Jinshan Yan’s research while affiliated with Zhejiang University and other places

Visible/Near-infrared (Vis/NIR) spectroscopy is widely used in the detection of dry matter content (DMC) of potatoes. However, biological variability (e.g., cultivar and season) will affect the potato DMC and spectral features, and will further cause the DMC prediction model ineffective. This study aimed to develop robust Vis/NIR models for predicting potato DMC with influence of cultivar and season. The local and global models were developed to explore the influence of cultivar and season. The Mahalanobis distance and concentration gradient (MD-CG) method was developed to select representative samples, and the combinations of different variable selection methods (CARS, SPA and CSMW) and model updating methods (SBC and recalibration) were investigated for model enhancement. The results indicated that 10 new samples selected by MD-CG method, combined with variable selection and model updating, were sufficient to improve the performance of the local (RPDp>1.7) and global (RPDp>2) models. In the local models, for the datasets with different cultivars (EG-2021, XS-2021 and AT-2021), the optimal results were obtained using CSMW combined with recalibration, and the RMSEp was decreased from 4.18%, 1.14%, 2.54–1.05%, 0.72%, 0.79%, respectively. For the datasets with different seasons (FA-2022), the optimal result was obtained by using SPA combined with recalibration, and the RMSEp was decreased from 3.70% to 0.91%. For the global model, CSMW combined with recalibration and SPA combined with SBC obtained better results, with RMSEp decreasing from 0.83% to 0.52% and 0.51%, respectively. The MD-CG method and the combinations of variable selection and model updating proposed in this study are important to reduce the influence of external conditions and enhance the model robustness to biological variability.

Potatoes are generally consumed directly as a staple food or used for processing, depending on the quality of raw materials. Dry matter content (DMC) is the most critical characteristic of potatoes, as it determines the processing and the final product quality. This study aimed to investigate the potential of different optical sensing systems in predicting the DMC of intact potato tubers, and the efficacy of classifying potatoes based on dry matter levels. The whole tubers were scanned using three optical sensing modes (transmittance spectra, interactance spectra and hyperspectral imaging). PLSR and different classifiers (PLSDA, SVM and ANN) were utilized to build the prediction and classification models, respectively. To extract the most influential wavelengths related to the prediction of DMC, the CARS and CSMW techniques were applied. The results indicated that the DMC of two sections on the equator of the potato tuber belly can well represent the DMC of the intact potato, and together with the spectral detection at the equatorial position, it provided good performance. The CARS-PLSR prediction model in transmittance mode showed stronger correlations than other systems, with Rp and RMSEP values of 0.968 and 0.413%, respectively. The CARS-SVM-Linear classification model exhibited the best performance with classification rates of 100% and 97.62% in the training and testing sets, respectively. Moreover, the spectra preferred by CARS and CSMW variable selection methods in transmittance mode overlapped near the absorption peak at 980 nm, indicating the importance of this band for predicting DMC. This study presented the feasible application of using spectroscopy to evaluate the DMC of intact potatoes and classify potatoes based on thresholds that are crucial to consumers and food processors. Graphical abstract

The on-line detection of paddy moisture content (MC) during harvest has gained increasing interest recently due to its unique role for the control of combine harvester, yield evaluation and post-harvest grain handling operations. However, it is very difficult to achieve good performance under the complex and changeable situation during field harvest. In this study, paddy varieties, paddy flow, feeding types and algorithms were comprehensively considered to optimize the MC detection method. Firstly, an on-line near-infrared sensing system supplemented for grain tank of combine harvester was designed, and spectra were collected under the most common and essential detecting conditions, which including paddy varieties, feeding types and straw effect. Then, ensemble preprocessing, parameter optimization and accuracy test were performed. The best result of all conditions was extreme learning machine (ELM) coupled with the ensemble preprocessing of orthogonal signal correction with savitzky-golay (OSC + SG). The root mean standard error of prediction (RMSEPV) of this method after validation on unknown sample was as low as 1.0791% w.b, and the residual predictive deviation (RPDV) was higher than 3.5646. Stability tests were carried out under conditions of varying feeding types and straw quantities. The results showed that ELM had enough robustness to cope with complex detecting conditions and maintain proper accuracy as the mean value of repeatability, conditions and reproducibility were calculated as 0.0213%, 0.4471% and 0.6868% w.b, respectively. Despite the preliminary feasibility for on-line MC measurement of paddy, the on-line near-infrared sensing system needs to be verified on combine harvester during harvest.

As production and demand for high quality Macadamia nuts rise worldwide, rapid and accurate in-situ methods for monitoring internal nut quality will need to be developed. Therefore, purpose of this study was to determine the quality (internal nut defects and oil content) of intact macadamia nuts by combining near-infrared spectroscopy with variable selection algorithms and calibration models. Transmission spectra in the ranges of 1,000-1,650 nm from a total of 345 macadamia nuts were acquired. Partial least square-discriminant analysis (PLS-DA) and partial least square-regression (PLS-R) models with three different spectral preprocessing techniques were then evaluated using the full spectra to classify nut defects and predict oil content. A Savitzky-Golay (S-G) first derivatives preprocessing technique was selected as the best one. Then, competitive adaptive reweighted sampling (CARS), random frog (RF), and variable importance projection (VIP) algorithms were used to select effective wavelengths (EWs) to build simpler and more robust models for classification of intact macadamia nut defects and prediction of oil content. The PLS-DA-CARS with S-G first derivatives preprocessing based model provided the best nut defect classification with a 91.4% accuracy, whilst a PLS-R-CARS with S-G second derivatives preprocessing model for oil content prediction had a coefficient of determination (R²pred) of 0.88 and standard error of prediction (SEP) of 1.15%.

Highlights A custom-designed online Vis/NIR spectroscopy system was used for real-time detection of watercore in apples. Watercore severity index (WSI) was applied for watercore severity assessment. Higher than 95.0% accuracy was obtained for total samples in classifying sound apples from watercore groups using kNN, BPNN, SVM, and 1D CNN at a detection speed of 3 apples s ⁻¹ . Linear kernel SVM achieved the best classification accuracy of 96% for samples in the prediction set. Abstract . Watercore, an internal physiological disorder affecting apples, can be characterized by water-soaked, glassy regions near the fruit core. It is used as an indicator of full ripeness, storage suitability, and price of apples in many countries. Therefore, fast and non-destructive detection of watercore plays an important role in improving the commercial value of apples and reducing postharvest costs. In this study, an online visible/near-infrared (Vis/NIR) spectroscopy system was proposed for real-time detection of watercore in ‘Fuji’ apples (Malus pumila Mill.). A total of 318 samples harvested during harvest season in the same orchard were analyzed for both watercore severity index (WSI) and soluble solids content (SSC). According to the USDA watercore classification standard, all samples were classified into one of four classes (sound, slight, moderate, or severe) based on the affected area of watercore. Results showed that, although there was a positive correlation between spectral intensity and affected area of watercore, no significant relationship between affected area size and SSC could be obtained by Pearson test (correlation coefficient ~0.094). Generally, >95.0% accuracy was obtained for total samples at a detection speed of 3 apples s-1 in classifying sound from watercore groups using k-nearest neighbors (kNN) algorithm, back-propagation neural network (BPNN), support vector machine (SVM) classification, and one-dimensional convolutional neural network (1D-CNN). The best classification result was achieved by linear kernel SVM, with an accuracy of 96% for total samples. These classification algorithms showed preliminary feasibility for online screening of apples with watercore using Vis/NIR spectroscopy in industrial applications. Keywords: Apple watercore, Machine learning, Online detection, Vis/NIR spectroscopy, Watercore severity index.