A calibration transfer optimized single kernel near-infrared spectroscopic method

Xu, Zhuopin; Fan, Shuang; Liu, Jing; Liu, Binmei; Lei, Tao; Wu, Jin; Hu, Shupeng; Zhao, Liping; Wang, Qi; Wu, Yuejin

doi:10.1016/j.saa.2019.05.003

Cited by 32 publications

(9 citation statements)

References 21 publications

Supporting

Mentioning

Contrasting

Order By: Relevance

“…The range of 1210–1450 nm is attributed to the 2nd overtone of C-H and the 1st overtone of O-H [ 54 ]. The wavelength between 975 nm and 1015 nm is mainly attributed to N-H stretch second overtone [ 57 ], and 1526 nm (N-H stretch first overtone) [ 58 ], which can reflect pesticide residue differences among different levels. Since Jiatu, Huiyin, and Xishuangke contain a large amount of C-H, O-H, and N-H as observed by their chemical molecular formula, these selected bands have a great correlation with pesticides.…”

Section: Resultsmentioning

confidence: 99%

Detection of Pesticide Residue Level in Grape Using Hyperspectral Imaging with Machine Learning

Yan

Zhang

et al. 2022

Foods

View full text Add to dashboard Cite

Rapid and accurate detection of pesticide residue levels can help to prevent the harm of pesticide residue. This study used visible/near-infrared (Vis-NIR) (376–1044 nm) and near-infrared (NIR) (915–1699 nm) hyperspectral imaging systems (HISs) to detect the level of pesticide residues. Three different varieties of grapes were sprayed with four levels of pesticides. Logistic regression (LR), support vector machine (SVM), random forest (RF), convolutional neural network (CNN), and residual neural network (ResNet) models were used to build classification models for pesticide residue levels. The saliency maps of CNN and ResNet were conducted to visualize the contribution of wavelengths. Overall, the results of NIR spectra performed better than those of Vis-NIR spectra. For Vis-NIR spectra, the best model was ResNet, with the accuracy of over 93%. For NIR spectra, LR was the best, with the accuracy of over 97%, but SVM, CNN, and ResNet also showed closed and fine results. The saliency map of CNN and ResNet presented similar and closed ranges of crucial wavelengths. Overall results indicated deep learning performed better than conventional machine learning. The study showed that the use of hyperspectral imaging technology combined with machine learning can effectively detect the level of pesticide residues in grapes.

show abstract

Section: Resultsmentioning

confidence: 99%

Detection of Pesticide Residue Level in Grape Using Hyperspectral Imaging with Machine Learning

Yan

Zhang

et al. 2022

Foods

View full text Add to dashboard Cite

show abstract

“…For the SGPC model, the peaks at 1465, 2127, 2290, and 2302 nm were protein-related absorption peaks, and the peak at 1940 nm was a water-related absorption peak, as proteins in the endosperm strongly interact with water [ 24 , 25 , 26 ]. The SGPC model’s results were similar to those based on the population rice grain spectrum using hyperspectral imaging [ 27 ], and slightly worse than the diffuse transmission SGPC model built by Xu et al [ 11 ] because of the difference in the spectral acquisition methods, e.g., the diffuse reflectance spectra that were used in the paper.…”

Section: Discussionmentioning

confidence: 56%

“…To verify this view, a high-throughput detection of rice composition at the single-grain level is needed. The traditional chemical detection technique for single-grain rice composition is destructive, expensive, inefficient, and insufficient to support the simultaneous detection of multiple components [ 11 ]. Therefore, the development of a high-throughput nondestructive detection technique for determining single-grain rice composition became the basis for conducting this study.…”

Section: Introductionmentioning

confidence: 99%

Effects of Variations in the Chemical Composition of Individual Rice Grains on the Eating Quality of Hybrid Indica Rice Based on Near-Infrared Spectroscopy

Cheng

Fan

et al. 2022

Foods

Self Cite

View full text Add to dashboard Cite

The chemical composition of individual hybrid rice (F2) varieties varies owing to genetic differences between parental lines, and the effects of these differences on eating quality are unclear. In this study, based on a self-developed near-infrared spectroscopy platform, we explored these effects among a set of 143 hybrid indica rice varieties with different eating qualities. The single-grain amylose content (SGAC) and single-grain protein content (SGPC) models were established with coefficients of determination (R2) of 0.9064 and 0.8847, respectively, and the dispersion indicators (standard deviation, variance, extreme deviation, quartile deviation, and coefficient of variation) were proposed to analyze the variations in the SGAC and SGPC based on the predicted results. Our correlation analysis found that the higher the variation in the SGAC and SGPC, the lower the eating quality of the hybrid indica rice. Moreover, the addition of the dispersion indicators of the SGAC and SGPC improved the R2 of the eating quality model constructed using the composition-related physicochemical indicators (amylose content, protein content, alkali-spreading value, and gel consistency) from 0.657 to 0.850. Therefore, this new method proved to be useful for identifying high-eating-quality hybrid indica rice based on single near-infrared spectroscopy prior to processing and cooking.

show abstract

“…Therefore, the more useful information based on higher factors should be used. A similar number of factors were needed as the previous studies, such as for single rice kernels (factor = 9) (Xu et al, 2019b), single coffee beans (factor = 8-10) (Fox et al, 2013), and single cocoa beans (factor = 8-15) (Caporaso et al, 2018) to ensure robustness of the models.…”

Section: Prediction Models For Compositional Characteristicsmentioning

confidence: 99%

Rapid high-throughput determination of major components and amino acids in a single peanut kernel based on portable near-infrared spectroscopy combined with chemometrics

Liu

Erasmus

et al. 2020

Industrial Crops and Products

View full text Add to dashboard Cite

A calibration transfer optimized single kernel near-infrared spectroscopic method

Abstract: Highlights  A calibration transfer optimized NIR method was used to analyze individual seeds.  The protein contents of single rice kernels were evaluated via two NIR methods.  Spectra of individual seeds in different forms can be transferred among each other.

Cited by 32 publications

References 21 publications

Detection of Pesticide Residue Level in Grape Using Hyperspectral Imaging with Machine Learning

Detection of Pesticide Residue Level in Grape Using Hyperspectral Imaging with Machine Learning

Effects of Variations in the Chemical Composition of Individual Rice Grains on the Eating Quality of Hybrid Indica Rice Based on Near-Infrared Spectroscopy

Rapid high-throughput determination of major components and amino acids in a single peanut kernel based on portable near-infrared spectroscopy combined with chemometrics

Contact Info

Product

Resources

About