An Extended NRBF Model for the Detection of Meat Spoilage

A fast non-invasive detection of spoilage microorganisms in meat, using Fourier transform infrared spectroscopy (FTIR) and Extended Normalized Radial Basis Function neural networks has been proposed in this paper. The aim is to associate spectral data with microbiological data (log counts), for Total Viable Counts, Pseudomonas spp., Lactic Acid Bacteria and Enterobacteriaceae by predicting their micro-biological population from FTIR spectra. The dimensionality reduction of spectral data has been explored by the implementation of a fuzzy principal component algorithm, while produced results confirmed the superiority of the proposed method compared to multilayer perceptron neural networks used recently in the area of food microbiology.