ABSTRACT
This chapter discusses the application of Artificial neural networks (ANN) in food quality using Hyperspectral imaging technique (HIT) data. ANN are a set of mathematical nonlinear tools that allow to model complex systems. ANNs are computational networks which attempt to simulate, in a highly simplified model, the networks of nerve cells of the biological central nervous system. ANN architecture is usually represented by a graph where units operating on the same input variables are organized in layers, while the weights that modulate the combination of the nonlinear functions are represented as lines connecting units in different layers. Spectral spatial data generated by HIT require the application of chemometric techniques for its analysis in order to carry out food quality control. Hyperspectral imaging systems emerged in land-related research and subsequently extended to other fields of science including food technology.
