Chemometrics in food science - a demonstration of the feasibility of a highly exploratory, inductive evaluation strategy of fundamental scientific significance
L. Munck et al., Chemometrics in food science - a demonstration of the feasibility of a highly exploratory, inductive evaluation strategy of fundamental scientific significance, CHEM INTELL, 44(1-2), 1998, pp. 31-60
At the roots of science lies observation and data collection from the world
as is and from which conclusions can be induced after classification. This
is far from the present theory-driven, deductive, normative stage of scien
ce which depends heavily on modelling discrete functional factors in labora
tory experiments and suppresses the aspect of interaction. In spite of its
successes, science today has great difficulty in adapting to the changes wh
ich technology has created to cope with registering and evaluating real dat
a from the world, such as in food production chains. This paper demonstrate
s that it is possible and profitable with the help of new technology to rei
ntroduce an explorative, inductive strategy to investigate the chemistry of
a complex food process as is with a minimum of a priori assumptions. The f
ood process investigated is a sugar plant and the tools necessary in this s
trategy include a multivariate screening method (fluorescence spectroscopy)
, an arsenal of chemometric models (PCA, PLS, principal variables), includi
ng multiway models (PARAFAC, Tucker), and a computer. Not only can chemical
criteria and process parameters throughout the process be validly predicte
d by the screening method, but process irregularities as well as chemical s
pecies can also be detected and validated by multiway chemometric technique
s. Inspired by examples from the food area, the paper further discusses the
nature of the exploration method in the selection of tools and data. The a
im is to study complex processes as a whole in order to model interaction o
f the underlying latent functional factors which may later be defined more
precisely by deductive methods. These methods in combination with an approp
riate multivariate screening method allow for unique identification of obje
cts-a significant prerequisite for a viable, exploratory, inductive data st
rategy which is needed as a fundamental complement to prevalent normative r
esearch in order to obtain a science on the interdisciplinary level. (C) 19
98 Elsevier Science B.V. All rights reserved.