Solids Content Of Apples Research Articles

Stacking Ensemble Learning Method for Quantitative Analysis of Soluble Solid Content in Apples

ABSTRACTThe soluble solids content (SSC) in apples directly affects their quality. This study aimed to detect SSC nondestructively using hyperspectral technology combined with chemometrics. However, data generation may not follow a specific pattern, and even small perturbations in the data can have a significant impact on the constructed model. To improve the anti‐interference capability of individual models, this study proposed a stacking ensemble learning method that adopted partial least squares (PLS), support vector machine (SVM), extreme gradient boosting (Xgboost), random forest (RF) as basic‐learners, and RF serving as a meta‐learner. Experimental results showed that the performance of the established model on the test set were as follows: the root mean square error (RMSE) was 0.4325, mean absolute error (MAE) was 0.3245, mean absolute percentage error (MAPE) was 0.0271, coefficient of determination () was 0.9250. These results indicate that the stacking ensemble learning approach could appropriately fuse the predictive results of each basic‐learner and improve the prediction accuracy of individual models. To verify the superiority of the proposed stacking ensemble learning method, the selection of its basic‐learners, meta‐learner, and combination strategy were compared and analyzed. This study not only provides a theoretical reference for the further development of related nondestructive detection equipment but also offers guidance for fusion algorithms as well.

Combining hyperspectral imaging technology and visible-near infrared spectroscopy with a data fusion strategy for the detection of soluble solids content in apples

Soluble solids content (SSC) is an important indicator for evaluating apple quality. This study aimed to assess two spectral techniques (hyperspectral imaging (HSI) and visible-near infrared (Vis-NIR)) combined with low-level and mid-level fusion strategies (LLF and MLF) for the detection of SSC in apples. Firstly, baseline correction (BC), detrending (DT), multiplicative scatter correction (MSC), savitzky-golay (SG), and standard normal variables (SNV) were used for the preprocessing of spectral data. Secondly, genetic algorithm (GA), competitive adaptive reweighted sampling (CARS), and their combinations were used for feature variable extraction. Finally, models were developed using partial least squares regression (PLSR) for spectral data. The results showed that Vis-NIR has an advantage over HSI in predicting apple SSC if only a single spectral technique was considered. The data fusion strategy showed better performance in predicting SSC metrics compared to individual spectral data. Among them, the LLF strategy showed the best performance in predicting SSC, with an Rp2 of 0.927, an RMSEP of 0.529 °Brix, and an Akike information criterion (AIC) of 332.96. In addition, an optimal model based on HSI data was used to achieve visual maps of SSC. It was demonstrated that the fusion of HSI and Vis-NIR data provided a promising method for detecting the SSC in apples.

Convolutional neural networks fusing spectral shape features with attentional mechanisms for accurate prediction of soluble solids content in apples

Convolutional neural networks fusing spectral shape features with attentional mechanisms for accurate prediction of soluble solids content in apples

An improved method for predicting soluble solids content in apples by heterogeneous transfer learning and near-infrared spectroscopy

Predicting fruit soluble solids content (SSC) is a hot topic in non-destructive detection. Biological variability of fruit decreases the accuracy of the prediction model. Therefore, modeling methods that can reduce the negative effect of biological variability are necessary. In this paper, an improved modeling method based on the partial least squares (PLS) regression was proposed, using convolutional autoencoder and heterogeneous transfer learning for feature extraction. The dataset used for calibration and prediction contains spectra and corresponding SSC values of apples collected from 2012 to 2018. In comparison with the traditional PLS method, the proposed method performed better for long-term SSC prediction of apples with biological variability. The correlation coefficients calculated on validation set were 0.934, 0.940, 0.915, 0.899, 0.901, respectively. The root mean square errors calculated on validation set were 0.736 °Brix, 0.694 °Brix, 0.674 °Brix, 0.571 °Brix, 0.620 °Brix, respectively. Besides, the proposed method could still achieve relatively satisfactory results when the quantity of calibration samples was less.

Postharvest acibenzolar-S-methyl treatment maintains storage quality and retards softening of apple fruit.

"Golden delicious" apples were dipped in 100mg/L acibenzolar-S-methyl (ASM) to investigate the fruit quality and softening during 12days of storage. Weight loss, flesh firmness, ethylene release, respiratory rate, content of total soluble solids and titratable acid, the activity of pectinase, cellulase, and β-glucosidase, and water-insoluble pectin and water-soluble pectin contents were investigated. The results demonstrated that ASM treatment inhibited ethylene release and respiratory rate, reduced titratable acidity, and enhanced total soluble solids content in apples. Moreover, application of ASM suppressed the reduction of flesh firmness, activity of pectin methylesterase, and polygalacturonase. Cellulase, β-glucosidase, and degradation of protopectin in apple fruit were also suppressed by ASM treatment during storage. In conclusion, ASM could maintain fruit quality by regulating cell wall-degrading enzymes during storage. PRACTICAL APPLICATIONS: Application of acibenzolar-S-methyl after harvest has the potential of delaying fruit softening by regulating cell wall-degrading enzymes, thus retain fruit quality.

Determination of soluble solid content in multi-origin ‘Fuji’ apples by using FT-NIR spectroscopy and an origin discriminant strategy

Apple is widely planted all over the world. Origin variability influences the internal quality of apples because soil characteristics, light effects, nutrition, weather conditions, as well as growing management vary from orchard to orchard. However, if taking spectral variations caused by the origin variability of apple samples from different orchards into account, the fruit quality parameters could not be measured or predicted with high accuracy by using the current models without updates. To improve the practicability and accuracy of the prediction models, a multi-origin regression model for the determination of soluble solids content in apples from three origins by using FT-NIR spectroscopy and a model search strategy was developed in this paper. In this model, based on the wavelengths selected by competitive adaptive reweighted sampling algorithm (CARS), partial least squares discriminant analysis (PLS-DA) was trained and applied to identify the geographical origins of the apple samples. The results indicate that the samples spectra were correctly matched to the corresponding classes and a 98.1% correct classification was achieved. Partial least squares regression (PLS) was used to establish three single-origin calibration models for the determination of soluble solids content (SSC) in apples from three different origins, and meanwhile, CARS algorithm was also applied to select the most effective wavelengths for calibration models. Then, the multi-origin CARS-PLS model for determination of SSC in apples from three origins was developed combined with origin discriminant and the proposed model search strategy. It was concluded that the multi-origin CARS-PLS model achieved more satisfying results than the single-origin CARS-PLS models for the determination of SSC, with Rp and RMSEP values for the apple samples from three geographical origins being 0.921, 0.759, 0.924 and 0.661, 0.673, 0.547 °Brix, respectively. The above results indicate that it is promising to build a multi-origin CARS-PLS model to predict SSC for apples based on an origin discriminant approach to reduce the effect of geographical origin.

Noncontact evaluation of soluble solids content in apples by near-infrared hyperspectral imaging

Near-infrared (NIR) hyperspectral imaging was used to evaluate soluble solids content (SSC) in ‘Fuji’ apples [Malus sylvestris (L.) Mill. var. domestica (Borkh. Mansf.)]. Eighty ‘Fuji’ apples were analyzed by collecting four small block samples from each one (approximately 2.0 cm × 2.0 cm × 1.5 cm). Partial least squares (PLS) regression analysis was performed to determine the relation between SSC reference data and NIR spectral data measured from each sample. The cross-validation coefficient of determination (r2) between predicted and measured SSC values is 0.89 with a root mean squared error of cross-validation (RMSECV) of 0.55%. Then, we successfully mapped SSC at a high spatial resolution (375 μm per pixel). In addition, the absorption and reduced scattering coefficients of the measured samples were determined based on a diffusion theory model. The absorption coefficients are positively correlated to the SSC values (chemical information), whereas water cored tissue content (physical information) causes a characteristic change in light scattering coefficients. The fitting results were validated by Monte Carlo simulation, and the light penetration depth in ‘Fuji’ apples was estimated to be around 0.33 cm at 1198 nm and 0.17 cm at 1450 nm, respectively.

Nondestructive Measurement of Soluble Solids Content in Apples by a Portable Fruit Analyzer

Feasibility studies of using a portable fiber spectrometer in conjunction with multivariate and variable screening analysis were investigated for noninvasive inspection of the internal quality of fruit. A highly effective illumination with circular reflective accessories was designed to reflect the divergent light of the lamps onto the sample. The penetrating spectra of the apples were measured for soluble solids content (SSC) at 550 to 985 nm in transmission mode with different numbers of lamps illuminating. The illumination was optimized with six lamps by comparison to the performance of partial least square (PLS) models. Stepwise multiple linear regression (SMLR), genetic algorithm (GA), successive projective algorithm (SPA), uninformative variable elimination (UVE), and their combinations were comparatively employed to screen the important wavelengths and promote the robustness of the calibration model. Finally, the novel calibration model built using UVE-SPA-MLR method on 21 screening wavelengths (only 1 % of all) exhibited higher coefficient of prediction (r p) of 0.951 and root mean square error of prediction (RMSEP) of 0.39 % brix for the prediction set. This study shows that the accuracy of the quantitative analysis conducted by the developed analyzer can meet the requirement for practical use.

Optimization of Informative Spectral Regions in FT-NIR Spectroscopy for Measuring the Soluble Solids Content of Apple

A novel potential method, linear combination weight PLS (LCW-PLS) model, was suggested for improving the performance of routine PLS model based on selected informative regions. Moving window partial least squares (MWPLS), genetic algorithms interval partial least squares (GAiPLS) and synergy interval partial least squares (SiPLS) were used to optimize informative spectral regions from FT-NIR spectra. A total of 660 apples harvested at 2006, 2007 and 2008, were divided into calibration and prediction sets by Kennard-Stone method. The best calibration model was obtained by LCW-PLS method based on informative spectral regions of 4328–4787, 5323–5512, 5982–7135 and 7159–7463 cm− 1 selected by MWPLS procedure, and corresponding weights of 0.004, 0.070, 0.066 and 0.860, respectively. The LCW-MWPLS model was applied to predict samples, the prediction results were with RP of 0.942, RMSEP of 0.649 %Brix and RPDP of 3.10. In addition, developed LCW-MWPLS model using random two years samples was used to predict one ...