Application of terahertz spectroscopy imaging for discrimination of transgenic rice seeds with chemometrics

Research on terahertz image analysis of thin-shell seeds based on semantic segmentation

Assessing crop seed phenotypic traits is essential for breeding innovations and germplasm enhancement. However, the tough outer layers of thin-shelled seeds present significant challenges for traditional methods aimed at the rapid assessment of their internal structures and quality attributes. This study explores the potential of combining terahertz (THz) time-domain spectroscopy and imaging with semantic segmentation models for the rapid and non-destructive examination of these traits. A total of 120 watermelon seed samples from three distinct varieties, were curated in this study, facilitating a comprehensive analysis of both their outer layers and inner kernels. Utilizing a transmission imaging modality, THz spectral images were acquired and subsequently reconstructed employing a correlation coefficient method. Deep learning-based SegNet and DeepLab V3+ models were employed for automatic tissue segmentation. Our research revealed that DeepLab V3+ significantly surpassed SegNet in both speed and accuracy. Specifically, DeepLab V3+ achieved a pixel accuracy of 96.69 % and an intersection over the union of 91.3 % for the outer layer, with the inner kernel results closely following. These results underscore the proficiency of DeepLab V3+ in distinguishing between the seed coat and kernel, thereby furnishing precise phenotypic trait analyses for seeds with thin shells. Moreover, this study accentuates the instrumental role of deep learning technologies in advancing agricultural research and practices.

Identification and quantification of adulteration in collagen powder by terahertz spectroscopy - the effect of spectral characteristics on performance is considered

Terahertz spectroscopy is an emerging rapid detection method that can be used to detect and analyze food quality issues. However, models developed based on various spectral characteristics of terahertz have shown different performances in food identification. Therefore, we preliminarily analyzed the effect of terahertz spectral characteristics on the identification and quantification of collagen powder adulterated with food powders (plant protein powder, corn starch, wheat flour) with the use of random forest (RF), linear discriminant analysis (LDA), and partial least squares regression (PLSR), and determined the spectral characteristics suitable for identification and quantitative analysis. Then, the selected spectral characteristics data were preprocessed using baseline correction (BC), gaussian filter (GF), moving average (MA), and savitzky-golay (SG). Feature variables were extracted from preprocessed spectral characteristics data using genetic algorithm (GA), random forest (RF), and least angle regression (LAR). The study indicated that the BC-GA-LDA classification model based on the absorption coefficient spectra achieved an accuracy of 96.96% in identifying adulterated collagen powder. Additionally, the GA-PLSR model developed based on the power spectra demonstrated excellent performance in predicting adulteration levels, with the coefficient of determination (Rp2) values ranging from 0.93 to 0.99. The results showed that the rational selection of terahertz spectral characteristics is highly feasible for the accurate detection of collagen powder adulteration.

Intelligent Rapid Detection Techniques for Low-Content Components in Fruits and Vegetables: A Comprehensive Review

Fruits and vegetables are an important part of our daily diet and contain low-content components that are crucial for our health. Detecting these components accurately is of paramount significance. However, traditional detection methods face challenges such as complex sample processing, slow detection speed, and the need for highly skilled operators. These limitations fail to meet the growing demand for intelligent and rapid detection of low-content components in fruits and vegetables. In recent years, significant progress has been made in intelligent rapid detection technology, particularly in detecting high-content components in fruits and vegetables. However, the accurate detection of low-content components remains a challenge and has gained considerable attention in current research. This review paper aims to explore and analyze several intelligent rapid detection techniques that have been extensively studied for this purpose. These techniques include near-infrared spectroscopy, Raman spectroscopy, laser-induced breakdown spectroscopy, and terahertz spectroscopy, among others. This paper provides detailed reports and analyses of the application of these methods in detecting low-content components. Furthermore, it offers a prospective exploration of their future development in this field. The goal is to contribute to the enhancement and widespread adoption of technology for detecting low-content components in fruits and vegetables. It is expected that this review will serve as a valuable reference for researchers and practitioners in this area.

Terahertz time-domain imaging for the examination of gilded wooden artifacts

Terahertz imaging is unlocking unique capabilities for the analysis of cultural heritage artifacts. This paper uses terahertz time-domain imaging for the study of a gilded wooden artifact, providing a means to perform stratigraphic analysis, yielding information about the composition of the artifact, presence of certain materials identifiable through their THz spectral fingerprint, as well as alterations that have been performed over time. Due to the limited information that is available for many historic artifacts, the data that can be obtained through the presented technique can guide proper stewardship of the artifact, informing its long-term preservation.

The Rapid Non-Destructive Differentiation of Different Varieties of Rice by Fluorescence Hyperspectral Technology Combined with Machine Learning

A rice classification method for the fast and non-destructive differentiation of different varieties is significant in research at present. In this study, fluorescence hyperspectral technology combined with machine learning techniques was used to distinguish five rice varieties by analyzing the fluorescence hyperspectral features of Thai jasmine rice and four rice varieties with a similar appearance to Thai jasmine rice in the wavelength range of 475-1000 nm. The fluorescence hyperspectral data were preprocessed by a first-order derivative (FD) to reduce the background and baseline drift effects of the rice samples. Then, a principal component analysis (PCA) and t-distributed stochastic neighborhood embedding (t-SNE) were used for feature reduction and 3D visualization display. A partial least squares discriminant analysis (PLS-DA), BP neural network (BP), and random forest (RF) were used to build the rice classification models. The RF classification model parameters were optimized using the gray wolf algorithm (GWO). The results show that FD-t-SNE-GWO-RF is the best model for rice classification, with accuracy values of 99.8% and 95.3% for the training and test sets, respectively. The fluorescence hyperspectral technique combined with machine learning is feasible for classifying rice varieties.

Predicting wheat gluten concentrations in potato starch using GPR and SVM models built by terahertz time-domain spectroscopy

The purpose of this study was for the first time to explore the feasibility of terahertz (THz) spectral imaging for the detection of gluten contents in food samples. Based on the obtained 80 THz spectrum data, Gaussian process regression (GPR) and support vector machine (SVM) models were established to predict wheat gluten concentrations in 40 potato starch mixture samples. The prediction performances of GPR and SVM obtained were R2 = 0.859 and RMSE = 0.070, and R2 = 0.715 and RMSE = 0.101 in the gluten concentration range of 1.3%-100%, respectively, showing that the linear SVM algorithm had better prediction performance. The results indicated that THz spectral imaging combined with GPR could be used to predict the gluten content in food samples. It is thus hoped that this research should provide a novel technique for gluten content detection to ensure gluten-free food samples.

Rapid analysis technologies with chemometrics for food authenticity field: A review

In recent years, the problem of food adulteration has become increasingly rampant, seriously hindering the development of food production, consumption, and management. The common analytical methods used to determine food authenticity present challenges, such as complicated analysis processes and time-consuming procedures, necessitating the development of rapid, efficient analysis technology for food authentication. Spectroscopic techniques, ambient ionization mass spectrometry (AIMS), electronic sensors, and DNA-based technology have gradually been applied for food authentication due to advantages such as rapid analysis and simple operation. This paper summarizes the current research on rapid food authenticity analysis technology from three perspectives, including breeds or species determination, quality fraud detection, and geographical origin identification, and introduces chemometrics method adapted to rapid analysis techniques. It aims to promote the development of rapid analysis technology in the food authenticity field.

Predicting rice diseases using advanced technologies at different scales: present status and future perspectives

The past few years have witnessed significant progress in emerging disease detection techniques for accurately and rapidly tracking rice diseases and predicting potential solutions. In this review we focus on image processing techniques using machine learning (ML) and deep learning (DL) models related to multi-scale rice diseases. Furthermore, we summarize applications of different detection techniques, including genomic, physiological, and biochemical approaches. In addition, we also present the state-of-the-art in contemporary optical sensing applications of pathogen-plant interaction phenotypes. This review serves as a valuable resource for researchers seeking effective solutions to address the challenges of high-throughput data and model recognition for early detection of issues affecting rice crops through ML and DL models.

Application of spectroscopic techniques combined with chemometrics to the authenticity and quality attributes of rice

Rice is a staple food for two-thirds of the world's population and is grown in over a hundred countries around the world. Due to its large scale, it is vulnerable to adulteration. In addition, the quality attribute of rice is an important factor affecting the circulation and price, which is also paid more and more attention. The combination of spectroscopy and chemometrics enables rapid detection of authenticity and quality attributes in rice. This article described the application of seven spectroscopic techniques combined with chemometrics to the rice industry. For a long time, near-infrared spectroscopy and linear chemometric methods (e.g., PLSR and PLS-DA) have been widely used in the rice industry. Although some studies have achieved good accuracy, with models in many studies having greater than 90% accuracy. However, higher accuracy and stability were more likely to be obtained using multiple spectroscopic techniques, nonlinear chemometric methods, and key wavelength selection algorithms. Future research should develop larger rice databases to include more rice varieties and larger amounts of rice depending on the type of rice, and then combine various spectroscopic techniques, nonlinear chemometric methods, and key wavelength selection algorithms. This article provided a reference for a more efficient and accurate determination of rice quality and authenticity.

Concise Cascade Methods for Transgenic Rice Seed Discrimination using Spectral Phenotyping

Currently, the presence of genetically modified (GM) organisms in agro-food markets is strictly regulated by enacted legislation worldwide. It is essential to ensure the traceability of these transgenic products for food safety, consumer choice, environmental monitoring, market integrity, and scientific research. However, detecting the existence of GM organisms involves a combination of complex, time-consuming, and labor-intensive techniques requiring high-level professional skills. In this paper, a concise and rapid pipeline method to identify transgenic rice seeds was proposed on the basis of spectral imaging technologies and the deep learning approach. The composition of metabolome across 3 rice seed lines containing the cry1Ab/cry1Ac gene was compared and studied, substantiating the intrinsic variability induced by these GM traits. Results showed that near-infrared and terahertz spectra from different genotypes could reveal the regularity of GM metabolic variation. The established cascade deep learning model divided GM discrimination into 2 phases including variety classification and GM status identification. It could be found that terahertz absorption spectra contained more valuable features and achieved the highest accuracy of 97.04% for variety classification and 99.71% for GM status identification. Moreover, a modified guided backpropagation algorithm was proposed to select the task-specific characteristic wavelengths for further reducing the redundancy of the original spectra. The experimental validation of the cascade discriminant method in conjunction with spectroscopy confirmed its viability, simplicity, and effectiveness as a valuable tool for the detection of GM rice seeds. This approach also demonstrated its great potential in distilling crucial features for expedited transgenic risk assessment.

A Review of Recent Advances for the Detection of Biological, Chemical, and Physical Hazards in Foodstuffs Using Spectral Imaging Techniques

Traditional methods for detecting foodstuff hazards are time-consuming, inefficient, and destructive. Spectral imaging techniques have been proven to overcome these disadvantages in detecting foodstuff hazards. Compared with traditional methods, spectral imaging could also increase the throughput and frequency of detection. This study reviewed the techniques used to detect biological, chemical, and physical hazards in foodstuffs including ultraviolet, visible and near-infrared (UV-Vis-NIR) spectroscopy, terahertz (THz) spectroscopy, hyperspectral imaging, and Raman spectroscopy. The advantages and disadvantages of these techniques were discussed and compared. The latest studies regarding machine learning algorithms for detecting foodstuff hazards were also summarized. It can be found that spectral imaging techniques are useful in the detection of foodstuff hazards. Thus, this review provides updated information regarding the spectral imaging techniques that can be used by food industries and as a foundation for further studies.

Origin identification of Cornus officinalis based on PCA-SVM combined model

Infrared spectroscopy can quickly and non-destructively extract analytical information from samples. It can be applied to the authenticity identification of various Chinese herbal medicines, the prediction of the mixing amount of defective products, and the analysis of the origin. In this paper, the spectral information of Cornus officinalis from 11 origins was used as the research object, and the origin identification model of Cornus officinalis based on mid-infrared spectroscopy was established. First, principal component analysis was used to extract the absorbance data of Cornus officinalis in the wavenumber range of 551~3998 cm-1. The extracted principal components contain more than 99.8% of the information of the original data. Second, the extracted principal component information was used as input, and the origin category was used as output, and the origin identification model was trained with the help of support vector machine. In this paper, this combined model is called PCA-SVM combined model. Finally, the generalization ability of the PCA-SVM model is evaluated through an external test set. The three indicators of Accuracy, F1-Score, and Kappa coefficient are used to compare this model with other commonly used classification models such as naive Bayes model, decision trees, linear discriminant analysis, radial basis function neural network and partial least square discriminant analysis. The results show that PCA-SVM model is superior to other commonly used models in accuracy, F1 score and Kappa coefficient. In addition, compared with the SVM model with full spectrum data, the PCA-SVM model not only reduces the redundant variables in the model, but also has higher accuracy. Using this model to identify the origin of Cornus officinalis, the accuracy rate is 84.8%.

Discrimination of Pericarpium Citri Reticulatae in different years using Terahertz Time-Domain spectroscopy combined with convolutional neural network

Pericarpium Citri Reticulatae (PCR) in longer storage years possess higher medicinal values, but their differentiation is difficult due to similar morphological characteristics. Therefore, this study investigated the feasibility of using terahertz time-domain spectroscopy (THz-TDS) combined with a convolutional neural network (CNN) to identify PCR samples stored from 1 to 20 years. The absorption coefficient and refractive index spectra in the range of 0.2-1.5 THz were acquired. Partial least squares discriminant analysis, random forest, least squares support vector machines, and CNN were used to establish discriminant models, showing better performance of the CNN model than the others. In addition, the output data points of the CNN intermediate layer were visualized, illustrating gradual changes in these points from overlapping to clear separation. Overall, THz-TDS combined with CNN models could realize rapid identification of different year PCRs, thus providing an efficient alternative method for PCR quality inspection.

THz-ATR Spectroscopy Integrated with Species Recognition Based on Multi-Classifier Voting for Automated Clinical Microbial Identification

The demand for rapid and accurate identification of microorganisms is growing due to considerable importance in all areas related to public health and safety. Here, we demonstrate a rapid and label-free strategy for the identification of microorganisms by integrating terahertz-attenuated total reflection (THz-ATR) spectroscopy with an automated recognition method based on multi-classifier voting. Our results show that 13 standard microbial strains can be classified into three different groups of microorganisms (Gram-positive bacteria, Gram-negative bacteria, and fungi) by THz-ATR spectroscopy. To detect clinical microbial strains with better differentiation that accounts for their greater sample heterogeneity, an automated recognition algorithm is proposed based on multi-classifier voting. It uses three types of machine learning classifiers to identify five different groups of clinical microbial strains. The results demonstrate that common microorganisms, once time-consuming to distinguish by traditional microbial identification methods, can be rapidly and accurately recognized using THz-ATR spectra in minutes. The proposed automatic recognition method is optimized by a spectroscopic feature selection algorithm designed to identify the optimal diagnostic indicator, and the combination of different machine learning classifiers with a voting scheme. The total diagnostic accuracy reaches 80.77% (as high as 99.6% for Enterococcus faecalis) for 1123 isolates from clinical samples of sputum, blood, urine, and feces. This strategy demonstrates that THz spectroscopy integrated with an automatic recognition method based on multi-classifier voting significantly improves the accuracy of spectral analysis, thereby presenting a new method for true label-free identification of clinical microorganisms with high efficiency.

A dual AE-GAN guided THz spectral dehulling model for mapping energy and moisture distribution on sunflower seed kernels

Energy and moisture contents are important food chemical attributes. In the current study, a nondestructive Terahertz (THz) time-domain imaging system was first time used for evaluating the energy and moisture distributions of sunflower seed kernels inside shells. For this task, a dual autoencoders (AE)-generative adversarial nets (GAN) spectral dehulling semi-supervised model was developed. The model could automatically learn the kernel information from the latent representations of the spectra of the intact seeds through adversarial learning to achieve feature disentanglement. Results indicated that the generated kernel images had similar features to the original kernel images and high-quality chemical distribution maps for energy and moisture contents of sunflower seed kernels inside shells were successfully obtained. As the current method took the advantage of the characteristics of THz imaging and selected a suitable deep learning algorithm, it has the potential to generalize for imaging other chemical substances of other dry shelled seeds or biological samples (moisture content and thickness below 15% and 5 mm, respectively).

Applications of THz Spectral Imaging in the Detection of Agricultural Products

Agricultural products need to be inspected for quality and safety, and the issue of safety of agricultural products caused by quality is frequently investigated. Safety testing should be carried out before agricultural products are consumed. The existing technologies for inspecting agricultural products are time-consuming and require complex operation, and there is motivation to develop a rapid, safe, and non-destructive inspection technology. In recent years, with the continuous progress of THz technology, THz spectral imaging, with the advantages of its unique characteristics, such as low energies, superior spatial resolution, and high sensitivity to water, has been recognized as an efficient and feasible identification tool, which has been widely used for the qualitative and quantitative analyses of agricultural production. In this paper, the current main performance achievements of the use of THz images are presented. In addition, recent advances in the application of THz spectral imaging technology for inspection of agricultural products are reviewed, including internal component detection, seed classification, pesticide residues detection, and foreign body and packaging inspection. Furthermore, machine learning methods applied in THz spectral imaging are discussed. Finally, the existing problems of THz spectral imaging technology are analyzed, and future research directions for THz spectral imaging technology are proposed. Recent rapid development of THz spectral imaging has demonstrated the advantages of THz radiation and its potential application in agricultural products. The rapid development of THz spectroscopic imaging combined with deep learning can be expected to have great potential for widespread application in the fields of agriculture and food engineering.

The application of machine-learning and Raman spectroscopy for the rapid detection of edible oils type and adulteration

Raman spectroscopy is an emerging technique for the rapid detection of oil qualities. But the spectral analysis is time-consuming and low-throughput, which has limited the broad adoption. To address this issue, nine supervised machine learning (ML) algorithms were integrated into a Raman spectroscopy protocol for achieving the rapid analysis. Raman spectra were obtained for ten commercial edible oils from a variety of brands and the resulting spectral dataset was analyzed with supervised ML algorithms and compared against a principal component analysis (PCA) model. A ML-derived model obtained an accuracy of 96.7% in detecting oil type and an adulteration prediction of 0.984 (R²). Several ML algorithms also were superior than PCA in classifying edible oils based on fatty acid compositions by gas chromatography, with a faster readout and 100% accuracy. This study provided an exemplar for combining conventional Raman spectroscopy or gas chromatography with ML for the rapid food analysis.

A terahertz time-domain super-resolution imaging method using a local-pixel graph neural network for biological products

The low image acquisition speed of terahertz (THz) time-domain imaging systems limits their application in biological products analysis. In the current study, a local pixel graph neural network was built for THz time-domain imaging super-resolution. The method could be applied to the analysis of any heterogeneous biological products as it only required a small number of sample images for training and particularly it focused on THz feature frequencies. The graph network applied the Fourier transform to graphs extracted from low-resolution (LR) images bringing an invariance of rotation and flip for local pixels, and the network then learnt the relationship between the state of graphs and the corresponding pixels to be reconstructed. With wood cores and seeds as examples, the images of these samples were captured by a THz time-domain imaging system for training and analysed by the method, achieving the root mean square error (RMSE) of pixels of 0.0957 and 0.1061 for the wood core and seed images, respectively. In addition, the reconstructed high-resolution (HR) images, LR images and true HR images at several feature frequencies were also compared in the current study. Results indicated that the method could not only reconstruct the spatial details and the useful signals from high noise signals at high feature frequencies but could also operate super-resolution in both spatial and spectral aspects.

Advances in the Immunoassays for Detection of Bacillus thuringiensis Crystalline Toxins

Insect-resistant genetically modified organisms have been globally commercialized for the last 2 decades. Among them, transgenic crops based on Bacillus thuringiensis crystalline (Cry) toxins are extensively used for commercial agricultural applications. However, less emphasis is laid on quantifying Cry toxins because there might be unforeseen health and environmental concerns. Immunoassays, being the preferred method for detection of Cry toxins, are reviewed in this study. Owing to limitations of traditional colorimetric enzyme-linked immunosorbent assay, the trend of detection strategies shifts to modified immunoassays based on nanomaterials, which provide ultrasensitive detection capacity. This review assessed and compared the properties of the recent advances in immunoassays, including colorimetric, fluorescence, chemiluminescence, surface-enhanced Raman scattering, surface plasmon resonance, and electrochemical approaches. Thus, the ultimate aim of this study is to identify research gaps and infer future prospects of current approaches for the development of novel immunosensors to monitor Cry toxins in food and the environment.

Determination of the Geographical Origin of Coffee Beans Using Terahertz Spectroscopy Combined With Machine Learning Methods

Different geographical origins can lead to great variance in coffee quality, taste, and commercial value. Hence, controlling the authenticity of the origin of coffee beans is of great importance for producers and consumers worldwide. In this study, terahertz (THz) spectroscopy, combined with machine learning methods, was investigated as a fast and non-destructive method to classify the geographic origin of coffee beans, comparing it with the popular machine learning methods, including convolutional neural network (CNN), linear discriminant analysis (LDA), and support vector machine (SVM) to obtain the best model. The curse of dimensionality will cause some classification methods which are struggling to train effective models. Thus, principal component analysis (PCA) and genetic algorithm (GA) were applied for LDA and SVM to create a smaller set of features. The first nine principal components (PCs) with an accumulative contribution rate of 99.9% extracted by PCA and 21 variables selected by GA were the inputs of LDA and SVM models. The results demonstrate that the excellent classification (accuracy was 90% in a prediction set) could be achieved using a CNN method. The results also indicate variable selecting as an important step to create an accurate and robust discrimination model. The performances of LDA and SVM algorithms could be improved with spectral features extracted by PCA and GA. The GA-SVM has achieved 75% accuracy in a prediction set, while the SVM and PCA-SVM have achieved 50 and 65% accuracy, respectively. These results demonstrate that THz spectroscopy, together with machine learning methods, is an effective and satisfactory approach for classifying geographical origins of coffee beans, suggesting the techniques to tap the potential application of deep learning in the authenticity of agricultural products while expanding the application of THz spectroscopy.

Terahertz, infrared and Raman absorption spectra of tyrosine enantiomers and racemic compound

The application of terahertz (THz)-based techniques in biomolecule study is very promising but still in its infancy. In the present work, we employed THz time-domain spectroscopy (THz-TDS) and THz time-domain attenuated total reflection (THz-TD-ATR) spectroscopy to investigate the properties of tyrosine (Tyr) enantiomers (L- and D-Tyr) and racemate (DL-Tyr) in solid state and aqueous solutions, respectively. THz absorption spectra of solid L- and D-Tyr show similar absorption spectra with peaks at 0.95, 1.92, 2.06 and 2.60 THz, which are obviously different from the spectrum of DL-Tyr with peaks at 1.5, 2.15 and 2.40 THz. In contrast, although THz absorption spectra of L-Tyr solution and D-Tyr solution are similar and different from the spectrum of DL-Tyr solution, both of them have no observable peaks. Interestingly, it was found that the solution containing equal amounts of L- and D-Tyr has a similar spectrum as that of DL-Tyr solution, as far as the mass concentrations of the two types of solutions are kept the same. On other hand, solid L-, D- and DL-Tyr were also investigated with infrared spectroscopy and Raman spectroscopy, respectively. The results show that the spectra of L- and D-Tyr can be regarded the same but they are slightly different from the spectrum of DL-Tyr. With the aid of principal component analysis (PCA), the difference between L-/D-Tyr and DL-Tyr can be confirmed without any ambiguity. Overall, this work systematically interrogated and evaluated the performance of THz-based techniques in the detection of the chirality of tyrosine.

Authentication of Rice (Oryza sativa L.) Using Near Infrared Spectroscopy Combined with Different Chemometric Classification Strategies

Rice is a staple food in Vietnam, and the concern about rice is much greater than that for other foods. Preventing fraud against this product has become increasingly important in order to protect producers and consumers from possible economic losses. The possible adulteration of this product is done by mixing, or even replacing, high-quality rice with cheaper rice. This highlights the need for analytical methodologies suitable for its authentication. Given this scenario, the present work aims at testing a rapid and non-destructive approach to detect adulterated rice samples. To fulfill this purpose, 200 rice samples (72 authentic and 128 adulterated samples) were analyzed by near infrared (NIR) spectroscopy coupled, with partial least squares-discriminant analysis (PLS-DA) and soft independent modeling of class analogies (SIMCA). The two approaches provided different results; while PLS-DA analysis was a suitable approach for the purpose of the work, SIMCA was unable to solve the investigated problem. The PLS-DA approach provided satisfactory results in discriminating authentic and adulterated samples (both 5% and 10% counterfeits). Focusing on authentic and 10%-adulterated samples, the accuracy of the approach was even better (with a total classification rate of 82.6% and 82.4%, for authentic and adulterated samples, respectively).

Rapid detection of carmine in black tea with spectrophotometry coupled predictive modelling

Carmine is an artificial colorant commonly used by fraudulent food business participants in black tea adulteration, for purpose of gaining illegal profits. This study combined spectrophotometry with machine learning for rapid detection of carmine in black tea based on the spectral characteristics of tea infusion. The qualitative model demonstrated an accuracy rate of 100% for successful identification of the presence/absence of carmine in black tea. For quantitative analysis, the R² between carmine concentrations generated according to spectral characteristics and those determined with HPLC was 0.988 and 0.972, respectively, for black tea samples involved in the test subset and an independent dataset II. Paired t-test indicated that the difference was statistically insignificant (P values of 0.26 and 0.44, respectively). The method established in this study was rapid and reliable for detecting carmine in black tea, and thus could be used as a useful tool to identify black tea adulteration in market.

Preliminary study on discrimination of transgenic cotton seeds using terahertz time-domain spectroscopy

Presence of genetically modified (GM) organisms is considered to be controversial by legislation and public. It is very important to develop detection methods for early discriminations. Conventional gene detection methods, including protein detection (PCR, ELISA, and so on) and DNA detection (Southern blot, GC/MS, and so on), have the disadvantages of high costs, time-consuming, complex operations, and destructive of the samples. Terahertz spectroscopy (THz) is a brand-new radiation with many unique advantages. Most biological macromolecules have fingerprint characteristics in THz band from the current recognition. In this study, feasibility of identifying the transgenic cotton seeds from nontransgenic counterparts using THz spectroscopy method was investigated. The transgenic cotton seeds-Lumianyan No.28 and nontransgenic cotton seeds-Xinluzao No.51 were selected and the sample-making methods were studied; then the refractive and absorption curves of samples were got and given a detailed discussion; finally, absorption index of transgenic and nontransgenic DNA was observed and discussed. The results showed there were small fluctuations in THz band, and refractive index of transgenic seeds was lower than nontransgenic ones and had obvious turning point at 1.4-2.0 THz region. There were significant peaks in 1.0-1.2 and 1.3-1.5 THz regions for the transgenic cotton seeds. Transgenic DNA had higher absorption index than nontransgenic DNA, and there were 3-4 peaks corresponding to the cotton seed samples in 1.0-1.6 THz region. These results showed cotton seeds samples can provide important bio-information in THz band, and this study provided a basis for developing potential THz-based gene detection technologies.

Application of terahertz spectrum and interval partial least squares method in the identification of genetically modified soybeans

Genetically modified soybeans are the world's most important genetically modified agricultural product. At present, the traditional methods for identifying genetically modified and non-transgenic soybeans are time-consuming, costly, and complicated to operate, which cannot meet the needs of practical applications. Therefore, it is necessary to discover a fast and accurate method for identifying transgenic soybeans. Terahertz (THz) time domain spectra were collected in sequence from 225 transgenic and non-transgenic soybean samples. Fourier transform was used to convert the terahertz time domain spectrum into a THz frequency domain spectrum with a frequency range of 0.1-2.5 THz. Firstly, the interval partial least squares (iPLS) method was used to remove interference spectral bands and select appropriate spectral intervals. Secondly, 168 samples were selected as the calibration set. Discriminant partial least squares (DPLS), Grid Search support vector machine (Grid Search-SVM) and principal component analysis back propagation neural network (PCA-BPNN) were used to establish a qualitative identification model. Afterwards, 57 test set samples were predicted. By comparing the experimental results, it was found that iPLS could effectively screen and remove the interference THz band, which was more helpful to improve the efficiency and accuracy of the identification model. After the iPLS and mean center pre-treatment technology, the Grid Search-SVM identification model had the best identification effect, with a total accuracy rate of 98.25% (transgenic identification rate was 96.15%, non-transgenic identification rate was 100%). This study shows that after selecting spectra from iPLS, THz spectroscopy combined with chemometrics can more accurately, quickly, and efficiently identify transgenic and non-transgenic soybeans.

Comparison of Chemometric Problems in Food Analysis Using Non-Linear Methods

Food analysis is a challenging analytical problem, often addressed using sophisticated laboratory methods that produce large data sets. Linear and non-linear multivariate methods can be used to process these types of datasets and to answer questions such as whether product origin is accurately labeled or whether a product is safe to eat. In this review, we present the application of non-linear methods such as artificial neural networks, support vector machines, self-organizing maps, and multi-layer artificial neural networks in the field of chemometrics related to food analysis. We discuss criteria to determine when non-linear methods are better suited for use instead of traditional methods. The principles of algorithms are described, and examples are presented for solving the problems of exploratory analysis, classification, and prediction.

Terahertz spectroscopy technology as an innovative technique for food: Current state-of-the-Art research advances

With the dramatic development of source and detector components, terahertz (THz) spectroscopy technology has recently shown a renaissance in various fields such as medical, material, biosensing and pharmaceutical industry. As a rapid and noninvasive technology, it has been extensively exploited to evaluate food quality and ensure food safety. In this review, the principles and processes of THz spectroscopy are first discussed. The current state-of-the-art applications of THz and imaging technologies focused on foodstuffs are then discussed. The advantages and challenges are also covered. This review offers detailed information for recent efforts dedicated to THz for monitoring the quality and safety of various food commodities and the feasibility of its widespread application. THz technology, as an emerging and unique method, is potentially applied for detecting food processing and maintaining quality and safety.

Identification of Bacterial Blight Resistant Rice Seeds Using Terahertz Imaging and Hyperspectral Imaging Combined With Convolutional Neural Network

Because bacterial blight (BB) disease seriously affects the yield and quality of rice, breeding BB resistant rice is an important priority for plant breeders but the process is time-consuming. The feasibility of using terahertz imaging technology and near-infrared hyperspectral imaging technology to identify BB resistant seeds has therefore been studied. The two-dimensional (2D) spectral images and one-dimensional (1D) spectra provided by both imaging methods were used to build discriminant models based on a deep learning method, the convolutional neural network (CNN), and traditional machine learning methods, support vector machine (SVM), random forest (RF), and partial least squares discriminant analysis (PLS-DA). The highest classification accuracy was achieved by the discriminate model based on CNN using the terahertz absorption spectra. Confusion matrixes were pictured to show the identification details. The t-distributed stochastic neighbor embedding (t-SNE) method was used to visualize the process of CNN data processing. Terahertz imaging technology combined with CNN has great potential to quickly identify BB resistant rice seeds and is more accurate than using near-infrared hyperspectral imaging.

Studies on qualitative and quantitative detection of trehalose purity by terahertz spectroscopy

Terahertz spectroscopy was used to qualitatively and quantitatively analyze four samples (three brands) of trehalose produced in China and other countries. The results show that the main characteristic peak was greatly affected by concentration, and the optimal detection concentration of trehalose was determined to be 25%-55% by transmission scanning. There were six significant characteristic absorption peaks in the trehalose spectrum, meaning that terahertz spectroscopy can be used for qualitative analysis, analogous to infrared spectroscopy. Moreover, the terahertz spectrum can effectively distinguish the three isomers of trehalose, whereas infrared spectroscopy cannot. Thus, it was found that the current commercially available trehalose is the α,α-isomer. Quantitative analysis of the three brands of trehalose using terahertz spectroscopy matched the purity trends found by high-performance liquid chromatography analysis, with the order of purity from highest to lowest being TREHA, Pioneer, and Huiyang. The actual quantitative values did differ between the two detection methods, but the variation in the values from the same sample obtained by the two detection methods was less than 5%, confirming that terahertz spectroscopy is very suitable for the rapid and relative quantitative detection of trehalose.

A Rapid and Highly Efficient Method for the Identification of Soybean Seed Varieties: Hyperspectral Images Combined with Transfer Learning

Convolutional neural network (CNN) can be used to quickly identify crop seed varieties. 1200 seeds of ten soybean varieties were selected, hyperspectral images of both the front and the back of the seeds were collected, and the reflectance of soybean was derived from the hyperspectral images. A total of 9600 images were obtained after data augmentation, and the images were divided into a training set, validation set, and test set with a 3:1:1 ratio. Pretrained models (AlexNet, ResNet18, Xception, InceptionV3, DenseNet201, and NASNetLarge) after fine-tuning were used for transfer training. The optimal CNN model for soybean seed variety identification was selected. Furthermore, the traditional machine learning models for soybean seed variety identification were established by using reflectance as input. The results show that the six models all achieved 91% accuracy in the validation set and achieved accuracy values of 90.6%, 94.5%, 95.4%, 95.6%, 96.8%, and 97.2%, respectively, in the test set. This method is better than the identification of soybean seed varieties based on hyperspectral reflectance. The experimental results support a novel method for identifying soybean seeds rapidly and accurately, and this method also provides a good reference for the identification of other crop seeds.

Rapidly and exactly determining postharvest dry soybean seed quality based on machine vision technology

The development of machine vision-based technologies to replace human labor for rapid and exact detection of agricultural product quality has received extensive attention. In this study, we describe a low-rank representation of jointly multi-modal bag-of-feature (JMBoF) classification framework for inspecting the appearance quality of postharvest dry soybean seeds. Two categories of speeded-up robust features and spatial layout of L*a*b* color features are extracted to characterize the dry soybean seed kernel. The bag-of-feature model is used to generate a visual dictionary descriptor from the above two features, respectively. In order to exactly represent the image characteristics, we introduce the low-rank representation (LRR) method to eliminate the redundant information from the long joint two kinds of modal dictionary descriptors. The multiclass support vector machine algorithm is used to classify the encoding LRR of the jointly multi-modal bag of features. We validate our JMBoF classification algorithm on the soybean seed image dataset. The proposed method significantly outperforms the state-of-the-art single-modal bag of features methods in the literature, which could contribute in the future as a significant and valuable technology in postharvest dry soybean seed classification procedure.

A Comprehensive Review on Food Applications of Terahertz Spectroscopy and Imaging

Food product safety is a public health concern. Most of the food safety analytical and detection methods are expensive, labor intensive, and time consuming. A safe, rapid, reliable, and nondestructive detection method is needed to assure consumers that food products are safe to consume. Terahertz (THz) radiation, which has properties of both microwave and infrared, can penetrate and interact with many commonly used materials. Owing to the technological developments in sources and detectors, THz spectroscopic imaging has transitioned from a laboratory-scale technique into a versatile imaging tool with many practical applications. In recent years, THz imaging has been shown to have great potential as an emerging nondestructive tool for food inspection. THz spectroscopy provides qualitative and quantitative information about food samples. The main applications of THz in food industries include detection of moisture, foreign bodies, inspection, and quality control. Other applications of THz technology in the food industry include detection of harmful compounds, antibiotics, and microorganisms. THz spectroscopy is a great tool for characterization of carbohydrates, amino acids, fatty acids, and vitamins. Despite its potential applications, THz technology has some limitations, such as limited penetration, scattering effect, limited sensitivity, and low limit of detection. THz technology is still expensive, and there is no available THz database library for food compounds. The scanning speed needs to be improved in the future generations of THz systems. Although many technological aspects need to be improved, THz technology has already been established in the food industry as a powerful tool with great detection and quantification ability. This paper reviews various applications of THz spectroscopy and imaging in the food industry.

Geographic identification of Boletus mushrooms by data fusion of FT-IR and UV spectroscopies combined with multivariate statistical analysis

Boletus griseus and Boletus edulis are two well-known wild-grown edible mushrooms which have high nutrition, delicious flavor and high economic value distributing in Yunnan Province. In this study, a rapid method using Fourier transform infrared (FT-IR) and ultraviolet (UV) spectroscopies coupled with data fusion was established for the discrimination of Boletus mushrooms from seven different geographical origins with pattern recognition method. Initially, the spectra of 332 mushroom samples obtained from the two spectroscopic techniques were analyzed individually and then the classification performance based on data fusion strategy was investigated. Meanwhile, the latent variables (LVs) of FT-IR and UV spectra were extracted by partial least square discriminant analysis (PLS-DA) and two datasets were concatenated into a new matrix for data fusion. Then, the fusion matrix was further analyzed by support vector machine (SVM). Compared with single spectroscopic technique, data fusion strategy can improve the classification performance effectively. In particular, the accuracy of correct classification of SVM model in training and test sets were 99.10% and 100.00%, respectively. The results demonstrated that data fusion of FT-IR and UV spectra can provide higher synergic effect for the discrimination of different geographical origins of Boletus mushrooms, which may be benefit for further authentication and quality assessment of edible mushrooms.

Analysis of fluoroquinolones antibiotic residue in feed matrices using terahertz spectroscopy

As antibiotic residue becomes more and more serious all over the world, a rapid and effective detection method is needed to evaluate the antibiotic residue in feed matrices to ensure food safety for consumers. In this study, three different kinds of fluoroquinolones (norfloxacin, enrofloxacin, and ofloxacin) in feed matrices were analyzed using terahertz (THz) spectroscopy, respectively. Meanwhile, pure fluoroquinolones and pure feed matrices were also measured in the same way. Then, the absorption spectra of all of the samples were extracted in the transmission mode. Pure norfloxacin has two absorption peaks at 0.825 and 1.187 THz, and they could still be observed when mixing norfloxacin with feed matrices. Also, there was an obvious and strong absorption peak for ofloxacin at 1.044 THz. However, no obvious absorption peak for enrofloxacin was observed, and only a weak absorption peak was located at 0.8 THz. Then, the different models were established with different chemometrics to identify the fluoroquinolones in feed matrices and determined the fluoroquinolones content in the feed matrices. The least squares support vector machines, Naive Bayes, Mahalanobis distance, and back propagation neural network (BPNN) were used to build the identification model with a Savitzky-Golay filter and standardized normal variate pretreatments. The results show that the excellent classification model was acquired with the BPNN combined with no pretreatment. The optimal classification accuracy was 80.56% in the testing set. After that, multiple linear regression and stepwise regression were used to establish the quantitative detection model for different kinds of fluoroquinolones in feed matrices. The optimal correlation coefficients for norfloxacin, enrofloxacin, and ofloxacin in the prediction set were obtained with multiple linear regression that combined absorption peaks with wavelengths selected by stepwise regression, which were 0.867, 0.828, and 0.964, respectively. Overall, this research explored the potential of identifying the fluoroquinolones in feed matrices using THz spectroscopy without a complex pretreatment process and then quantitatively detecting the fluoroquinolones content in feed matrices. The results demonstrate that THz spectra could be used to identify fluoroquinolones in feed matrices and also detect their content quantitatively, which has great significance for the food safety industry.

An atypical strictosidine synthase, OsSTRL2, plays key roles in anther development and pollen wall formation in rice

Strictosidine synthase (STR) plays an important role in the biosynthesis of terpenoid indole alkaloids (TIAs) and is expressed in a range of active meristematic tissues of higher plants. STR proteins are involved in different physiological and biochemical pathways. However, the function of STR proteins in rice development remains poorly understood. In this study, we identified 21 possible STR-like (OsSTRL) family members in rice genome and found that only one gene, OsSTRL2, exhibited a pre-emergency specific florescence expression pattern. Tissue-specific expression profile analysis, β-glucuronidase histochemical (GUS) staining and RNA in situ hybridization confirmed that OsSTRL2 was highly expressed in tapetal cells and microspores. Comparative protein sequence analysis indicated that OsSTRL2 lacked the key catalytic residue found in a typical STR (STR1), although it possessed conserved β-propellers and α-helices formed the basic structure of STR1. OsSTRL2 knockout mutant resulted to male sterility because of the defects in anther development and pollen wall formation. Subcellular localization of OsSTRL2-YFP revealed that the OsSTRL2 protein was primarily localized in the endoplasmic reticulum (ER). Therefore, OsSTRL2 is an atypical strictosidine synthase that plays crucial roles in regulating anther development and pollen wall formation in rice.

Terahertz Spectroscopic Diagnosis of Myelin Deficit Brain in Mice and Rhesus Monkey with Chemometric Techniques

While myelin deficit of the central nervous system leads to several severe diseases, the definitive diagnostic means are lacking. We proposed and performed terahertz time-domain spectroscopy (THz-TDS) combined with chemometric techniques to discriminate and evaluate the severity of myelin deficit in mouse and rhesus monkey brains. The THz refractive index and absorption coefficient of paraffin-embedded brain tissues from both normal and mutant dysmyelinating mice are shown. Principal component analysis of time-domain THz signal (PCA-tdTHz) and absorption-refractive index relation of THz spectrum identified myelin deficit without exogenous labeling or any pretreatment. Further, with the established PCA-tdTHz, we evaluated the severity of myelin deficit lesions in rhesus monkey brain induced by experimental autoimmune encephalomyelitis, which is the most-studied animal model of multiple sclerosis. The results well matched the pathological analysis, indicating that PCA-tdTHz is a quick, powerful, evolving tool for identification and evaluation myelin deficit in preclinical animals and potentially in para-clinical human biopsy.

Discrimination of transgenic soybean seeds by terahertz spectroscopy

Discrimination of genetically modified organisms is increasingly demanded by legislation and consumers worldwide. The feasibility of a non-destructive discrimination of glyphosate-resistant and conventional soybean seeds and their hybrid descendants was examined by terahertz time-domain spectroscopy system combined with chemometrics. Principal component analysis (PCA), least squares-support vector machines (LS-SVM) and PCA-back propagation neural network (PCA-BPNN) models with the first and second derivative and standard normal variate (SNV) transformation pre-treatments were applied to classify soybean seeds based on genotype. Results demonstrated clear differences among glyphosate-resistant, hybrid descendants and conventional non-transformed soybean seeds could easily be visualized with an excellent classification (accuracy was 88.33% in validation set) using the LS-SVM and the spectra with SNV pre-treatment. The results indicated that THz spectroscopy techniques together with chemometrics would be a promising technique to distinguish transgenic soybean seeds from non-transformed seeds with high efficiency and without any major sample preparation.