[Origin identification of Polygonatum cyrtonema based on hyperspectral data].

In this study, visual-near infrared(VNIR), short-wave infrared(SWIR), and VNIR + SWIR fusion hyperspectral data of Polygonatum cyrtonema from different geographical origins were collected and preprocessed by first derivative(FD), second derivative(SD), Savitzky-Golay smoothing(S-G), standard normalized variate(SNV), multiplicative scatter correction(MSC), FD+S-G, and SD+S-G. Three algorithms, namely random forest(RF), linear support vector classification(LinearSVC), and partial least squares discriminant analysis(PLS-DA), were used to establish the identification models of P. cyrtonema origin from three spatial scales, i.e., province, county, and township, respectively. Successive projection algorithm(SPA) and competitive adaptive reweighted sampling(CARS) were used to screen the characteristic bands, and the P. cyrtonema origin identification models were established according to the selected characteristic bands. The results showed that(1)after FD preprocessing of VNIR+SWIR fusion hyperspectral data, the accuracy of recognition models established using LinearSVC was the highest, reaching 99.97% and 99.82% in the province origin identification model, 100.00% and 99.46% in the county origin identification model, and 99.62% and 98.39% in the township origin identification model. The accuracy of province, county, and township origin identification models reached more than 98.00%.(2)Among the 26 characteristic bands selected by CARS, after FD pretreatment, the accuracy of origin identification models of different spatial scales was the highest using LinearSVC, reaching 98.59% and 97.05% in the province origin identification model, 97.79% and 94.75% in the county origin identification model, and 90.13% and 87.95% in the township origin identification model. The accuracy of identification models of different spatial scales established by 26 characteristic bands reached more than 87.00%. The results show that hyperspectral imaging technology can realize accurate identification of P. cyrtonema origin from different spatial scales.

The combination of HSI and NMR techniques with deep learning for identification of geographical origin and GI markers of Lycium barbarum L.

Lycium barbarum L. (L. barbarum) is renowned worldwide for its nutritional and medicinal benefits. Rapid and accurate identification of L.barbarum's geographic origin is essential because its nutritional content, medicinal efficacy, and market price significantly vary by region. This study proposes an innovative method combining hyperspectral imaging (HSI), nuclear magnetic resonance (NMR), and an improved ResNet-34 deep learning model to accurately identify the geographical origin and geographical indication (GI) markers of L.barbarum. The deep learning model achieved a 95.63% accuracy, surpassed traditional methods by 6.26% and reduced runtime by 29.9% through SHapley Additive exPlanations (SHAP)-based feature selection. Pearson correlation analysis between GI markers and HSI characteristic wavelengths enhanced the interpretability of HSI data and further reduced runtime by 33.99%. This work lays the foundation for portable multispectral devices, offering a rapid, accurate, and cost-effective solution for quality assurance and market regulation of L.barbarum products.

A weighted twin support vector machine as a potential discriminant analysis tool and evaluation of its performance for near-infrared spectroscopic discrimination of the geographical origins of diverse agricultural products.

A weighted twin support vector machine (wTWSVM) was proposed as a potential discriminant analysis tool and its utility was evaluated for near-infrared (NIR) spectroscopic identification of the geographical origins of 12 different agricultural products including black soybean and garlic. In the wTWSVM, weights were applied on each variable in the sample spectra to highlight detailed NIR spectral features and the optimal weights to minimize the discrimination error were iteratively searched. Then, the weighted spectra were employed to determine the samples' geographical origins using a TWSVM adopting two non-parallel hyperplanes for the discrimination. For the performance evaluation, SVM, TWSVM, and wTWSVM were separately used for the two-group discriminations and their accuracies were comparatively analyzed. When the SVM and TWSVM accuracies were compared, the improvements by using the TWSVM were significant (95% confidence level) for 10 out of the 12 products. Moreover, the accuracy improvements with the wTWSVM against SVM were significant for all the 12 products. In the case of the TWSVM-wTWSVM accuracy comparison, the improvements by the wTWSVM were also significant for 10 products, thereby demonstrating superior discrimination performance of wTWSVM. Based on the overall results, the wTWSVM could be a potential chemometric tool for discriminant analysis and expandable to other areas such as spectroscopy-based biomedical disease diagnosis and forensic analysis.

Alternative selection of Raman or LIBS spectral information in hierarchical discrimination of raw sapphires according to geographical origin for accuracy improvement.

Both Raman spectroscopy and laser-induced breakdown spectroscopy (LIBS) were cooperatively utilized to improve the geographical origin identification of raw sapphires from five different countries (Mozambique, Laos, Australia, Rwanda, and Congo). A hierarchical support vector machine (H-SVM) was used for multi-group identification. Initially, accuracy improved to 87.5% using merged Raman-LIBS data compared to those of using only Raman (82.8%) or LIBS (71.9%) information. This improvement was attributed to incorporating two complimentary spectroscopic datasets that provided molecular vibrational and elemental information. However, merging both spectroscopic datasets is may not be the best choice since it would make distinct and sample-descriptive information in one spectroscopic dataset less recognized for analysis by the inclusion of less characteristic information in another spectroscopic dataset; using only Raman or LIBS information at each discrimination stage would be more effective. When Raman information was utilized during the first three discrimination stages followed by LIBS data during the fourth (last) discrimination stage in H-SVM, the accuracy improved to 90.6%. The proper selection of molecular vibrational or elemental sample information at different discrimination stages is attributed to this improvement.

Application of Laser-Induced Breakdown Spectroscopy Coupled With Spectral Matrix and Convolutional Neural Network for Identifying Geographical Origins of Gentiana rigescens Franch.

Accurate geographical origin identification is of great significance to ensure the quality of traditional Chinese medicine (TCM). Laser-induced breakdown spectroscopy (LIBS) was applied to achieve the fast geographical origin identification of wild Gentiana rigescens Franch (G. rigescens Franch). However, LIBS spectra with too many variables could increase the training time of models and reduce the discrimination accuracy. In order to solve the problems, we proposed two methods. One was reducing the number of variables through two consecutive variable selections. The other was transforming the spectrum into spectral matrix by spectrum segmentation and recombination. Combined with convolutional neural network (CNN), both methods could improve the accuracy of discrimination. For the underground parts of G. rigescens Franch, the optimal accuracy in the prediction set for the two methods was 92.19 and 94.01%, respectively. For the aerial parts, the two corresponding accuracies were the same with the value of 94.01%. Saliency map was used to explain the rationality of discriminant analysis by CNN combined with spectral matrix. The first method could provide some support for LIBS portable instrument development. The second method could offer some reference for the discriminant analysis of LIBS spectra with too many variables by the end-to-end learning of CNN. The present results demonstrated that LIBS combined with CNN was an effective tool to quickly identify the geographical origin of G. rigescens Franch.

Detection of Changes in Total Antioxidant Capacity, the Content of Polyphenols, Caffeine, and Heavy Metals of Teas in Relation to Their Origin and Fermentation.

Tea (Camellia sinensis) is widely sought for beverages worldwide. Heavy metals are often the main aims of the survey of teas, given that the use of agricultural fertilization is very frequent. Some of these may affect the content of bioactive compounds. Therefore, in this study, we analyzed fermented and non-fermented teas of a single plant origin from Japan, Nepal, Korea, and China, and described mutual correlations and changes in the total antioxidant capacity (TAC), and the content of polyphenols (TPC), caffeine, and heavy metals in tea leaves, in relation to the origin and fermentation process. Using UV-VIS spectrophotometry and HPLC-DAD, we determined variations in bioactive compounds' content in relation to the fermentation process and origin and observed negative correlations between TAC and TPC. Heavy metal content followed this order: Mn > Fe > Cu > Zn > Ni > Cr > Pb > Co > Cd > Hg. Given the homogenous content of these elements in relation to fermentation, this paper also describes the possibility of using heavy metals as determinants of geographical origin. Linear Discriminant Analysis showed an accuracy of 75% for Ni, Co, Cd, Hg, and Pb, explaining 95.19% of the variability between geographical regions.

Exploring two-trace two-dimensional (2T2D) correlation spectroscopy as an effective approach to improve accuracy of discriminant analysis by highlighting asynchronous features in two separate spectra of a sample.

This study aims to demonstrate two-trace two-dimensional (2T2D) correlation spectroscopy as an effective tool for improving the accuracy of discriminant analysis. Because 2T2D correlation analysis allows sensitive capturing of asynchronous spectral behaviors between two compared spectra of a sample, the subsequent asynchronous correlation features are expected to reveal more sample-to-sample characteristics and discriminants than the original spectral feature. Initially, near-infrared (NIR) spectroscopic authentication of pure olive oil was performed using the spectra collected at 20 °C and 41 °C. When the 2T2D slice spectra of the samples were used for the discriminant analysis, the authentication accuracy reached to 100%, while became degraded in the cases of using the spectra collected either at 20 °C or 41 °C. Furthermore, a simple strategy of utilizing the average spectrum of one sample group as the reference spectrum in the 2T2D correlation analysis was proposed for two-group discrimination and evaluated for the NIR identification of the geographical origins of agricultural products (milk vetch root (MVR) and perilla seed samples). Because the average spectrum of one sample group was used for comparison, dissimilar constituent compositions of the samples in another group were better observed, thereby improving the accuracy of discrimination of the geographical origins of the samples in both cases. The overall results demonstrated that 2T2D correlation analysis is effective for highlighting the minute asynchronous spectral features of a sample and can be expanded for diverse vibrational spectroscopy-based discriminant analyses.

Evaluation of an autoencoder as a feature extraction tool for near-infrared spectroscopic discriminant analysis.

The utility of an autoencoder (AE) as a feature extraction tool for near-infrared (NIR) spectroscopy-based discrimination analysis has been explored and the discrimination of the geographic origins of 8 different agricultural products has been performed as the case study. The sample spectral features were broad and insufficient for component distinction due to considerable overlap of individual bands, so AE enabling of extracting the sample-descriptive features in the spectra would help to improve discrimination accuracy. For comparison, four different inputs of AE-extracted features, raw NIR spectra, principal component (PC) scores, and features extracted using locally linear embedding were employed for sample discrimination using support vector machine. The use of AE-extracted feature improved the accuracy in the discrimination of samples in all 8 products. The improvement was more substantial when the sample spectral features were indistinct. It demonstrates that AE is expandable for vibrational spectroscopic discriminant analysis of other samples with complex composition.