摘要：AbstractImitating the mechanism of human taste perception, an electronic tongue (ET) system for orange juice quality detection based on internet of things was developed. The system consists of three parts: hand-held detection terminal, wireless communication system and cloud service platform. During the detection, the hand-held detection terminal was used to obtain taste “fingerprint” data from various kinds of juices based on large pulse scanning potential, and then transmitted these data to a cloud service platform through a wireless communication system, as well as the pattern recognition methods were utilized to analyze the data. Finally, the results were compared with the built-in “fingerprint” database of the beverage on the cloud platform so as to obtain the brand or adulteration information of the tested juice. In this study, the developed ET system was further used for the identification of orange juice brand and purity detection. Linear discriminant analysis (LDA) was applied to the qualitative analysis of orange juice with different brand, and the support vector machine (SVM) was used to quantitative forecast of orange juice purity. The result indicated that the LDA can effectively differentiate samples of orange juice with different brand, which the identification accuracy reached 100%; the SVM model possess a good quantitative prediction accuracy for orange juice purity with the root mean square error (RMSE) in prediction set reaching 0.0172. This system possessed the advantages of fast detection, simple operation, low cost, high stability as well as the result was easy to query.
关键词：Keywordsinternet of thingselectronic tonguepattern recognitionorange juice quality
