Combined laser-induced breakdown spectroscopy and hyperspectral imaging with machine learning for the classification and identification of rice geographical origin

Dai Y., Song C., Gao X., Chen A., Hao Z., Lin J.

In this work, LIBS technology combined with the LASSO–LSSVM regression model was used to improve the detection ability of minor elements in Al–Cu–Mg–Fe–Ni aluminum alloy.

Zhao S., Song W., Hou Z., Wang Z.

This study used LIBS and HSI combined with chemometrics to determine the ginseng samples based on plant species, geographical origin, and age.

Wang Y., Tan F.

Rice origin identification can provide brand protection for rice with geographical indications. Therefore, it is necessary to design a convenient and fast detection method to meet the demands of the market. Based on Raman spectroscopy, this study involved the extraction and classification of characteristic spectral peaks of rice grain samples of the same cultivar but different places of origin. Raman spectra were acquired from 80 samples of rice with four different places of origin (Longjing 31 cultivar), and spectral information was extracted for analysis. First, the rice spectra were pretreated using a baseline correction and range normalization. Second, from the 400−1600cm −1 and 2800−3200cm -1 spectral region starting from the first four principal components of the regression coefficients extracted from principal component analysis (PCA), further screening produced eight spectral peaks characteristic of the place of origin: 476 cm −1 , 867 cm −1 ,940 cm −1 , 1121 cm −1 , 1342 cm −1 , 1384 cm −1 , 1462 cm −1 , and 2914 cm −1 . These were also assigned to functional groups, revealing subtle differences in the nutritional content dependent on place of origin. Third, eight characteristic values extracted by PCA were used to establish a four-layer 8-9-6-4 (input-hidden-hidden-output) back propagation (BP) neural network structure as a rice-origin identification model. Finally, the model was used to train 80 rice samples in place-of-origin classification, and the average prediction accuracy of the cyclic test for the training samples reached 97.5 % after five epochs; for the other four epochs the accuracy ranged from 98.75%–96.25%. These results show that the model is feasible as a tool for the identification of rice types of the same variety and that it can effectively identify rice from different areas.

Guo L., Zhang D., Sun L., Yao S., Zhang L., Wang Z., Wang Q., Ding H., Lu Y., Hou Z., Wang Z.

Laser-induced breakdown spectroscopy (LIBS) has been widely studied due to its unique advantages such as remote sensing, real-time multi-elemental detection and none-to-little damage. With the efforts of researchers around the world, LIBS has been developed by leaps and bounds. Moreover, in recent years, more and more Chinese LIBS researchers have put tremendous energy in promoting LIBS applications. It is worth mentioning that the application of LIBS in a specific field has its special application background and technical difficulties, therefore it may develop in different stages. A review summarizing the current development status of LIBS in various fields would be helpful for the development of LIBS technology as well as its applications especially for Chinese LIBS community since most of the researchers in this field work in application. In the present work, we summarized the research status and latest progress of main research groups in coal, metallurgy, and water, etc. Based on the current research status, the challenges and opportunities of LIBS were evaluated, and suggestions were made to further promote LIBS applications.

Fu Y., Gu W., Hou Z., Muhammed S.A., Li T., Wang Y., Wang Z.

Relatively large measurement uncertainty severely hindered wide application for laser-induced breakdown spectroscopy (LIBS), therefore it is of great importance to understand the mechanism of signal uncertainty generation, including initiation and propagation. It has been found that the fluctuation of plasma morphology was the main reason for signal uncertainty. However, it still remains unclear what mechanism leads to laser-induced plasma morphology fluctuation. In the present work, we employed three fast-imaging cameras to capture three successive plasma images from a same laser-induced Titanium alloy plasma, which enables us to understand more clearly of the plasma evolution process especially for the early plasma evolution stage when plasma and surrounding gases interact drastically. Seen from the images, the plasma experienced an increasing morphological fluctuation as delay time increased, transforming from a “stable plasma” before the delay time of 100 ns to a “fluctuating plasma” after the delay time of 300 ns. Notably, the frontier part of plasma showed a significant downward motion from the delay time of 150 ns to 200 ns and crashed with the lower part of the plasma, making the plasma flatter and later even splitting the plasma into two parts, which was considered as a critical process for the transformation of “stable plasma” to “unstable plasma”. By calculating the correlation coefficient of plasma image pairs at successive delay times, it was found that the higher the similarity between two plasma at early stage, the more similar at later stage; this implied that the tiny plasma fluctuation earlier than the critical delay time (150–200 ns) was amplified, causing a large plasma fluctuation at the later stage as well as LIBS measurement uncertainty. The initiation of slight fluctuation was linked with Rayleigh-Taylor Instability (RTI) due to the drastic material interpenetration at the plasma-ambient gas interface at earlier stage (before 50 ns). That is, the uncertainty generation of LIBS was proposed as: plasma morphology fluctuation was inevitably trigged by RTI at the early stage and the tiny fluctuation was amplified by the back pressed downward process of plasma frontier material, leading to severe morphology fluctuation as well as LIBS signal uncertainty.

Sha M., Zhang D., Zhang Z., Wei J., Chen Y., Wang M., Liu J.

Wang W., Sun L., Wang G., Zhang P., Qi L., Zheng L., Dong W.

In the microanalysis of laser-induced breakdown spectroscopy, the influence of surface roughness on spectral stability and quantitative analysis capability was studied for the first time when the laser ablation crater diameter was approximately 10 μm.

Sampaio P.S., Castanho A., Almeida A.S., Oliveira J., Brites C.

One of the most important problems associated with the rice industry is the authenticity, mainly the identification of varieties by providing a reliable, fast, yet accurate method. To overcome these limitations, the development of fast and non-destructive methodologies for different rice type classification is, nowadays, a huge challenge for producers. The near-infrared (NIR) spectroscopy associated to principal component analysis (PCA), partial least squares-discriminant analysis (PLS-DA), and support vector machines (SVM) for discrimination and classification of rice varieties (Indica and Japonica) were explored after different spectra processing steps such as multiplicative scatter correction (MSC), first derivative and second derivative. The SVM model developed after the MSC processing procedure, showed a significant fitting accuracy (97%), cross-validation (93%) and prediction (91%). These data support the robustness of the model for efficient rice types classification. In terms of spectral analysis, the major differences between both rice types are present at range 7476–7095 cm−1, 7046 cm−1 and 4264–4153 cm−1, which can be used for its discrimination. This study showed that NIR spectroscopy associated to PLS-DA and SVM techniques allowed an efficient discrimination of rice samples, being considered as a suitable strategy for a competent system for fully automated classification and sorting of rice types grouping with a high level of accuracy, representing a valuable approach for discrimination and anti-fraud procedure for food control as well as in terms of security issues of any product.

Zhao S., Gao X., Chen A., Lin J.

This study investigates the spatial confinement effect on Pb measurements in soil by femtosecond laser-induced breakdown spectroscopy (fs-LIBS). Spatial confinement within a cylindrical cavity significantly enhanced the intensities of the Pb plasma emission spectrum and the enhancement increased with decreasing diameter of the cylindrical cavity. When the cavity diameter was increased from 3 to 6 mm, the spectral emission enhancement was more delayed and the spatial confinement effect was weakened. The limit of detection (LOD), coefficient of determination (R2), relative standard deviation (RSD), and root mean squared error of cross-validation (RMSECV) were 8.85 ± 0.16 mg/kg, 98.34%, 4.98%, and 0.45%, respectively in the 3 mm diameter cavity and 33.16 ± 1.45 mg/kg, 97.66%, 8.21%, and 0.54%, respectively, in the unconfined measurements. The cylindrical cavity improved the detection sensitivity (as evidenced by the LODs) and the detection accuracy (as evidenced by the RMSECV and RSD values) of fs-LIBS. Overall, the spatial confinement method promises to improve the analytical figures of merit of the fs-LIBS technology.

Ito V.C., Lacerda L.G.

Black rice is a variety of pigmented rice. It contains numerous nutritional and bioactive components, including essential amino acids, functional lipids, dietary fibre, vitamins, minerals, anthocyanins, phenolic compounds, γ-oryzanols, tocopherols, tocotrienols, phytosterols and phytic acid. There have been several studies of black rice due to its alleged beneficial health effects when consumed regularly. This review focuses on the historical aspects, chemical composition, and nutritional and functional properties of black rice. Furthermore, a discussion of the development of new foods and beverages with applications and processing technologies designed to improve their quality attributes. The nutritional value of black rice means that it has the potential to be used in the production of healthy foods and beverages, such as functional products and gluten-free cereals, thereby providing extra health benefits to consumers.

Zhang J., Li M., Pan T., Yao L., Chen J.

• Purity analysis of multi-grain rice seeds. • Rapid and non-destructive detection technique. • Visible and near-infrared spectroscopy. • Equidistant wavelength combination screening. • Wavelength step-by-step phase-out. Seed purity is a crucial indicator of seed breeding, production and circulation. The traditional purity analysis methods are based on the authenticity identification of single-seed, which are complex, time consuming and lowly efficient. Using visible and near-infrared (Vis-NIR) spectroscopy, a novel purity analysis method of multi-grain rice seeds was developed. The samples were mixed samples that the target variety (Y Liangyou 900) was contaminated by the other four varieties. The standard normal variate method was used for spectral pretreatment. The equidistant combination-partial least squares (EC-PLS) was adopted for large-range wavelength screening. The wavelength step-by-step phase-out PLS (WSP-PLS) was further used to eliminate interference wavelengths and improve predicted effect. In vis-short NIR region, the selected WSP-PLS model included 19 non-equidistant wavelengths. The root mean square errors and correlation coefficients for prediction in modeling (RMSEP M , R P,M ) reached 0.115, 0.920, respectively. In validation, the root mean square errors and correlation coefficients for prediction (RMSEP V , R P,V ) were 0.152, 0.845, respectively. In the long NIR region, the selected model included 24 non-equidistant wavelengths, the RMSEP M , R P,M were 0.103, 0.930 and the RMSEP V , R P,V were 0.129, 0.894, respectively. Results showed that the predicted and actual purity values had high correlation, and the wavelength model complexity was low. The proposed Vis-NIR detection method has the feasibility to analyse the purity of multi-grain rice seeds, which is a rapid, non-destructive and promising analytical technique. As a simple and efficient wavelength selection method, WSP-PLS is expected to be used for more analysis objects.

Chen J., Li M., Pan T., Pang L., Yao L., Zhang J.

The rapid and non-destructive discriminant analysis of rice seeds has great significance for large-scale agriculture. Using near-infrared (NIR) diffuse-reflectance spectroscopy with partial least squares-discriminant analysis (PLS-DA), a variety identification method of multi-grain rice seeds was developed. The equidistant combination method was adopted for large-range wavelength screening. A step-by-step phase-out method was proposed to eliminate interference wavelengths and improve the predicted effect. The optimal wavelength model was a combination of 54 wavelengths within 808-974 nm of the short-NIR region. One type of pure rice variety (Y Liangyou 900) was used for identification (negative). Positive samples included the other four pure varieties and contamination of Y Liangyou 900 by the above four varieties. The recognition-accuracy rates for positive, negative and total validation samples reached 93.1%, 95.1%, and 94.3%, respectively. In the long-NIR region, the local optimal wavelength model was a combination of 49 wavelengths within 1188-1650 nm, and the recognition-accuracy rates for positive, negative and total validation samples were 90.3%, 94.1%, and 92.5%, respectively. Results confirmed the feasibility of NIR spectroscopy for variety identification of multi-grain rice seeds. The proposed two discrete-wavelength models located in the short- and long-NIR regions can provide valuable reference to a dedicated spectrometer.

Ríos-Reina R., Callejón R.M., Savorani F., Amigo J.M., Cocchi M.

Spain is one of the major producers of high-quality wine vinegars having three protected designations of origin (a.k.a. PDOs): "Vinagre de Jerez", "Vinagre de Condado de Huelva" and "Vinagre de Montilla-Moriles". Their high prices due to their high quality and their high production costs explain the need for developing an adequate quality control technique and the interest in extensive characterization in order to capture the identity of each denomination. In this framework, methodologies based on non-targeted techniques, such as spectroscopies, are becoming popular in food authentication. Thus, for improving vinegar quality assessment, fusion of data blocks obtained from the same samples but different analytical techniques could be a good strategy, since the quantity and quality of sample knowledge could be enhanced providing new insights into the differentiation of vinegars. Therefore, the aim of this manuscript is the development of a multi-platform methodology and a model able to classify the Spanish wine vinegar PDOs. Sixty-five PDO wine vinegars were analyzed by four spectroscopic techniques: Fourier-transform mid-infrared spectroscopy (MIR), near infrared spectroscopy (NIR), multidimensional fluorescence spectroscopy (EEM) and proton nuclear magnetic resonance (1H-NMR). Two different data fusion strategies were evaluated: Mid-level data fusion with different preprocessing, and Common Component and Specific Weights analysis multiblock method. Exploratory and classification analysis on the data from individual techniques were also performed and compared with data fusion models. The data fusion models improved the classification, providing a more efficient differentiation, than the models based on single methods, and supporting the approach to combine these methods to achieve synergies for an optimized PDO differentiation.

Wu D., Meng L., Yang L., Wang J., Fu X., Du X., Li S., He Y., Huang L.

An effective and rapid way to detect thiophanate-methyl residue on mulberry fruit is important for providing consumers with quality and safe of mulberry fruit. Chemical methods are complex, time-consuming, and costly, and can result in sample contamination. Rapid detection of thiophanate-methyl residue on mulberry fruit was studied using laser-induced breakdown spectroscopy (LIBS) and hyperspectral imaging (HSI) techniques. Principal component analysis (PCA) and partial least square regression (PLSR) were used to qualitatively and quantitatively analyze the data obtained by using LIBS and HSI on mulberry fruit samples with different thiophanate-methyl residues. The competitive adaptive reweighted sampling algorithm was used to select optimal variables. The results of model calibration were compared. The best result was given by the PLSR model that used the optimal preprocessed LIBS–HSI variables, with a correlation coefficient of 0.921 for the prediction set. The results of this research confirmed the feasibility of using LIBS and HSI for the rapid detection of thiophanate-methyl residue on mulberry fruit.

Chukwu S.C., Rafii M.Y., Ramlee S.I., Ismail S.I., Oladosu Y., Okporie E., Onyishi G., Utobo E., Ekwu L., Swaray S., Jalloh M.

AbstractMarker-assisted selection and gene pyramiding are very important breeding strategies for conferring broad spectrum and durable resistance against diseases causing yield loss in rice. One su...

Li H., Sun H., Gao X.

Hazrul A.F., Raja Ibrahim R.K., Duralim M.

Abstract This research employed laser-induced breakdown spectroscopy (LIBS) technique to analyse elements in various rice samples including white rice, fragrant rice, basmati rice, and glutinous rice. The LIBS parameters including laser energy and integration time were optimised to obtain the optimised LIBS spectra ranging from 30 40, and 50 mJ and 10, 20, and 30 ms, respectively. The optimised LIBS parameters used in this study were determined at 40 mJ laser energy and 20 ms integration time. From the obtained LIBS spectrum, the elemental composition in rice were identified using National Institute of Standards and Technology (NIST) database. Principal component analysis (PCA), was used for further analysis to discriminate between each type of rice. The results from the PCA score were able to discriminate white and fragrant rice. However, for basmati and glutinous rice, the data points were overlapping with each other.

Lopes T., Cavaco R., Capela D., Dias F., Teixeira J., Monteiro C.S., Lima A., Guimarães D., Jorge P.A., Silva N.A.

Sun X., Zhou X., Liu C., Li C., Zhang S., Zheng D.

Yang Y., Zhang L., Qu X., Zhang W., Shi J., Xu X.

Alemayhu A.S., Ji R., Abdalla A.N., Bian H.

Cui M., Xiong S., Yang N., Wang Y., Wang Z., Luo M., Yao C., Deguchi Y.

Hao Z., Liu K., Lian Q., Song W., Hou Z., Zhang R., Wang Q., Sun C., Li X., Wang Z.

Laser-induced breakdown spectroscopy (LIBS) is a spectroscopic analytic technique with great application potential because of its unique advantages for online/in-situ detection. However, due to the spatially inhomogeneity and drastically temporal varying nature of its emission source, the laser-induced plasma, it is difficult to find or hard to generate an appropriate spatiotemporal window for high repeatable signal collection with lower matrix effects. The quantification results of traditional physical principle based calibration model are unsatisfactory since these models were not able to compensate for complicate matrix effects as well as signal fluctuation. Machine learning is an emerging approach, which can intelligently correlated the complex LIBS spectral data with its qualitative or/and quantitative composition by establishing multivariate regression models with greater potential to reduce the impacts of signal fluctuation and matrix effects, therefore achieving relatively better qualitative and quantitative performance. In this review, the progress of machine learning application in LIBS is summarized from two main aspects: i) Pre-processing data for machine learning model, including spectral selection, variable reconstruction, and denoising to improve qualitative/quantitative performance; ii) Machine learning methods for better quantification performance with reduction of the impact of matrix effect as well as LIBS spectra fluctuations. The review also points out the issues that researchers need to address in their future research on improving the performance of LIBS analysis using machine learning algorithms, such as restrictions on training data, the disconnect between physical principles and algorithms, the low generalization ability and massive data processing ability of the model.

Xie A., Zhang Y., Wu H., Chen M.

The process of meat postmortem aging is a complex one, in which improved tenderness and aroma coincide with negative effects such as water loss and microbial growth. Determining the optimal postmortem storage time for meat is crucial but also challenging. A new visual monitoring technique based on hyperspectral imaging (HSI) has been proposed to monitor pork aging progress. M. longissimus thoracis from 15 pigs were stored at 4 °C for 12 days while quality indexes and HSI spectra were measured daily. Based on changes in physical and chemical indicators, 100 out of the 180 pieces of meat were selected and classified into rigor mortis, aged, and spoilt meat. Discrete wavelet transform (DWT) technology was used to improve the accuracy of classification. DWT separated approximate and detailed signals from the spectrum, resulting in a significant increase in classification speed and precision. The support vector machine (SVM) model with 70 band spectra achieved remarkable classification accuracy of 97.06%. The study findings revealed that the aging and microbial spoilage process started at the edges of the meat, with varying rates from one pig to another. Using HSI and visualization techniques, it was possible to evaluate and portray the postmortem aging progress and edible safety of pork during storage. This technology has the potential to aid the meat industry in making informed decisions on the optimal storage and cooking times that would preserve the quality of the meat and ensure its safety for consumption.

Lopes T., Capela D., Guimarães D., Ferreira M.F., Jorge P.A., Silva N.A.

AbstractMultimodal spectral imaging offers a unique approach to the enhancement of the analytical capabilities of standalone spectroscopy techniques by combining information gathered from distinct sources. In this manuscript, we explore such opportunities by focusing on two well-known spectral imaging techniques, namely laser-induced breakdown spectroscopy, and hyperspectral imaging, and explore the opportunities of collaborative sensing for a case study involving mineral identification. In specific, the work builds upon two distinct approaches: a traditional sensor fusion, where we strive to increase the information gathered by including information from the two modalities; and a knowledge distillation approach, where the Laser Induced Breakdown spectroscopy is used as an autonomous supervisor for hyperspectral imaging. Our results show the potential of both approaches in enhancing the performance over a single modality sensing system, highlighting, in particular, the advantages of the knowledge distillation framework in maximizing the potential benefits of using multiple techniques to build more interpretable models and paving for industrial applications.

Patriarca M., Barlow N., Cross A., Hill S., Robson A., Tyson J.

This review discusses developments in elemental mass spectrometry, atomic absorption, emission and fluorescence, XRF and LIBS, as applied to the analysis of specimens of clinical interest, foods and beverages. Sample preparation procedures and quality assurance are also included.

Ahmed Z., D P., Yadav D.K.

Li X., Wang D., Yu L., Ma F., Wang X., Pérez‐Marín D., Li P., Zhang L.

AbstractStable isotopes, multi‐elements, metabolic profiles, and integrated spectroscopic fingerprints are priority options for food geographical origin traceability. However, til now, it is still hard to detect adteration with the same one from other geographic origins, which is harder than geographical origin traceability. In this study, partial least square discriminant analysis was employed to build a classification model to discriminate the domestic and imported soybeans after variable selection by uninformative variable elimination using near infrared hyperspectral imaging. As a result, this model could completely discriminate domestic and imported soybeans. Moreover, the developed model was used to detect the adulterated domestic soybean was adulterated with 13.3%, 20.0%, 26.7%, and 33.3% of imported soybean. When the skewness value was less than 0.76 and kurtosis value was less than 1.57 of a sample, the sample was considered as the adulterated. The results indicated that the domestic soybeans adulterated with 20.0%, 26.7%, and 33.3% of imported soybeans were successfully identified. This method could not only identify origin traceability but also detect adulteration of soybeans, which will be beneficial to guarantee the quality and safety of soybean.

Shi S., Tang Z., Ma Y., Cao C., Jiang Y.