Classifying big data in hyperspectral imaging (HSI) can be challenging when minor (low-concentrated) compounds are present in actual samples, as for chemical additives and adulterants in food matrix. Herein, we propose a new strategy to classify HSI data for the identification of adulterants in food material for the first time. This strategy is based on the selection of essential spectral pixels of full HSI data followed by the feature space construction using uniform manifold approximation and projection as well as the data clustering utilizing hierarchical clustering analysis on the reduced data (named ESPs-UMAP-HCA). We apply our approach to analyze two real NIR datasets and four new Raman datasets. Compared with non-ESPs UMAP-HCA and t-distributed stochastic neighbor embedding combined with ESPs and HCA (ESPs-t-SNE-HCA), the developed strategy provides well-separated clusters for major and minor compounds in food matrix. Finally, the adulterants as minor compounds are accurately identified, which is confirmed by the fact that the extracted spectra of them perfectly match with their pure spectra. In addition, their locations are found in the contribution map even though they are present in a few pixels. What’s more, the proposed strategy does not need any a priori knowledge of the data structure and the class memberships and therefore reduced the studied difficulty and confirmation bias in the analysis of big HSI datasets. Overall, the proposed ESPs-UMAP-HCA method could be a potential approach for food adulteration detection.
Xiangdong Qing,Xinran Wu,Taoxiang Wang,Xiaohua Zhang,Zhiyuan Hu,Xiaohong Zhou,Jie Luan,Rong An
In the work, a novel strategy was developed to characterize and classify Chinese dark tea based on alternating trilinear decomposition combined with uniform manifold approximation and projection (ATLD-UMAP). Firstly, nine active components as targeted analytes were selected to construct qualitative and quantitative models to investigate the performance of ATLD-UMAP analysis of 3D fluorescence data. Spiked sample sets demonstrated that satisfactory results were returned with their average recoveries ranging from (91.4 ± 9.7)% to (109.3 ± 1.5)%. Subsequently, ATLD-UMAP was employed to analyze the contents of analytes in 124 real dark tea samples, revealing the presence of eight active components other than tryptophan with their average contents ranging from 0.22 mg·g −1 to 57.69 mg·g −1 . Finally, ATLD-UMAP was applied to discriminate tea samples produced from different geographical origins and processing depths, and compared with the targeted-based feature component analysis (ATLD-FCA) and the nontargeted-based principal component analysis (ATLD-PCA). The research findings demonstrated that ATLD-UMAP achieved satisfactory classification results (100.0 % accuracy, sensitivity and specificity) in simultaneously identifying dark tea's geographical origin and processing depth. In contrast, ATLD-FCA and ATLD-PCA failed to distinguish them accurately with accuracies of only 68.5 % and 64.8 %, respectively. In a word, ATLD-UMAP provides a new method for rapid authenticity identification in the dark tea industry.
A fluorescent sensor array (FSA) combined with deep learning (DL) techniques was developed for meat freshness real-time monitoring from development to deployment. The array was made up of copper metal nanoclusters (CuNCs) and fluorescent dyes, having a good ability in the quantitative and qualitative detection of ammonia, dimethylamine, and trimethylamine gases with a low limit of detection (as low as 131.56 ppb) in range of 5 ∼ 1000 ppm and visually monitoring the freshness of various meats stored at 4 °C. Moreover, SqueezeNet was applied to automatically identify the fresh level of meat based on FSA images with high accuracy (98.17 %) and further deployed in various production environments such as personal computers, mobile devices, and websites by using open neural network exchange (ONNX) technique. The entire meat freshness recognition process only takes 5 ∼ 7 s. Furthermore, gradient-weighted class activation mapping (Grad-CAM) and uniform manifold approximation and projection (UMAP) explanatory algorithms were used to improve the interpretability and transparency of SqueezeNet. Thus, this study shows a new idea for FSA assisted with DL in meat freshness intelligent monitoring from development to deployment.
危险品化学品经营许可证（带存储）