Machine learning and deep learning based on the small FT-MIR dataset for fine-grained sampling site recognition of Boletus tomentipes

Fingerprinting of Boletus bainiugan: FT-NIR spectroscopy combined with machine learning a new workflow for storage period identification

Food authenticity and food safety issues have threatened the prosperity of the entire community. The phenomenon of selling porcini mushrooms as old mixed with new jeopardizes consumer safety. Herein, nucleoside contents and spectra of 831 Boletus bainiugan stored for 0, 1 and 2 years are comprehensively analyzed by high performance liquid chromatography (HPLC) coupled with Fourier transform near infrared (FT-NIR) spectroscopy. Guanosine and adenosine increased with storage time, and uridine has a decreasing trend. Multi-conventional machine learning and deep learning models are employed to identify the storage time of Boletus bainiugan, in which convolutional neural network (CNN) and back propagation neural network (BPNN) models have superior identification performance for distinct storage periods. The Data-driven soft independent modelling of class analogy (DD-SIMCA) model can completely differentiate between new and old samples, and partial least squares regression (PLSR) can accurately predict the three nucleoside compounds with an optimal R2 of 0.918 and an excellent residual predictive deviation (RPD) value of 3.492. This study provides a low-cost and user-friendly solution for the market to determine, in real time, storage period of Boletus bainiugan in the supply chain.

FT-NIR Spectra of Different Dimensions Combined with Machine Learning and Image Recognition for Origin Identification: An Example of Panax notoginseng

Panax notoginseng (P. notoginseng) is a traditional medicinal plant with high medicinal and economic values. The authenticity of P. notoginseng often determines its quality, and the quality of geographical indication (GI)-producing areas is usually superior to that of other producing areas, which are exploited by unscrupulous traders and affect the market order. The aim of this study was to characterize and identify the geographic origin of P. notoginseng using Fourier transform near-infrared (FT-NIR) spectroscopy, with rapid detection combined with multivariate analysis. The use of principal component analysis and correlation spectral analysis enabled the initial differential characterization and identification of P. notoginseng from different production areas. Then, random forest (RF) and support vector machine (SVM) models were established, and the results show that the results showed that the second-order derivative preprocessing and successive projection algorithm feature extraction achieved 100% classification correctness and the model training time is the shortest. Further constructing the image recognition model, synchronous two-dimensional correlation spectroscopy (2DCOS) image combined with residual convolutional neural network achieved accurate classification (accuracy of 100%) and did not require complex preprocessing and artificial feature extraction process, to maximize the avoidance of errors caused by human factors. The recognition results of the externally validated set showed that the image recognition method has a strong generalization ability and has a high potential for application in the identification of P. notoginseng production areas.

Geographic traceability of Gastrodia elata Blum based on combination of NIRS and Chemometrics

The content of the active ingredient in G. elata Bl. is affected by the soil and climate of different regions, so geographical traceability is essential to ensure its quality, commercial value. This study used a combination of NIRS and various chemometric methods to establish an effective geotraceability method for G. elata Bl.. Firstly, a traditional machine learning model was built based on the SF dataset NIRS, and a ResNet model was built based on NIRS generated 2DCOS images and 3DCOS images. Secondly, the model performance was validated using the ZT dataset. The results show that the 3DCOS-ResNet model performs the best with 100.00 % and 95.45 % test set and EV accuracy, respectively. This study provides a theoretical basis for regulators to quickly ensure the authenticity of G. elata Bl. sources. However, more data and in-depth studies are needed in the future to validate and improve the applicability of the model.

Feasibility study on discrimination of Polygonatum kingianum origins by NIR and MIR spectra data

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.

Analysis of Chemical Changes during Maturation of Amomum tsao-ko Based on GC-MS, FT-NIR, and FT-MIR

Amomum tsao-ko Crevost et Lemaire (A. tsao-ko) is widely grown for its high nutritional and economic value. However, the lack of a scientific harvesting and quality control system has resulted in an uneven product quality. The present study was based on A. tsao-ko from four maturity stages from the same growing area, and its chemical trends and quality were evaluated using a combination of agronomic trait analysis, spectroscopy, chromatography, chemometrics, and network pharmacology. The results showed that A. tsao-ko was phenotypically dominant in October. Spectroscopy showed that the absorbance intensity at different maturity stages showed a trend of October > September > August > July. Further chemical differences between A. tsao-ko at different stages of maturity were found by chromatography to originate mainly from alcohol, aromatic, acids, esters, hydrocarbons, ketone, heterocyclic, and aldehydes. The network pharmacology results showed that the active ingredient for the treatment of obesity was present in A. tsao-ko and had high levels in A. tsao-ko in September and October. The results of this study provide a new idea for the comprehensive evaluation of A. tsao-ko and a theoretical basis for the harvesting and resource utilization of A. tsao-ko.

Visible detection of chilled beef freshness using a paper-based colourimetric sensor array combining with deep learning algorithms

This study developed an innovative approach that combines a colourimetric sensor array (CSA) composed of twelve pH-response dyes with advanced algorithms, aiming to detect amine gases and assess the freshness of chilled beef. With the assistance of multivariate statistical analysis, the sensor array can effectively distinguish five amine gases and enable rapid quantification of trimethylamine vapour with a limit of detection (LOD) of 8.02 ppb and visually monitor the fresh levels of chilled beef. Moreover, the utilization of deep learning models (ResNet34, VGG16, and GoogleNet) for chilled beef freshness evaluation achieved an overall accuracy of 98.0 %. Furthermore, t-distributed stochastic neighbour embedding (t-SNE) visualized the feature extraction process and provided explanations to understand the classification process of deep learning. The results demonstrated that applying deep learning techniques in the process of pattern recognition of CSA can help in realizing the rapid, robust, and accurate assessment of chilled beef freshness.

A rapid method for identification of Lanxangia tsaoko origin and fruit shape: FT-NIR combined with chemometrics and image recognition

Lanxangia tsaoko's accurate classifications of different origins and fruit shapes are significant for research in L. tsaoko difference between origin and species as well as for variety breeding, cultivation, and market management. In this work, Fourier transform-near infrared (FT-NIR) spectroscopy was transformed into two-dimensional and three-dimensional correlation spectroscopies to further investigate the spectral characteristics of L. tsaoko. Before building the classification model, the raw FT-NIR spectra were preprocessed using multiplicative scatter correction and second derivative, whereas principal component analysis, successive projections algorithm, and competitive adaptive reweighted sampling were used for spectral feature variable extraction. Then combined with partial least squares-discriminant analysis (PLS-DA), support vector machine (SVM), decision tree, and residual network (ResNet) models for origin and fruit shape discriminated in L. tsaoko. The PLS-DA and SVM models can achieve 100% classification in origin classification, but what is difficult to avoid is the complex process of model optimization. The ResNet image recognition model classifies the origin and shape of L. tsaoko with 100% accuracy, and without the need for complex preprocessing and feature extraction, the model facilitates the realization of fast, accurate, and efficient identification.

Building deep learning and traditional chemometric models based on Fourier transform mid-infrared spectroscopy: Identification of wild and cultivated Gastrodia elata

To identify wild and cultivated Gastrodia elata quickly and accurately, this study is the first to apply three-dimensional correlation spectroscopy (3DCOS) images combined with deep learning models to the identification of G. elata. The spectral data used for model building do not require any preprocessing, and the spectral data are converted into three-dimensional spectral images for model building. For large sample studies, the time cost is minimized. In addition, a partial least squares discriminant analysis (PLS-DA) model and a support vector machine (SVM) model are built for comparison with the deep learning model. The overall effect of the deep learning model is significantly better than that of the traditional chemometric models. The results show that the model achieves 100% accuracy in the training set, test set, and external validation set of the model built after 46 iterations without preprocessing the original spectral data. The sensitivity, specificity, and the effectiveness of the model are all 1. The results concluded that the deep learning model is more effective than the traditional chemometric model and has greater potential for application in the identification of wild and cultivated G. elata.

Rapid Prediction of Adulteration Content in Atractylodis rhizoma Based on Data and Image Features Fusions from Near-Infrared Spectroscopy and Hyperspectral Imaging Techniques

Atractylodis rhizoma (AR) is an herb and food source with great economic, medicinal, and ecological value. Atractylodes chinensis (DC.) Koidz. (AC) and Atractylodes lancea (Thunb.) DC. (AL) are its two botanical sources. The commercial fraud of AR adulterated with Atractylodes japonica Koidz. ex Kitam (AJ) frequently occurs in pursuit of higher profit. To quickly determine the content of adulteration in AC and AL powder, two spectroscopic techniques, near-infrared spectroscopy (NIRS) and hyperspectral imaging (HSI), were introduced. The partial least squares regression (PLSR) algorithm was selected for predictive modeling of AR adulteration levels. Preprocessing and feature variable extraction were used to optimize the prediction model. Then data and image feature fusions were developed to obtain the best predictive model. The results showed that if only single-spectral techniques were considered, NIRS was more suitable for both tasks than HSI techniques. In addition, by comparing the models built after the data fusion of NIRS and HSI with those built by the single spectrum, we found that the mid-level fusion strategy obtained the best models in both tasks. On this basis, combined with the color-texture features, the prediction ability of the model was further optimized. Among them, for the adulteration level prediction task of AC, the best strategy was combining MLF data (at CARS level) and color-texture features (C-TF), at which time the R2T, RMSET, R2P, and RMSEP were 99.85%, 1.25%, 98.61%, and 5.06%, respectively. For AL, the best approach was combining MLF data (at SPA level) and C-TF, with the highest R2T (99.92%) and R2P (99.00%), as well as the lowest RMSET (1.16%) and RMSEP (2.16%). Therefore, combining data and image features from NIRS and HSI is a potential strategy to predict the adulteration content quickly, non-destructively, and accurately.