Marker-Independent Food Identification Enabled by Combing Machine Learning Algorithms with Comprehensive GC × GC/TOF-MS

• Published in: Molecules (Basel, Switzerland) Vol. 27; no. 19; p. 6237
• Main Authors: Li, Bei, Liu, Miao, Lin, Feng, Tai, Cui, Xiong, Yanfei, Ao, Ling, Liu, Yumin, Lin, Zhixin, Tao, Fei, Xu, Ping
• Format: Journal Article
• Language: English
• Published: Basel MDPI AG 22.09.2022; MDPI
• Subjects: Algorithms; Chemicals; Chinese liquors; Chromatography; Comparative analysis; Consumption; Data mining; Datasets; Dimensional analysis; Food; Food inspection; Food products; GC × GC/TOF-MS; Geographical distribution; Identification; Identification methods; Inspection; Instrument industry; Learning algorithms; Liquor; Liquors; Machine learning; Mass spectrometry; Methods; Sample preparation; Scientific imaging; Solid phase methods; Statistical analysis; Support vector machines; Tea; United States; China
• ISSN: 1420-3049; 1420-3049
• DOI: 10.3390/molecules27196237

Reliable methods are always greatly desired for the practice of food inspection. Currently, most food inspection techniques are mainly dependent on the identification of special components, which neglect the combination effects of different components and often lead to biased results. By using Chinese liquors as an example, we developed a new food identification method based on the combination of machine learning with GC × GC/TOF-MS. The sample preparation methods SPME and LLE were compared and optimized for producing repeatable and high-quality data. Then, two machine learning algorithms were tried, and the support vector machine (SVM) algorithm was finally chosen for its better performance. It is shown that the method performs well in identifying both the geographical origins and flavor types of Chinese liquors, with high accuracies of 91.86% and 97.67%, respectively. It is also reasonable to propose that combining machine learning with advanced chromatography could be used for other foods with complex components.