Matches in SemOpenAlex for { <https://semopenalex.org/work/W4385554800> ?p ?o ?g. }
- W4385554800 endingPage "115150" @default.
- W4385554800 startingPage "115150" @default.
- W4385554800 abstract "Tea grade evaluation plays an important role in detecting the quality of tea. In this work, we proposed a method for black tea grade discrimination, which is based on the hyperspectral (HSI) technique, chemometric algorithms and data fusion strategies. Standard Normal Variable (SNV) and Multiple Scattering Correction (MSC) were used for the pretreatment of HSI-NIR data. Moreover, the spectral features of catechins, tea polyphenols and soluble sugars were extracted separately by the Uninformative Variable Elimination (UVE). To improve the accuracy of the model, the spectral data were secondarily downscaled by the Successive Projection Algorithm (SPA) and Kernel Principal Component Analysis (KPCA), respectively. Image features were extracted by Principal Component Analysis (PCA) and Gray Level Co-generation Matrix (GLCM). Simultaneously, the image features had been fused with the spectral features in order to realize data fusion. Partial Least Squares Discriminant Analysis (PLS-DA), Support Vector Machines (SVM) and Probabilistic Neural Networks (PNN) were utilized to build the discriminant models. The results show that hyperspectral techniques combined with data fusion strategies could improve the model accuracy. The UVE-SPA-GLCM-SVM was chosen as the optimal model with 98.33% accuracy of the validation set. The method provides a theoretical basis for online black tea grade differentiation." @default.
- W4385554800 created "2023-08-04" @default.
- W4385554800 creator A5006373071 @default.
- W4385554800 creator A5020303638 @default.
- W4385554800 creator A5045099503 @default.
- W4385554800 creator A5060368771 @default.
- W4385554800 creator A5079847717 @default.
- W4385554800 creator A5081563767 @default.
- W4385554800 creator A5092216132 @default.
- W4385554800 date "2023-08-01" @default.
- W4385554800 modified "2023-10-14" @default.
- W4385554800 title "Fusing spectral and image information for characterization of black tea grade based on hyperspectral technology" @default.
- W4385554800 cites W1144514670 @default.
- W4385554800 cites W2020984122 @default.
- W4385554800 cites W2031668803 @default.
- W4385554800 cites W2062988009 @default.
- W4385554800 cites W2084169316 @default.
- W4385554800 cites W2094868831 @default.
- W4385554800 cites W2108314099 @default.
- W4385554800 cites W2117914983 @default.
- W4385554800 cites W2515227998 @default.
- W4385554800 cites W2738012852 @default.
- W4385554800 cites W2796330417 @default.
- W4385554800 cites W2806779833 @default.
- W4385554800 cites W2942577838 @default.
- W4385554800 cites W2956569383 @default.
- W4385554800 cites W2968359660 @default.
- W4385554800 cites W2972951566 @default.
- W4385554800 cites W2996781884 @default.
- W4385554800 cites W2997231073 @default.
- W4385554800 cites W3008074694 @default.
- W4385554800 cites W3028231515 @default.
- W4385554800 cites W3032930553 @default.
- W4385554800 cites W3083600862 @default.
- W4385554800 cites W3121079640 @default.
- W4385554800 cites W3126090857 @default.
- W4385554800 cites W3161146206 @default.
- W4385554800 cites W3161414162 @default.
- W4385554800 cites W3216383890 @default.
- W4385554800 cites W4281723452 @default.
- W4385554800 cites W4315490142 @default.
- W4385554800 doi "https://doi.org/10.1016/j.lwt.2023.115150" @default.
- W4385554800 hasPublicationYear "2023" @default.
- W4385554800 type Work @default.
- W4385554800 citedByCount "0" @default.
- W4385554800 crossrefType "journal-article" @default.
- W4385554800 hasAuthorship W4385554800A5006373071 @default.
- W4385554800 hasAuthorship W4385554800A5020303638 @default.
- W4385554800 hasAuthorship W4385554800A5045099503 @default.
- W4385554800 hasAuthorship W4385554800A5060368771 @default.
- W4385554800 hasAuthorship W4385554800A5079847717 @default.
- W4385554800 hasAuthorship W4385554800A5081563767 @default.
- W4385554800 hasAuthorship W4385554800A5092216132 @default.
- W4385554800 hasBestOaLocation W43855548001 @default.
- W4385554800 hasConcept C114614502 @default.
- W4385554800 hasConcept C119857082 @default.
- W4385554800 hasConcept C122280245 @default.
- W4385554800 hasConcept C12267149 @default.
- W4385554800 hasConcept C153180895 @default.
- W4385554800 hasConcept C154945302 @default.
- W4385554800 hasConcept C159078339 @default.
- W4385554800 hasConcept C169272836 @default.
- W4385554800 hasConcept C182335926 @default.
- W4385554800 hasConcept C185592680 @default.
- W4385554800 hasConcept C22354355 @default.
- W4385554800 hasConcept C27438332 @default.
- W4385554800 hasConcept C2776214188 @default.
- W4385554800 hasConcept C2992231244 @default.
- W4385554800 hasConcept C31903555 @default.
- W4385554800 hasConcept C33923547 @default.
- W4385554800 hasConcept C41008148 @default.
- W4385554800 hasConcept C69738355 @default.
- W4385554800 hasConcept C74193536 @default.
- W4385554800 hasConceptScore W4385554800C114614502 @default.
- W4385554800 hasConceptScore W4385554800C119857082 @default.
- W4385554800 hasConceptScore W4385554800C122280245 @default.
- W4385554800 hasConceptScore W4385554800C12267149 @default.
- W4385554800 hasConceptScore W4385554800C153180895 @default.
- W4385554800 hasConceptScore W4385554800C154945302 @default.
- W4385554800 hasConceptScore W4385554800C159078339 @default.
- W4385554800 hasConceptScore W4385554800C169272836 @default.
- W4385554800 hasConceptScore W4385554800C182335926 @default.
- W4385554800 hasConceptScore W4385554800C185592680 @default.
- W4385554800 hasConceptScore W4385554800C22354355 @default.
- W4385554800 hasConceptScore W4385554800C27438332 @default.
- W4385554800 hasConceptScore W4385554800C2776214188 @default.
- W4385554800 hasConceptScore W4385554800C2992231244 @default.
- W4385554800 hasConceptScore W4385554800C31903555 @default.
- W4385554800 hasConceptScore W4385554800C33923547 @default.
- W4385554800 hasConceptScore W4385554800C41008148 @default.
- W4385554800 hasConceptScore W4385554800C69738355 @default.
- W4385554800 hasConceptScore W4385554800C74193536 @default.
- W4385554800 hasLocation W43855548001 @default.
- W4385554800 hasOpenAccess W4385554800 @default.
- W4385554800 hasPrimaryLocation W43855548001 @default.
- W4385554800 hasRelatedWork W1488165778 @default.
- W4385554800 hasRelatedWork W1756633271 @default.
- W4385554800 hasRelatedWork W1992961908 @default.