Unsupervised classification methods in food sciences: discussion and outlook

Abstract

This paper reviews three unsupervised multivariate classification methods: principal component analysis, principal component similarity analysis and heuristic cluster analysis. The theoretical basis of each method is presented in brief, and assumptions inherent to the methods are highlighted. A literature review shows that these methods have sometimes been used inappropriately or without referencing all essential parameters. The paper also brings to the attention of the reader a relatively unknown method: probabilistic or model-based cluster analysis. The goal of this method is to uncover the true classification of objects rather than a convenient classification provided by the other methods. For this reason it is felt that model-based cluster analysis will have broad application in the future.

Monitoring the authenticity of Brazilian UHT milk: A chemometric approach

“…However, it is necessary to consider the reality of each region and their respective problems, as well as the producers' level of knowledge on obtaining milk and on adopting quality systems in the milk processing in industrial units. Indeed, regulatory agencies may use groupings to establish food authenticity in terms of geographical region or biological source, or to detect adulteration of foods that have specific identities or legislated standards (Kozac & Scaman, 2008). These directions also are valid for food products consumed routinely, as is the case of the UHT milk for Brazilian people.…”

Discrimination of Luzhou -flavoured fresh raw liquor distilled from Zaopei fermented in new, trend to-be aged and aged pit mud based on their aroma and flavour compounds

“…Methanoic acid [2], butanoic acid [5], pentanoic acid [7], pelargonic acid [12], acetaldehyde [15], 2-butanol [25] and 3-methyl-3-buten-1-ol [31] were strongly correlated with N1 and N2. In terms of liquor from aged pit mud, many aroma and flavour compounds contributed to their specificity; isobutyraldehyde [14], 1-propanal [ Combining the results of GC × GC/TOF-MS with PCA-X and GC-FID and LC-MS with PLS-DA, the specific markers of fresh raw liquor distilled from Zaopei fermented in aged pit mud were 1hexanol, ethyl pentanoate and 2-pentanone, while those in new pit mud were 2-butanol and butanoic acid. 1-Hexanol has a floral and green aroma (29), and has been found to be the most abundant higher alcohol in four brands of Luzhou-flavoured liquors (30).…”

Near-infrared spectroscopy for rapid classification of fruit spirits

“…Classification of objects using PCA is done by constructing two-or threedimensional plots, using PCs chosen by the researcher. The number of principal components was based on the eigenvalue criterion and the total variance explained (Kozak and Scaman 2008).…”