Authenticity Tracing of Apples According to Variety and Geographical Origin Based on Electronic Nose and Electronic Tongue

Abstract

A combination of electronic nose (EN) and electronic tongue (ET) was used to trace apples according to apple variety and geographical origin by detecting the squeezed juices. A total of 126 apple samples from seven producing regions in China were analyzed. Principal component analysis (PCA) was displayed to get a primary distribution overview of samples. Linear discriminant analysis (LDA), support vector machine (SVM), and partial least squares discriminant analysis (PLS-DA) were carried out to develop discrimination models based on EN dataset, ET dataset, and the fusion dataset. All LDA, SVM, and PLS-DA models achieved satisfactory discrimination performances. The data fusion method made it possible to build a more robust classification model, and the discrimination ability was better than models based on solely EN dataset or ET dataset. The results demonstrated that EN and ET analysis combined with chemometrics was a promising approach for tracing apples and guaranteeing their authenticity.