Shortwave Infrared Hyperspectral Imaging Research Articles

Prediction and Visualization of Total Volatile Basic Nitrogen in Yellow Croaker (Larimichthys polyactis) Using Shortwave Infrared Hyperspectral Imaging.

In the present investigation, we have devised a hyperspectral imaging (HSI) apparatus to assess the chemical characteristics and freshness of the yellow croaker (Larimichthys polyactis) throughout its storage period. This system operates within the shortwave infrared spectrum, specifically ranging from 900 to 1700 nm. A variety of spectral pre-processing techniques, including standard normal variate (SNV), multiple scatter correction, and Savitzky-Golay (SG) derivatives, were employed to augment the predictive accuracy of total volatile basic nitrogen (TVB-N)-which serves as a critical freshness parameter. Among the assessed methodologies, SG-1 pre-processing demonstrated superior predictive accuracy (Rp2 = 0.8166). Furthermore, this investigation visualized freshness indicators as concentration images to elucidate the spatial distribution of TVB-N across the samples. These results indicate that HSI, in conjunction with chemometric analysis, constitutes an efficacious instrument for the surveillance of quality and safety in yellow croakers during its storage phase. Moreover, this methodology guarantees the freshness and safety of seafood products within the aquatic food sector.

Innovative strategies for protein content determination in dried laver (Porphyra spp.): Evaluation of preprocessing methods and machine learning algorithms through short-wave infrared imaging

In this study, we explored the application of Short-Wave Infrared (SWIR) hyperspectral imaging combined with Competitive Adaptive Reweighted Sampling (CARS) and advanced regression models for the non-destructive assessment of protein content in dried laver. Utilizing a spectral range of 900–1700 nm, we aimed to refine the quality control process by selecting informative wavelengths through CARS and applying various preprocessing techniques (standard normal variate [SNV], Savitzky-Golay filtering [SG], Orthogonal Signal Correction [OSC], and StandardScaler [SS]) to enhance the model's accuracy. The SNV-OSC-StandardScaler- Support vector regression (SVR) model trained on CARS-selected wavelengths significantly outperformed the other configurations, achieving a prediction determination coefficient (Rp2) of 0.9673, root mean square error of prediction of 0.4043, and residual predictive deviation of 5.533. These results highlight SWIR hyperspectral imaging's potential as a rapid and precise tool for assessing dried laver quality, aiding food industry quality control and dried laver market growth.

Evaluation of Nutritional Values of Edible Algal Species Using a Shortwave Infrared Hyperspectral Imaging and Machine Learning Technique.

In recent years, the growing demand for algae in Western countries is due to their richness in nutrients and bioactive compounds, and their use as ingredients for foods, cosmetics, nutraceuticals, fertilizers, biofuels,, etc. Evaluation of the qualitative characteristics of algae involves assessing their physicochemical and nutritional components to determine their suitability for specific end uses, but this assessment is generally performed using destructive, expensive, and time-consuming traditional chemical analyses, and requires sample preparation. The hyperspectral imaging (HSI) technique has been successfully applied in food quality assessment and control and has the potential to overcome the limitations of traditional biochemical methods. In this study, the nutritional profile (proteins, lipids, and fibers) of seventeen edible macro- and microalgae species widely grown throughout the world were investigated using traditional methods. Moreover, a shortwave infrared (SWIR) hyperspectral imaging device and artificial neural network (ANN) algorithms were used to develop multi-species models for proteins, lipids, and fibers. The predictive power of the models was characterized by different metrics, which showed very high predictive performances for all nutritional parameters (for example, R2 = 0.9952, 0.9767, 0.9828 for proteins, lipids, and fibers, respectively). Our results demonstrated the ability of SWIR hyperspectral imaging coupled with ANN algorithms in quantifying biomolecules in algal species in a fast and sustainable way.

Establishment and comparison of in situ detection models for foodborne pathogen contamination on mutton based on SWIR-HSI.

Rapid and accurate detection of food-borne pathogens on mutton is of great significance to ensure the safety of mutton and its products and the health of consumers. The feasibility of short-wave infrared hyperspectral imaging (SWIR-HSI) in detecting the contamination status and species of Escherichia coli (EC), Staphylococcus aureus (SA) and Salmonella typhimurium (ST) contaminated on mutton was explored. The hyperspectral images of uncontaminated and contaminated mutton samples with different concentrations (108, 107, 106, 105, 104, 103 and 102 CFU/mL) of EC, SA and ST were acquired. The one dimensional convolutional neural network (1D-CNN) model was constructed and the influence of structure hyperparameters on the model was explored. The effects of different spectral preprocessing methods on partial least squares-discriminant analysis (PLS-DA), support vector machine (SVM) and 1D-CNN models were discussed. In addition, the feasibility of using the characteristic wavelength to establish simplified models was explored. The best full band model was the 1D-CNN model with the convolution kernels number of (64, 16) and the activation function of tanh established by the original spectra, and its accuracy of training set, test set and external validation set were 100.00, 92.86 and 97.62%, respectively. The optimal simplified model was genetic algorithm optimization support vector machine (GA-SVM). For discriminating the pathogen species, the accuracies of SVM models established by full band spectra preprocessed by 2D and all 1D-CNN models with the convolution kernel number of (32, 16) and the activation function of tanh were 100.00%. In addition, the accuracies of all simplified models were 100.00% except for the 1D-CNN models. Considering the complexity of features and model calculation, the 1D-CNN models established by original spectra were the optimal models for pathogenic bacteria contamination status and species. The simplified models provide basis for developing multispectral detection instruments. The results proved that SWIR-HSI combined with machine learning and deep learning could accurately detect the foodborne pathogen contamination on mutton, and the performance of deep learning models were better than that of machine learning. This study can promote the application of HSI technology in the detection of foodborne pathogens on meat.

Non-destructive identification of Pseudostellaria heterophylla from different geographical origins by Vis/NIR and SWIR hyperspectral imaging techniques.

The composition of Pseudostellaria heterophylla (Tai-Zi-Shen, TZS) is greatly influenced by the growing area of the plants, making it significant to distinguish the origins of TZS. However, traditional methods for TZS origin identification are time-consuming, laborious, and destructive. To address this, two or three TZS accessions were selected from four different regions of China, with each of these resources including distinct quality grades of TZS samples. The visible near-infrared (Vis/NIR) and short-wave infrared (SWIR) hyperspectral information from these samples were then collected. Fast and high-precision methods to identify the origins of TZS were developed by combining various preprocessing algorithms, feature band extraction algorithms (CARS and SPA), traditional two-stage machine learning classifiers (PLS-DA, SVM, and RF), and an end-to-end deep learning classifier (DCNN). Specifically, SWIR hyperspectral information outperformed Vis/NIR hyperspectral information in detecting geographic origins of TZS. The SPA algorithm proved particularly effective in extracting SWIR information that was highly correlated with the origins of TZS. The corresponding FD-SPA-SVM model reduced the number of bands by 77.2% and improved the model accuracy from 97.6% to 98.1% compared to the full-band FD-SVM model. Overall, two sets of fast and high-precision models, SWIR-FD-SPA-SVM and SWIR-FD-DCNN, were established, achieving accuracies of 98.1% and 98.7% respectively. This work provides a potentially efficient alternative for rapidly detecting the origins of TZS during actual production.

An improved DCGAN model: Data augmentation of hyperspectral image for identification pesticide residues of Hami melon

The increasing concern over pesticide residues on Hami melon is due to the unregulated use of pesticides, which poses a potential food safety hazard. Thus, it is urgent to propose a method for the rapid and nondestructive detection of pesticide residues on the Hami melon. This study used short-wave infrared hyperspectral imaging (SWIR-HSI) to identify pesticide residues on the Hami melon. The data augmentation method based on improved deep convolutional generative adversarial networks (DCGAN) was proposed to expand Hami melon's spectral data with different pesticide residues. To determine the optimal training epoch, the 1-nearest neighbor (1-NN) classifier was used to evaluate the quality of the generated spectra. The effectiveness of the improved DCGAN was verified by three commonly used classifiers, including the decision tree (DT), random forest (RF), and support vector machine (SVM). The results showed that the performance of all three classifiers was improved to varying degrees by the improved DCGAN. The DT, RF, and SVM accuracy was improved by 13.13%, 7.50%, and 11.25%, respectively. Moreover, the SVM model achieved the highest accuracy of 93.13%. These findings indicated that the combination of SWIR-HSI and the improved DCGAN-based data augmentation method has good promise for detecting pesticide residues on Hami melon.

Spatio-temporal distribution patterns and quantitative detection of aflatoxin B1 and total aflatoxin in peanut kernels explored by short-wave infrared hyperspectral imaging.

Aflatoxin contamination in peanut kernels seriously harms the health of humans and causes significant economic losses. Rapid and accurate detection of aflatoxin is necessary to minimize its contamination. However, current detection methods are time-consuming, expensive and destructive to samples. Therefore, short-wave infrared (SWIR) hyperspectral imaging coupled with multivariate statistical analysis was used to investigate the spatio-temporal distribution patterns of aflatoxin, and quantitatively detect the aflatoxin B1 (AFB1) and total aflatoxin in peanut kernels. In addition, Aspergillus flavus contamination was identified to prevent the production of aflatoxin. The result of validation set demonstrated that SWIR hyperspectral imaging could predict the contents of the AFB1 and total aflatoxin accurately, with residual prediction deviation values of 2.7959 and 2.7274, and limits of detection of 29.3722 and 45.7429μg/kg, respectively. This study presents a novel method for the quantitative detection of aflatoxin and offers an early warning system for its potential application.

Determination of Freshness of Mackerel (Scomber japonicus) Using Shortwave Infrared Hyperspectral Imaging.

Shortwave infrared (SWIR) hyperspectral imaging was applied to classify the freshness of mackerels. Total volatile basic nitrogen (TVB-N) and acid values, as chemical compounds related to the freshness of mackerels, were also analyzed to develop a prediction model of freshness by combining them with hyperspectral data. Fresh mackerels were divided into three groups according to storage periods (0, 24, and 48 h), and hyperspectral data were collected from the eyes and whole body, separately. The optimized classification accuracies were 81.68% using raw data from eyes and 90.14% using body data by multiple scatter correction (MSC) pretreatment. The prediction accuracy of TVB-N was 90.76%, and the acid value was 83.76%. These results indicate that hyperspectral imaging, as a nondestructive method, can be used to verify the freshness of mackerels and predict the chemical compounds related to the freshness.

Comparison of a portable Vis-NIR hyperspectral imaging and a snapscan SWIR hyperspectral imaging for evaluation of meat authenticity.

The performance of visible-near infrared hyperspectral imaging (Vis-NIR-HSI) (400-1000nm) and shortwave infrared hyperspectral imaging (SWIR-HSI) (1116-1670nm) combined with different classification and regression (linear and non-linear) multivariate methods were assessed for meat authentication. In Vis-NIR-HSI, total accuracies in the prediction set for SVM and ANN-BPN (the best classification models) were 96 and 94% surpassing the performance of SWIR-HSI with 88 and 89% accuracy, respectively. In Vis-NIR-HSI, the best-obtained coefficient of determinations for the prediction set (R2p) were 0.99, 0.88, and 0.99 with root mean square error in prediction (RMSEP) of 9, 24 and 4 (%w/w) for pork in beef, pork in lamb and pork in chicken, respectively. In SWIR-HSI, the best-obtained R2p were 0.86, 0.77, and 0.89 with RMSEP of 16, 23 and 15 (%w/w) for pork in beef, pork in lamb and pork in chicken, respectively. The results ascertain that Vis-NIR-HSI coupled with multivariate data analysis has better performance rather than SWIR-HIS.

Detecting different pesticide residues on Hami melon surface using hyperspectral imaging combined with 1D-CNN and information fusion.

Efficient, rapid, and non-destructive detection of pesticide residues in fruits and vegetables is essential for food safety. The visible/near infrared (VNIR) and short-wave infrared (SWIR) hyperspectral imaging (HSI) systems were used to detect different types of pesticide residues on the surface of Hami melon. Taking four pesticides commonly used in Hami melon as the object, the effectiveness of single-band spectral range and information fusion in the classification of different pesticides was compared. The results showed that the classification effect of pesticide residues was better by using the spectral range after information fusion. Then, a custom multi-branch one-dimensional convolutional neural network (1D-CNN) model with the attention mechanism was proposed and compared with the traditional machine learning classification model K-nearest neighbor (KNN) algorithm and random forest (RF). The traditional machine learning classification model accuracy of both models was over 80.00%. However, the classification results using the proposed 1D-CNN were more satisfactory. After the full spectrum data was fused, it was input into the 1D-CNN model, and its accuracy, precision, recall, and F1-score value were 94.00%, 94.06%, 94.00%, and 0.9396, respectively. This study showed that both VNIR and SWIR hyperspectral imaging combined with a classification model could non-destructively detect different pesticide residues on the surface of Hami melon. The classification result using the SWIR spectrum was better than that using the VNIR spectrum, and the classification result using the information fusion spectrum was better than that using SWIR. This study can provide a valuable reference for the non-destructive detection of pesticide residues on the surface of other large, thick-skinned fruits.

Non-Destructive Detection of Different Pesticide Residues on the Surface of Hami Melon Classification Based on tHBA-ELM Algorithm and SWIR Hyperspectral Imaging.

In the field of safety detection of fruits and vegetables, how to conduct non-destructive detection of pesticide residues is still a pressing problem to be solved. In response to the high cost and destructive nature of existing chemical detection methods, this study explored the potential of identifying different pesticide residues on Hami melon by short-wave infrared (SWIR) (spectral range of 1000-2500 nm) hyperspectral imaging (HSI) technology combined with machine learning. Firstly, the classification effects of classical classification models, namely extreme learning machine (ELM), support vector machine (SVM), and partial least squares discriminant analysis (PLS-DA) on pesticide residues on Hami melon were compared, ELM was selected as the benchmark model for subsequent optimization. Then, the effects of different preprocessing treatments on ELM were compared and analyzed to determine the most suitable spectral preprocessing treatment. The ELM model optimized by Honey Badger Algorithm (HBA) with adaptive t-distribution mutation strategy (tHBA-ELM) was proposed to improve the detection accuracy for the detection of pesticide residues on Hami melon. The primitive HBA algorithm was optimized by using adaptive t-distribution, which improved the structure of the population and increased the convergence speed. Compared the classification results of tHBA-ELM with HBA-ELM and ELM model optimized by genetic algorithm (GA-ELM), the tHBA-ELM model can accurately identify whether there were pesticide residues and different types of pesticides. The accuracy, precision, sensitivity, and F1-score of the test set was 93.50%, 93.73%, 93.50%, and 0.9355, respectively. Metaheuristic optimization algorithms can improve the classification performance of classical machine learning classification models. Among all the models, the performance of tHBA-ELM was satisfactory. The results indicated that SWIR-HSI coupled with tHBA-ELM can be used for the non-destructive detection of pesticide residues on Hami melon, which provided the theoretical basis and technical reference for the detection of pesticide residues in other fruits and vegetables.

Non-destructive quality prediction of domestic, commercial red pepper powder using hyperspectral imaging

We analyzed the major quality characteristics of red pepper powders from various regions and predicted these characteristics nondestructively using shortwave infrared hyperspectral imaging (HSI) technology. We conducted partial least squares regression analysis on 70% (n=71) of the acquired hyperspectral data of the red pepper powders to examine the major quality characteristics. Rc2 values of >0.8 were obtained for the ASTA color value (0.9263) and capsaicinoid content (0.8310). The developed quality prediction model was validated using the remaining 30% (n=35) of the hyperspectral data; the highest accuracy was achieved for the ASTA color value (Rp2=0.8488), and similar validity levels were achieved for the capsaicinoid and moisture contents. To increase the accuracy of the quality prediction model, we conducted spectrum preprocessing using SNV, MSC, SG-1, and SG-2, and the model’s accuracy was verified. The results indicated that the accuracy of the model was most significantly improved by the MSC method, and the prediction accuracy for the ASTA color value was the highest for all the spectrum preprocessing methods. Our findings suggest that the quality characteristics of red pepper powders, even powders that do not conform to specific variables such as particle size and moisture content, can be predicted via HSI.

An Application and Technology of SWIR Hyperspectral Image for Inconspicuous Textile Pattern Analysis

This study applied short-wave infrared (SWIR) hyperspectral imaging technology to analyze the textile pattern used in the Jeogori of Baekdamsa Temple. First introduced in 1748, the Jeogori is a very important relic in the study of Korean traditional costume. The garment w as designated as a national treasure in 1993, and the pattern in its yellow silk has been well established. However, obtaining the pattern information of its reddish purple decoration has proven to be quite challenging. In contrast to yellow, reddish purple is a color that is difficult for a camera to recognize; thus, analyzing patterns in this color using only high-definition digital or infrared photography is difficult. In this work, SWIR hyperspectral imaging technology, which has recently been used in investigations of cultural heritage sites, was applied to identify the textile pattern on the Jeogori of Baekdamsa Temple. The technology successfully identified the patterns of a Wan-character, dragon, and phoenix. This type of textile pattern was identified in Korea from the end of the 17th century to the early-to-mid-18th century. This study is meaningful because it not only provides a detailed image of the textile pattern on the Jeogori of Baekdamsa Temple, which has not been previously achieved, but also proposes a new strategy based on hyperspectral imaging technology for studying the cultural heritage of textiles.

Shortwave Infrared Hyperspectral Imaging for the Determination and Visualization of Chemical Contents of Wheat and Tuber Flour

Understanding the physicochemical properties of flour in food preparation is important to determine the appropriate food utilization and processing. Some crops are processed into flour to improve their shelf life and extend their applications in food preparation. This study employed shortwave infrared hyperspectral imaging (SWIR HSI) coupled with multivariate analyses to determine wheat's protein, starch, amylose, glucose, and moisture compositions and several tuber flours. Tubers used were arrowroot, Canna edulis, modified cassava flour, taro, and sweet potato (purple, yellow, and white color). Hyperspectral images of all flour samples were captured using the SWIR HSI system at the wavelength range of 895–2504 nm in reflectance mode. The extracted spectral data were then processed and analyzed using partial least square regression (PLSR). Normalization (mean, max, and range), multiple scatter correction, standard normal variate, first and second Savitzky–Golay derivatives, and smoothing spectral pre-processing were applied to reduce scattering noise resulting from the HSI system. The PLSR models predicted the chemical concentrations of all samples with coefficients of determination of 0.85-0.97, 0.83-0.96, and 0.85-0.96 for calibration, validation, and prediction, respectively. Moreover, the models resulted in standard errors of 0.61-27.26, 0.63-27.71, and 0.63-29.14 for calibration, validation, and prediction. The concentration and distribution of protein, starch, amylose, glucose, and moisture in the flour samples were visualized by chemical imaging. This paper confirmed the potential of HSI for the rapid interpretation of chemical contents in different flour samples.

Shortwave infrared single-pixel spectral imaging based on a GSST phase-change metasurface.

Shortwave infrared (SWIR) spectral imaging obtains spectral fingerprints corresponding to overtones of molecular vibrations invisible to conventional silicon-based imagers. However, SWIR imaging is challenged by the excessive cost of detectors. Single-pixel imaging based on compressive sensing can alleviate the problem but meanwhile presents new difficulties in spectral modulations, which are prerequisite in compressive sampling. In this work, we theoretically propose a SWIR single-pixel spectral imaging system with spectral modulations based on a Ge2Sb2Se4Te1 (GSST) phase-change metasurface. The transmittance spectra of the phase-change metasurface are tuned through wavelength shifts of multipole resonances by varying crystallinities of GSST, validated by the multipole decompositions and electromagnetic field distributions. The spectral modulations constituted by the transmittance spectra corresponding to the 11 phases of GSST are sufficient for the compressive sampling on the spectral domain of SWIR hyperspectral images, indicated by the reconstruction in false color and point spectra. Moreover, the feasibility of optimization on phase-change metasurface via coherence minimization is demonstrated through the designing of the GSST pillar height. The concept of spectral modulation with phase-change metasurface overcomes the static limitation in conventional modulators, whose integratable and reconfigurable features may pave the way for high-efficient, low-cost, and miniaturized computational imaging based on nanophotonics.

Detection of Early Bruises in Honey Peaches Using Shortwave Infrared Hyperspectral Imaging

Honey peaches can bruise during harvesting, handling, storage, transportation, and distribution. In this study, the spectral range used was 400–1100 nm, and we extracted the RGB and HSI color space characteristics of the images. After principal component analysis (PCA) of the original data, the gray histogram features of the PC1 images were extracted. Partial least squares qualitative discriminant analysis (PLS-DA) and extreme learning machine (ELM) discriminant models were established. Among the 38 color features, the PLS-DA and ELM models had a high rate of misclassification, and the best classification accuracy was 74.29%. When extracting the spectral information of the bruised sample to build the model, the highest classification accuracy was 92.86% for the 176 characteristic wavelength points of the full band. In contrast, only 40 wavelength bands were used after selecting the genetic algorithm’s valid information. The classification accuracy of the PLS-DA model was 100%, which is because the softening and browning of the peach was not apparent after early bruising. However, the changes in the tissue’s thermal properties caused by internal defects are expressed in the internal spectrum. Therefore, the shortwave NIR hyperspectral imaging technique’s spectral information can detect the early bruising of peaches.

Comparative Performance of NIR-Hyperspectral Imaging Systems

Near-infrared spectroscopy (NIRS) allows for the rapid estimation of a wide range of wood properties. Typically, NIRS studies on wood have utilized benchtop spectrometers, but efforts to utilize NIR hyperspectral imaging to examine wood and wood products have increased. Compared to benchtop NIR systems, hyperspectral imaging has several advantages (speed, visualization of spatial variability), but the data typically have a lower signal-to-noise ratio as well as fewer wavelengths saved; thus, hyperspectral imaging systems have a larger spectral sampling interval (SSI). Furthermore, the SSI and wavelength range varies considerably among different HSI cameras. NIR-HSI systems based on indium gallium arsenide (InGaAs) detectors have a wavelength range typically from 900 to 1700 nm, while short-wave infrared hyperspectral imaging (SWIR-HSI) systems based on mercury cadmium telluride (MCT) detectors have the ‘full’ NIR wavelength range from 1000 to 2500 nm. These factors may influence the performance of wood property calibrations. We compared one NIR-HSI (900–1700 nm) and three SWIR-HSI (1000–2500 nm) commercially available cameras with an NIRS benchtop spectrometer (1100–2500 nm). The performance of specific gravity (SG) and stiffness (MOE) calibration models was compared with one-hundred Douglas-fir (Pseudotsuga menziesii) samples. The limited wavelength range of an NIR-HSI camera provided the best models for MOE, whereas the NIR-HSI and two SWIR-HSI cameras provided similar SG results. SWIR-HSI models heavily favored wavelengths greater than 1900 nm.

Recycling-oriented characterization of PET waste stream by SWIR hyperspectral imaging and variable selection methods

The proposed study was carried out to develop a fast and efficient strategy for plastic waste sensor-based sorting in recycling plants, based on hyperspectral imaging (HSI), combined with variable selection methods, to produce a high-quality recycled polyethylene terephthalate (PET) flakes stream. Variable selection techniques were applied in order to identify a limited number of spectral bands useful to recognize the presence of other plastic materials, considered as contaminant, inside a stream of recycled PET flakes, reducing processing time as requested by sorting online applications. Post-consumer plastic samples were acquired by HSI device working in the short-wave infrared (SWIR) range (1000 - 2500 nm). As a first step, the hypercubes were processed applying chemometric logics to build a partial least squares discriminant analysis (PLSDA) classification model using the full investigated spectral range, able to identify PET and contaminant classes. As a second step, two different variable selection methods were then applied, i.e., interval PLSDA (I-PLSDA) and variable importance in projection (VIP) scores, in order to identify a limited number of spectral bands useful to recognize the two classes and to evaluate the best method, showing efficiency values close to those obtained by the full spectrum model. The best result was achieved by the VIP score method with an average efficiency value of 0.98. The obtained results suggested that the variables selection method can represent a powerful approach for the sensor-based sorting-online, decreasing the amount of data to be processed and thus enabling faster recognition compared to the full spectrum model.

Spatio-temporal patterns of Aspergillus flavus infection and aflatoxin B1 biosynthesis on maize kernels probed by SWIR hyperspectral imaging and synchrotron FTIR microspectroscopy

The dynamics mechanisms regulating the growth and AFB1 production of Aspergillus flavus during its interactions with maize kernels remain unclear. In this study, shortwave infrared hyperspectral imaging (SWIR-HSI) and synchrotron radiation Fourier transform infrared (SR-FTIR) microspectroscopy were combined to investigate chemical and spatial–temporal changes in incremental damaged maize kernels induced by A. flavus infection at macroscopic and microscopic levels. SWIR-HSI was employed to extract spectral information of A. flavus growth and quantitatively detect AFB1 levels. Satisfactory full-spectrum models and simplified multispectral models were obtained respectively by partial least squares regression (PLSR) for three types of samples. Furthermore, SR-FTIR microspectroscopy coupled with two-dimensional correlation spectroscopy (2DCOS) was utilized to reveal the possible sequence of dynamic changes of nutrient loss and trace AFB1 in maize kernels. It exhibited new insights on how to quantify the spatio-temporal patterns of fungal infection and AFB1 accumulation on maize and provided theoretical basis for online sorting.

Accurate prediction of soluble solid content in dried Hami jujube using SWIR hyperspectral imaging with comparative analysis of models

Soluble solid content (SSC) is an important factor in determining jujube fruit’s nutritional and marketable values. In this study, the potential of using short-wave infrared (SWIR) hyperspectral imaging (HSI) technique with the spectral range of 1000–2500 nm coupled with multiple regression models for predicting SSC of dried Hami jujube was explored. The influence of three detection positions on the SSC prediction result was analyzed. Results indicated that the influence of detection position on the HSI data affected the prediction accuracy of SSC, and the stalk-side down was the optimal detection position. Then a custom convolutional neural network (CNN) model was constructed and compared with linear partial least squares regression (PLSR) and non-linear support vector machines regression (SVR). Competitive adaptive reweighted sampling (CARS), genetic algorithm (GA), and iteratively retains informative variables (IRIV) algorithms were used for selecting effective variables, respectively. Based on the full spectra and selected spectra, different models were built and compared to determine the best calibration strategy. Among all the models, the performance obtained by the CNN model based on full spectral was satisfactory. The determination coefficient of prediction (Rp2), root mean square error of prediction (RMSEP) and residual predictive deviation (RPD) were 0.857, 0.563 and 2.648, respectively. This research demonstrated that SWIR hyperspectral imaging combined with appropriate regression models could be applied to nondestructively predict the SSC of dried Hami jujubes. Furthermore, the CNN method had great potential for chemical compositions determination. This study can provide a valuable reference for the assessment of SSC in other dried fruits with small sizes.