Click on “Download PDF” for the PDF version or on the title for the HTML version.

If you are not an ASABE member or if your employer has not arranged for access to the full-text, Click here for options.

Application of Artificial Neural Networks for Predicting the Thermal Inactivation of Salmonella sp. and Listeria Inoccua

Published by the American Society of Agricultural and Biological Engineers, St. Joseph, Michigan

Citation:  Paper number  023051,  2002 ASAE Annual Meeting . (doi: 10.13031/2013.10562) @2002
Authors:   Fumihiko Tanaka, Kazuo Morita, Miyako Nishida, Shoko Shinto
Keywords:   Predictive microbiology; Artificial neural networks; Thermal inactivation

This paper focuses on predicting the thermal inactivation time of microorganisms in the chicken meat during microwave heating by artificial neural network (ANN). A comprehensive dataset was prepared using three-dimensional heat transfer simulation model developed and validated by Tanaka et al. (2002). Heat transfer simulation for getting the thermal death/inactivation time (TDT) data was conducted by a 4 x 3 x 4 x 2 x 3 (microwave power level x food initial temperature x sample length x sample width x sample thickness) factorial. After being trained 2 x 105 epochs by backpropagation, the developed ANN models were able to produce very good prediction of the TDT of Salmonella sp. and Listeria inoccua with the minimum standard deviation of mean absolute error of 1.709 and 1.568, respectively.

(Download PDF)    (Export to EndNotes)