An adaptive neuro-fuzzy identification model for the detection of meat spoilage

Abstract

In food industry, safety and quality are considered important issues worldwide that are directly related to health and social progress. To address the rapid and non-destructive detection of meat spoilage microorganisms during aerobic storage at chill and abuse temperatures, Fourier transform infrared (FTIR) spectroscopy with the aid of a neuro-fuzzy identification model has been considered in this research. FTIR spectra were obtained from the surface of beef samples, while microbiological analysis determined the total viable count for each sample. The dual purpose of the proposed modelling approach is not only to classify beef samples in the respective quality class (i.e. fresh, semi-fresh and spoiled), but also to predict their associated microbiological population directly from FTIR spectra. The proposed model utilises a prototype defuzzification scheme, whereas the number of input membership functions is directly associated to the number of rules, reducing thus, the curse of dimensionality problem. Results confirmed the advantage of the proposed scheme against the adaptive neuro-fuzzy inference system (ANFIS), in terms of prediction accuracy and structure simplicity. Subsequent comparison against multilayer perceptron (MLP) and partial least squares technique indicated that FTIR spectral information in combination with the proposed modelling scheme could be considered as an alternative methodology for the accurate evaluation of meat spoilage.