Visible and near infrared (Vis-NIR) hyperspectral imaging was used for soluble solids content (SSC) monitoring and shelf life analysis of winter jujube at different maturity stages. Relationships ...between SSC of mid-ripe and ripe fruit and their spectral data were investigated using support vector regression (SVR) and partial least squares regression (PLSR) models. The best determination coefficient and residual predictive deviation of the external validation set were 0.837 and 2.47 for mid-ripe winter jujube, and 0.806 and 2.28 for ripe winter jujube, respectively. This implied that the more effective prediction performances for SSC emerged from SVR model using the effective wavelengths screened by successive projections algorithm (SPA). A significant correlation between the spatial distribution of SSC and maturity and shelf life was found in the prediction maps. Furthermore, shelf life was analyzed using a library for support vector machines (LIBSVM) with an accuracy of 89% and 91% for mid-ripe and ripe fruit in the external validation set, respectively. These results indicate the great potential of hyperspectral imaging for quality monitoring and shelf life analysis of postharvest winter jujube.
•SSC in winter jujube significantly correlated with maturity stage and shelf life.•The SPA-SVR model performed well in SSC prediction.•Spatial distribution was mapped for monitoring SSC evolution.•The SPA-LIBSVM model was satisfactory for shelf life analysis.
In this study, a non-destructive method using visible/near infrared (Vis/NIR) spectroscopy was investigated to predict the soluble solids content (SSC) of intact melons (Cucumis melo L.) cv. ‘Manao’, ...‘Jinhongbao’, ‘Xizhoumi’. A set of 360 samples (120 melons of each cultivar) was used to develop the calibration model, and two location (stylar-end and equatorial locations) models were investigated independently. The samples' spectra were obtained by a portable Vis/NIR photo-diode array spectrometer operated in reflectance mode. Multiplicative scatter correction (MSC), first derivative and Savizky-Golay (SG) smoothing in turn were applied to the obtained spectra. The region from 750 to 950 nm was selected to develop NIR models combined with the partial least squares (PLS) regression method. The results indicated that the stylar-end of the intact melon was the proper location to evaluate the SSC in the intact melon due to its suitable and exclusive physiological structure. A competitive adaptive reweighted sampling (CARS) algorithm was used to select effective wavelengths. Results showed that the CARS algorithm had great potential for simplifying the variables. Furthermore, another 195 samples were used for external prediction to evaluate the CARS-PLS model's accuracy and stability, which resulted in a high determination coefficient (R2p = 0.83) and a low root mean square error (RMSEP = 0.73 ºBrix).
Display omitted
•A universal NIR model for SSC testing among three cultivars was examined.•Some spectral pre-treatments were helpful to develop a universal model.•Stylar-end proved more appropriate to predict SSC of three cultivars melons.•CARS algorithm reliable for effective wavelengths selection for universal PLS model.
Display omitted
•NIR models for soluble solids content of apple were developed.•Both short wave (SWNIR) and long wave (LWNIR) wavelength ranges were considered.•Color compensation significantly ...improves prediction accuracy for SWNIR.•Nonlinear calibration models were better than linear ones.•Wavelength selection and latent variable construction algorithms were investigated.
Shortwave near infrared (SWNIR) and long wave near infrared (LWNIR) spectroscopy with a novel color compensation method were compared to predict soluble solids content of apple. Linear and nonlinear regression models were considered. Eventually, independent component analysis-support vector machine (ICA-SVM) models proved to be superior to other nonlinear models. Rp was 0.9398 and RMSEP was 0.3870% for the optimal model of SWNIR, while Rp was 0.9455 and RMSEP was 0.3691% for that of LWNIR. Moreover, the results showed that color compensation could significantly improve the prediction performance of SWNIR model. Our work implies that SWNIR with color compensation has an obvious prospect in practical industrial use for real-time monitoring apple quality.
•A new method of calculating spectral differences was proposed to enhance quality predictions.•Firmness and SSC predictions for SR spectra varied with the source-detector distance.•IT spectra gave ...consistently better results for both firmness and SSC predictions than SR spectra.•IT spectra can make SSC prediction less sensitive to the light scattering effect.
Spatially resolved spectroscopy (SRS) provides a new approach to the measurement of optical scattering and absorption properties and quality assessment of horticultural products. In this research, spatially resolved (SR) spectra over 550 – 1,650 nm were acquired for 600 peaches using a recently developed SRS system covering the light source-detector (S-D) distances from 1.5 to 36 mm with 30 fibers of three sizes (i.e., 50 µm, 105 µm and 200 µm). A new method of calculating spectral differences, between the first S-D distance and the remaining 14 S-D distances was proposed to enhance firmness and soluble solids content (SSC) predictions. Partial least squares (PLS) regression models based on SR and difference reflectance (DR) spectra were developed and compared for firmness and SSC prediction. Results showed that when using SR spectra, prediction results for firmness and SSC varied greatly with the S-D distance; SSC prediction results became worse with the increasing S-D distance, while larger S-D distances of 12–32 mm resulted in better firmness predictions. DR spectra gave consistently better results for both firmness and SSC predictions than SR spectra, with the best correlation coefficients of 0.853 and 0.839 for firmness and SSC prediction, respectively. Overall, SRS coupled with the spectral difference technique can enhance the prediction of firmness and SSC for peach fruit.
Cherry tomato (
) is popular with consumers over the world due to its special flavor. Soluble solids content (SSC) and firmness are two key metrics for evaluating the product qualities. In this work, ...we develop non-destructive testing techniques for SSC and fruit firmness based on hyperspectral images and the corresponding deep learning regression model. Hyperspectral reflectance images of over 200 tomato fruits are derived with the spectrum ranging from 400 to 1,000 nm. The acquired hyperspectral images are corrected and the spectral information are extracted. A novel one-dimensional (1D) convolutional ResNet (Con1dResNet) based regression model is proposed and compared with the state of art techniques. Experimental results show that, with a relatively large number of samples our technique is 26.4% better than state of art technique for SSC and 33.7% for firmness. The results of this study indicate the application potential of hyperspectral imaging technique in the SSC and firmness detection, which provides a new option for non-destructive testing of cherry tomato fruit quality in the future.
The yellowing and quality deterioration are important factors to shorten the storage period of peeled water chestnuts (PWCs). Integration of 4-OH-7-C3HO-coumarin and controlled atmosphere (CA) ...storage (Ne, O2) to extend the storage period of PWCs has not been studied. The objective of the investigation was to reveal the mechanics with that integration of 4-OH-7-C3HO-coumarin (1.2 %) and CA storage (81.2 % Ne, 18.8 % O2) extended the storage period of PWCs. PWCs were treated with 4-OH-7-C3HO-coumarin (1.2 %), CA storage (81.2 % Ne, 18.8% O2), and integration of 4-OH-7-C3HO-coumarin (1.2 %) and CA storage (81.2 % Ne, 18.8 % O2). The yellowing degree, weight loss, yellowing substance contents, enzymatic activities, total soluble solids content, titratable acidity content, ascorbic acid content, and microbe of PWCs were detected. 4-OH-7-C3HO-coumarin (1.2 %), CA storage (81.2 % Ne, 18.8 % O2), and integration of 4-OH-7-C3HO-coumarin (1.2 %) and CA storage (81.2 % Ne, 18.8 % O2) extended the storage period by 3, 9 and 12 d. Integration of 4-OH-7-C3HO-coumarin (1.2 %) and CA storage (81.2 % Ne, 18.8% O2) was the best. On day 12, integration of 4-OH-7-C3HO-coumarin (1.2 %) and CA storage (81.2 % Ne, 18.8 % O2) reduced the yellowing degree from 99.5% to 0, the peroxidase activity from 35,603.37 to 28,504.61 U s−1 kg, the eriodictyol content from 3.09 × 10−4 % to 0, the weight loss from 5.24 % to 0. Integration of 4-OH-7-C3HO-coumarin (1.2 %) and CA storage (81.2 % Ne, 18.8 % O2) increased the total soluble solids content from 9.37 % to 13.49%, the titratable acidity content from 5.67 × 10−3 % to 8.62 × 10−3 %, and the titratable acidity content from 8 × 10−5 % to 8.55 × 10−5 %. Integration of 4-OH-7-C3HO-coumarin (1.2 %) and CA storage (81.2 % Ne, 18.8 % O2) can be employed to extend the storage period of PWCs. This study provided a theoretical basis for the practical application of integration of 4-OH-7-C3HO-coumarin and CA storage (Ne, O2) to extend the storage period of PWCs.
•The yellowing of peeled water chestnuts was catalyzed by peroxidase.•Peroxidase activity was inhibited by 4-OH-7-C3HO-coumarin.•Eriodictyol was a product of yellowing of peeled water chestnuts.•Controlled atmosphere storage delayed quality deterioration.•Integration treatment extended storage period of peeled water chestnuts by 12 d.
Spatially-resolved spectroscopy (SRS) enables better interrogation of tissue properties at different depths, and it thus has the potential for enhancing quality assessment of horticultural products ...like tomato, which are heterogeneous in structure and chemical composition. This research was aimed at assessing quality of tomato fruit by using a newly developed SRS system with 30 detection optic fibers covering the wavelength range of 550–1650 nm and comparing its performance with two conventional single-point (SP) spectroscopic instruments covering the visible and shortwave near-infrared (Vis/SWNIR) (400–1100 nm) and near-infrared (NIR) (900–1300 nm) regions, respectively. Spatially-resolved (SR) spectra and SP interactance spectra were acquired for 600 ‘Sun Bright’ tomato fruit. Partial least squares (PLS) models for individual SR spectra and their combinations and for SP Vis/SWNIR and NIR spectra were developed for prediction of soluble solids content (SSC) and pH. Results showed that SSC and pH predictions by SRS varied depending on the light source-detector distance, with the correlation coefficient of prediction (rp) ranging 0.608–0.791 and 0.688–0.800, respectively. Combinations of two or more SR spectra resulted in better, more consistent SSC and pH predictions. SR predictions of pH (rp = 0.819) were better than for SP Vis/SWNIR (rp = 0.743) and NIR (rp = 0.741) predictions, whereas SR predictions of SSC (rp = 0.800) were comparable to SP NIR predictions (rp = 0.810) but better than SP Vis/SWNIR predictions (rp = 0.729). This research showed that owning to its ability of acquiring spatially-resolved spectral information, the SRS technique has advantages over conventional SP spectroscopy for enhancing quality assessment of tomatoes.
•Light source-detector distance affected soluble solids content (SSC) and pH predictions.•Combinations of spatially-resolved spectra resulted in better SSC and pH predictions.•Spatially-resolved spectroscopy had better pH predictions than single-point spectroscopy.
The soluble solids content (SSC) is an important indicator for evaluating the internal quality of apples. This study proposed a novel method for detecting apple SSC. This method involved collecting ...the transmission spectra of apples, transforming one-dimensional spectra into two-dimensional images using the gramian angular difference field (GADF) technique, and analyzing the images using an improved mobile vision transformer (MobileViT) model. Furthermore, the Grad-CAM method was used to visualize the model's prediction effect on SSC and find the wavelength range that had a greater impact on the model results. The results indicated that the GADF-improved MobileViT model exhibited excellent performance on the test dataset, with a determination coefficient (R2) of 0.938, a root mean square error (RMSE) of 0.532, and a mean absolute error (MAE) of 0.423. As the number of wavelengths used for modeling decreased, the improvements made in this study to MobileViT continued to enhance the model's performance effectively. And when using fewer training samples, the GADF-improved MobileViT model also had better performance than the original model. In conclusion, using visible and near-infrared spectroscopy and GADF image encoding techniques for the prediction of apple SSC is feasible.
•The SSC of golden venus apples was predicted by visible/NIR spectroscopy.•Converting 1D spectral data into 2D spectral images to predict apple SSC.•Proposed GADF-improved MobileViT based on transformer to predict apple SSC.•The Grad-CAM visualized influential wavelength ranges impacting model predictions.
The purpose of this study was to compare the accuracy and robustness of the detection models based on bulk optical properties (BOP) with that based on conventional spectroscopy in kiwifruit quality ...evaluation. 81 kiwifruit were selected as experimental samples in this study. A single integrating sphere system was built to estimate the bulk absorption coefficient (μa) and bulk reduced scattering coefficient (μs′) of samples and a self-designed online system was used to obtain transmission spectra. The relationship of μa and μs′ with SSC and flesh firmness was analyzed, and detection models were established using partial least squares regression (PLSR). Competitive adaptive reweighted sampling (CARS) was also used to eliminate the variables in the original spectra that do not contribute to the improvement of the model performance. Results showed that μa at 670 nm decreased with the increase of SSC, μa at 720–900 nm and 950–1000 nm increased with the increase of SSC, and spectra of μs′ decreased with the decreasing firmness. CARS-PLSR models were developed, based on μa, μs′, μa×μs′, μeff, μt′, and transmission spectra. The accuracy of the model based on BOP in predicting internal quality was better than that based on transmission spectra. The model based on μa was the best for SSC (Rp2 = 0.97, RMSEP = 0.25%), and the model based on μa×μs′ was the best for flesh firmness (Rp2 = 0.97, RMSEP = 0.02 N). 20 kiwifruit that differed from the experimental samples in planting orchard and harvest time were used to compare the robustness and portability of the models. Results showed that all SSC models and the firmness model based on μa×μs′ had good robustness and portability. However, the model based on transmission spectra had a poor performance in predicting the firmness of samples from the external validation set. This study provides an effective reference for the prediction of firmness and SSC based on BOP and transmission spectra of kiwifruit.
•BOP difference of kiwifruit with different internal quality attributes were compared.•BOP and online transmission spectra were compared in predicting internal quality.•The SSC model of kiwifruit based on μa had the best robustness.•The model based on μa×μs′ performed best in determining firmness.•Robustness of firmness prediction model based on transmission spectra was poor.