Development and validation of a neural network model for growth of
            <i>Salmonella</i>
            Newport from chicken on cucumber for use in risk assessment

Oscar, Thomas P.

doi:10.1111/jfpp.15819

Cited by 5 publications

(4 citation statements)

References 47 publications

Supporting

Mentioning

Contrasting

Order By: Relevance

“…For example, frozen storage (À20 to 0 C for 0-12 months), refrigerated storage (1-18 C for 14 days), and meal preparation (16-40 C for 0-8 hr). This would allow use of the same sampling times within each model, which would simplify model development and validation (Oscar, 2009(Oscar, , 2021.…”

Section: Discussionmentioning

confidence: 99%

“…In addition, it was based on the convention used in Com-Base (Baranyi & Tamplin, 2004). Based on previous studies (Oscar, 2009(Oscar, , 2014(Oscar, , 2017a(Oscar, , 2017b(Oscar, , 2018a(Oscar, , 2018b(Oscar, , 2021, data were tagged for testing as follows: (a) for a time course of 30 days at 9 and 21 days; (b) for a time course of 14 days at 4, 9, and 13 days; and (c) for a time course of 3 days at 1 and 2.25 days. This resulted in 270 (82%) data for training and 58 (18%) data for testing the ANN during training.…”

Section: Data Source and Descriptionmentioning

confidence: 99%

“…In the past, ANN was difficult to use in predictive microbiology applications. However, with the arrival of commercial software programs, it is now easy to develop ANN models for foodborne pathogens (Oscar, 2009(Oscar, , 2014(Oscar, , 2017a(Oscar, , 2017b(Oscar, , 2018a(Oscar, , 2018b(Oscar, , 2021.…”

Section: Introductionmentioning

confidence: 99%

“…Finally, over-training can be avoided by following the criteria of the APZ method when developing and validating ANN (Oscar, 2017b(Oscar, , 2018a(Oscar, , 2018b(Oscar, , 2020a(Oscar, , 2021. Thus, there is no reason not to use ANN in predictive microbiology applications.…”

Section: Introductionmentioning

confidence: 99%

See 3 more Smart Citations

Use of ComBase data to develop an artificial neural network model for nonthermal inactivation of Campylobacter jejuni in milk and beef and evaluation of model performance and data completeness using the acceptable prediction zones method

Boleratz

Oscar

2022

Journal of Food Safety

Self Cite

View full text Add to dashboard Cite

ComBase is a widely used microbial modeling database. ComBase data can be used to develop and validate models and to test novel modeling methods like artificial neural networks (ANN) and acceptable prediction zones (APZ), which have been shown to outperform traditional methods. Here, ComBase data were used to evaluate the ANN and APZ methods for modeling nonthermal inactivation of Campylobacter jejuni in milk and beef as a function of time, temperature (À20, 1, 10, 20, 30, and 40 C), and strain (18177, ATCC 29428). Four ANN were developed using Excel and Neu-ralTools, and the best-performing was a general regression neural network (GRNN) whose performance and data completeness were evaluated using the APZ method.Relative variable impacts in the GRNN model were 42.5%, 31.5%, 20.1%, and 5.9% for time, temperature, food, and strain, respectively. Nonthermal inactivation of C. jejuni was faster and greater at ambient than at cold temperatures and in milk than in beef except at 1 C where it was similar. The proportion of residuals in the APZ (pAPZ) ranged from 0.77 to 1 for individual nonthermal inactivation curves. Although the model had acceptable performance (pAPZ ≥0.7), it failed validation because of data gaps like one instead of four replicates per combination of independent variables and no data at À10 C. Thus, these and other data gaps identified need to be filled before the model can be used with confidence to predict behavior of C. jejuni in milk and beef. Nonetheless, results indicated that ANN and APZ methods can be used to model data for nonthermal inactivation of C. jejuni in food.

show abstract

Section: Discussionmentioning

confidence: 99%