature-level fusion (VIP) spectral data were 100% accurate, indicating excellent potential in authenticating P. notoginseng. The data fusion strategy improved the authentication. The article presents a reliable and efficacious novel methodology for authenticating P. notoginseng origins and a scientific foundation for its quality control. [ABSTRACT FROM AUTHOR]

Geographical traceability is important to consumer protection and quality control of edible mushrooms. In this work, Fourier transform infrared (FT-IR) spectroscopy, ultraviolet (UV) spectroscopy, and inductively coupled plasma-atomic emission spectrometry were used for traceability of 312 mushroom samples from eight different geographical origins in combination with multivariate statistical analysis. Initially, FT-IR, UV spectra, and 14 elements of 312 samples obtained from 8 geographical origins were analyzed, respectively. Meanwhile, the principal components of three techniques were extracted by principal components analysis for data fusion. Finally, classification models were established in the basis of UV, FT-IR, elements, and fusion datasets combined with support vector machine (SVM). Compared with individual technology, data fusion of multi-technique can obviously promote the classification performance in SVM models for geographical origins traceability. Especially, the accuracy of prediction in SVM model by data fusion of three instruments was 99.04%, which was higher than single technique and data fusion of two spectroscopies techniques. This result indicated that data fusion strategy combined with SVM can provide high synergic effect for geographical origins traceability of Boletaceae mushrooms. The more information is fused, the better performance of the model is. This method may be applied for quality control and evaluation of analogous food. [ABSTRACT FROM AUTHOR]

Abstract: BACKGROUND: Boletaceae mushrooms are wild‐grown edible mushrooms that have high nutrition, delicious flavor and large economic value distributing in Yunnan Province, China. Traceability is important for the authentication and quality assessment of Boletaceae mushrooms. In this study, UV–visible and Fourier transform infrared (FTIR) spectroscopies were applied for traceability of 247 Boletaceae mushroom samples in combination with chemometrics. RESULTS: Compared with a single spectroscopy technique, data fusion strategy can obviously improve the classification performance in partial least square discriminant analysis (PLS‐DA) and grid‐search support vector machine (GS‐SVM) models, for both species and geographical origin traceability. In addition, PLS‐DA and GS‐SVM models can provide 100.00% accuracy for species traceability and have reliable evaluation parameters. For geographical origin traceability, the accuracy of prediction in the PLS‐DA model by data fusion was just 64.63%, but the GS‐SVM model based on data fusion was 100.00%. CONCLUSION: The results demonstrated that the data fusion strategy of UV–visible and FTIR combined with GS‐SVM could provide a higher synergic effect for traceability of Boletaceae mushrooms and have a good generalization ability for the comprehensive quality control and evaluation of similar foods. © 2017 Society of Chemical Industry [ABSTRACT FROM AUTHOR]

Different varieties of Gastrodia elata Blume (G. elata Bl.) have different qualities and different contents of active ingredients, such as polysaccharide and gastrodin, and it is generally believed that the higher the active ingredients, the better the quality of G. elata Bl. and the stronger the medicinal effects. Therefore, effective identification of G. elata Bl. species is crucial and has important theoretical and practical significance. In this study, first unsupervised PCA and t-SNE are established for data visualisation, follow by traditional machine learning (PLS-DA, OPLS-DA and SVM) models and deep learning (ResNet) models were established based on the fourier transform infrared (FTIR) and near infrared (NIR) spectra data of three G. elata Bl. species. The results show that PLS-DA, OPLS-DA and SVM models require complex preprocessing of spectral data to build stable and reliable models. Compared with traditional machine learning models, ResNet models do not require complex spectral preprocessing, and the training and test sets of ResNet models built based on raw NIR and low-level data fusion (FTIR + NIR) spectra reach 100 % accuracy, the external validation set based on low-level data fusion reaches 100 % accuracy, and the external validation set based on NIR has only one sample classification error and no overfitting. [Display omitted] • Identification of different G. elata Bl. species using FTIR and NIR. • Research on pre-processing methods for spectral data. • Comparison between traditional machine learning models and deep learning models. • A ResNet model based on NIR spectroscopy enables rapid and accurate identification of G. elata Bl. species. [ABSTRACT FROM AUTHOR]

Mushrooms, as a delicacy on the table, provide people with high nutritional value. Mushroom quality is affected by factors such as geographic environment, storage time, etc. Emerging nondestructive techniques have the advantages of nondestructiveness, efficiency and simplicity, which provide a wide range of application prospects for quality assessment of edible mushrooms. This paper summarizes recent advances in the application of vibrational spectroscopy, ultraviolet-visible spectroscopy, and electronic sensing techniques to the identification of edible mushroom source, species identification, storage time identification, and content prediction. It also provides an outlook on new areas and technologies for quality assessment of edible mushrooms. The results of the study showed that non-destructive techniques (NDT) combined with chemometrics are satisfactory for quality assessment of edible mushrooms. The spectral fusion technique was widely found to be more capable of encompassing complex chemical information for research purposes in its application. Meanwhile, it was found during the evaluation process that the grade assessment and finished packaging of mushrooms had not been quality assessed. Whether emerging nondestructive techniques and terahertz spectroscopy can be further applied in this area needs to be further investigated. Therefore, new techniques and methods could be developed for future exploration. [Display omitted] • Edible mushrooms are multi-nutrient functional foods. • The advantages of non-destructive techniques over traditional detection methods. • Recent applications of non-destructive techniques in edible mushrooms are listed. • Data fusion accommodates more information on edible mushrooms. [ABSTRACT FROM AUTHOR]

[Display omitted] • Non-destructive analysis (green, fast, accurate) is the trend of authentication. • Quality authentication methods based on multi-source information are superior. • Each step in the quality authentication process is essential and challenging. • The different quality attributes of herbs and spices can be well described. The growing concerns about the quality and safety of herbs and spices among consumers have increased the demand for technical testing. Recently, non-destructive analysis techniques have been widely studied and applied. Generally, a single technology has certain limitations, which are not enough to fully describe the characteristics of complex products (dynamic or complex structure). Combining non-destructive analysis technology (multi-source information) can overcome the above problems. The present review focused on applying multi-source and non-destructive information on herbs and spices quality authentication, including vibration spectroscopy and electronic sensor technologies. Then summarized and analyzed the authentication process for issues such as adulteration, contents prediction, geographical traceability, process and products analysis, and identification variety. Additionally, we presented trends in quality authentication, discussed the challenges and prospects, and made recommendations. This investigation provided clear evidence for the superiority of the quality authentication methods for herbs and spices based on multi-source and non-destructive information. [ABSTRACT FROM AUTHOR]

[Display omitted] • NIR and UV–Vis spectra of five different geographical regions were collected. • Variable dimension reduction and variables selection method were applied to extract feature information. • SO-PLS as well as SO-CovSel showed the better concise performance than traditional mid-level data fusion. Due to the world-wide concern relating to herb quality and safety, there is a momentum to authenticate the geographical origin of herb with multi-platform techniques. This study attempted to assess multi-platform information as a practical strategy for the geographical traceability of the fruits of Amomum tsao-ko. To this aim, one hundred and eighty dried fruits of A. tsao-ko from five geographical regions were analyzed by near infrared (NIR) and ultraviolet visible (UV–Vis) spectroscopy. On this basis, two variable dimension reduction strategies, including principal component analysis (PCA) and sequential and orthogonalized partial-least squares (SO-PLS), and two variables selection strategies, including variable importance in projection (VIP) and sequential and orthogonalized covariance selection (SO-CovSel), were performed to extract the feature information in the two blocks. Partial least squares discriminant analysis (PLS-DA) classification algorithm combined with fused matrices was used to identify the geographical origins. The results of PLS-DA models indicated that SO-PLS and SO-CovSel, taking advantage of the sequential modeling coupled to orthogonalization, could not only identify the common information presented in the two blocks but also provide more concise methods without any loss of classification ability, which could be employed in authenticating the geographical regions of the fruits of A. tsao-ko , effectively. [ABSTRACT FROM AUTHOR]

Wild porcini mushrooms have high nutritional value and are a kind of medicinal food. It is rich in protein and micronutrients needed by the human body, which is popular among consumers. In this paper, we take the problem of origin traceability of Boletus bainiugan as an example and use multiple data processing methods (preprocessing, feature extraction, and data fusion strategies) to establish partial least squares discriminant analysis and support vector machine models. In addition, a deep learning model (3DCOS-ResNet: three-dimensional correlation spectra combined with residual convolutional neural network model) is built to compare with the above two models. It was found that 3DCOS-ResNet was the best model to solve the Boletus baniugan origin traceability problem. Compared to the chemometrics model, it does not require complex processing of the data. The ideal identification effect can be achieved by directly utilizing the raw data, and it saves a lot of time and cost. [Display omitted] • Various data processing methods were used for model building. • SVM, PLS-DA and 3DCOS-ResNet models were built for comparison. • 3DCOS-ResNet was established under the data fusion strategy for the first time. [ABSTRACT FROM AUTHOR]

Traditional Chinese medicine Panax notoginseng is a valuable geo-authentic herbal material. The difference of growth environment in different producing areas has significant influence on the quality of traditional Chinese medicine, and origin identification is an important part of the quality assessment of P. notoginseng. In this study, Fourier transform mid-infrared (FT-MIR) and near infrared (NIR) sensor technologies combined with single spectra analysis and multi-sensor information fusion strategy (low-, mid- and high-level) for the origin identification of 210 P. notoginseng samples from five cities in Yunnan Province, China. FT-MIR spectra were considered to play a greater role in data analysis than NIR spectra. Random forest (RF) was used to establish classification models. The result of the random forest Boruta (RF-Bo) model and the random forest variable selection (RF-Vs) model based on high-level multi-sensor information fusion strategy was satisfactory. In addition, the RF-Bo model based on high-level multi-sensor information fusion strategy was faster and simpler in data analysis and the accuracy was 95.6%. Image 1 • Two classification models were established by random forest. • The classification ability of the three-level fusion strategy was compared. • The RF-Bo model was faster and simpler in the actual analysis process. • Important variables in FT-MIR and NIR spectra datasets were compared. [ABSTRACT FROM AUTHOR]