Validating an artificial neural network model of Leuconostoc mesenteroides in vacuum packaged sliced cooked meat products for shelf-life estimation

• Published in: European food research & technology Vol. 221; no. 5; pp. 717 - 724
• Main Authors: Zurera-Cosano, G, Garcia-Gimeno, R.M, Rodriguez-Perez, M.R, Hervas-Martinez, C
• Format: Journal Article
• Language: English; German
• Published: Heidelberg Springer 01.10.2005; Berlin Springer Nature B.V
• Subjects: Bacteria; bacterial contamination; Biological and medical sciences; breast muscle; chicken meat; cooked foods; food contamination; Food industries; food storage; Fundamental and applied biological sciences. Psychology; General aspects; ham; Handling, storage, packaging, transport; kinetics; Leuconostoc mesenteroides; Meat and meat product industries; Meat products; meat quality; microbial growth; model validation; Neural networks; Population density; prediction; shelf life; sodium chloride; sodium nitrite; storage quality; storage temperature; turkey meat; vacuum packaging; Validation; Cooked meat products; Leuconostoc mesenteroides; Estimation; Meat product; Shelf life; Vacuum packaging; Neural network; Streptococcaceae; Predictive microbiology; Model validation; Food preservation; Bacteria; Micrococcales; Models; Conditioning; Artificial neural network
• ISSN: 1438-2377; 1438-2385
• DOI: 10.1007/s00217-005-0006-1

An Artificial Neural Network-based predictive model (ANN) for Leuconostoc mesenteroides growth in response to temperature, pH, sodium chloride and sodium nitrite, developed by Garcia-Gimeno et al. [Int. J. Food Microbiol. (2005)]) was validated on vacuum packed, sliced, cooked meat products and applied to shelf-life determination. Lag-time (Lag), growth rate (Gr), and maximum population density (yEnd) of L. mesenteroides, estimated by the ANN model, were compared to those observed in vacuum-packed cooked ham, turkey breast meat, and chicken breast meat stored at 10.5°C, 13.5°C and 17.7°C, using bias and accuracy factors. The ANN model provided reliable estimates for the three kinetic parameters studied; with a bias factor of 1.09; 0.73 and 1.00 for Lag, Gr and yEnd, respectively and an accuracy factor of 1.26; 1.58 and 1.13 for Lag, Gr and yEnd, respectively. From the three kinetic parameters obtained by the ANN model, commercial shelf-life were estimated for each temperature and compared with the tasting panel evaluation. The commercial shelf life estimated microbiologically, i.e. times to reach 10⁶.⁵ cfu/g, was shorter than the period estimated using sensory methods.