A Novel Method Based on Multi-Molecular Infrared (MM-IR) AlexNet for Rapid Detection of Trace Harmful Substances in Flour

Direct Identification and Quantitation of Protein Peptide Powders Based on Multi-Molecular Infrared Spectroscopy and Multivariate Data Fusion

“…Multi-molecular infrared (MM-IR) spectroscopy was a comprehensive methodology, combining spectroscopic analysis methods with novel techniques in chemometrics. Tri-step infrared (IR) spectroscopy had been demonstrated as an effective approach for revealing the main constituents in complicated mixtures and distinguishing the varieties and contents of chemical constituents in highly similar matrices, − for example, quality evaluation of surimi, identification and quantitative analysis of small clear proteins, overall analysis and identification of flour types, advantages and disadvantages, and quantitative analysis of specific components (illegal additives, mycotoxins) therein, ,, origin and vintage traceability identification of wine, and quantification of multiple components, and rapid and accurate identification of foodborne pathogenic bacteria with different mixing ratios and different mixing types, etc. It integrated one-dimensional IR spectroscopy, second derivative infrared (SD-IR) spectroscopy, and two-dimensional correlation IR spectroscopy (2DCOS-IR) with progressively higher resolution, and it employed to directly identify flour with diverse harmful substances, which is more suitable for the establishment of the model and has high accuracy .…”

“…It integrated onedimensional IR spectroscopy, second derivative infrared (SD-IR) spectroscopy, and two-dimensional correlation IR spectroscopy (2DCOS-IR) with progressively higher resolution, and it employed to directly identify flour with diverse harmful substances, which is more suitable for the establishment of the model and has high accuracy. 23 Chemometrics maximized the extraction of useful chemical information to achieve a better description and prediction of the natural sciences, which was widely used as a multivariate statistical analysis tool for food quality evaluation and identification, including adulteration identification, traceability, and grade evaluation 28−31 generally by building classification and regression models for qualitative and quantitative analyses, such as principal component analysis (PCA), support vector machine (SVM), k-nearest neighbor (KNN), back propagation neural network (BPNN), and partial least squares regression (PLSR). 29,32−36 Data fusion strategies integrated multiple sources of information to perform automatic detection, correlation, estimation, combination processing, etc., resulting in a more accurate explanation or description of the interrogated objects, which improved the accuracy of adulteration identification, geographical traceability, and rapid determination of composition from the realm of food to biomedicine.…”

“…Tri-step infrared (IR) spectroscopy had been demonstrated as an effective approach for revealing the main constituents in complicated mixtures and distinguishing the varieties and contents of chemical constituents in highly similar matrices, − for example, quality evaluation of surimi, identification and quantitative analysis of small clear proteins, overall analysis and identification of flour types, advantages and disadvantages, and quantitative analysis of specific components (illegal additives, mycotoxins) therein, ,, origin and vintage traceability identification of wine, and quantification of multiple components, and rapid and accurate identification of foodborne pathogenic bacteria with different mixing ratios and different mixing types, etc. It integrated one-dimensional IR spectroscopy, second derivative infrared (SD-IR) spectroscopy, and two-dimensional correlation IR spectroscopy (2DCOS-IR) with progressively higher resolution, and it employed to directly identify flour with diverse harmful substances, which is more suitable for the establishment of the model and has high accuracy . Chemometrics maximized the extraction of useful chemical information to achieve a better description and prediction of the natural sciences, which was widely used as a multivariate statistical analysis tool for food quality evaluation and identification, including adulteration identification, traceability, and grade evaluation − generally by building classification and regression models for qualitative and quantitative analyses, such as principal component analysis (PCA), support vector machine (SVM), k -nearest neighbor (KNN), back propagation neural network (BPNN), and partial least squares regression (PLSR). ,− …”