Food product safety is one of the most promising areas for the application of electronic noses. During the last twenty years, these sensor-based systems have made odour analyses possible. Their application into the area of food is mainly focused on quality control, freshness evaluation, shelf-life analysis and authenticity assessment. In this paper, the performance of a portable electronic nose has been evaluated in monitoring the spoilage of beef fillets stored either aerobically or under modified atmosphere packaging, at different storage temperatures. A novel multi-output fuzzy wavelet neural network model has been developed, which incorporates a clustering pre-processing stage for the definition of fuzzy rules. The dual purpose of the proposed modelling approach is not only to classify beef samples in the relevant quality class (i.e. fresh, semi-fresh and spoiled), but also to predict their associated microbiological population. Comparison results against advanced machine learning schemes indicated that the proposed modelling scheme could be considered as a valuable detection methodology in food microbiology.
展开▼
