期刊论文

Qing, XD

英文

European Food Research and Technology

1438-2377

2025

1-15

10.1007/s00217-025-04890-z

This work was supported by the National Natural Science Foundation of China (Grant Nos. 21707032 and 32172300) and Hunan Provincial Natural Science Foundation (Grant No. 2025JJ52251). The funding agency had no role in the design of the study, the collection, analysis, and interpretation of data, or in writing the manuscript.

本校为第一且通讯机构

Extracting valuable physical and chemical information from massive hyperspectral imaging (HSI) data is a pressing challenge for food analysis. In this study, a new and intelligent strategy was developed to identify trace adulterants in the food matrix. The strategy was based on the hierarchical agglomerative clustering analysis of essential information selected by interesting features finder as well as uniform manifold approximation and projection from HSI data (named IFF-UMAP-HAC). Four Raman HSI datasets and four NIR HSI datasets were utilized to verify the accuracy and reliability of the ne...