Application of neural networks as a non-linear modelling technique in food mycology

dc.contributor.author	Panagou, EZ	en
dc.contributor.author	Kodogiannis, VS	en
dc.date.accessioned	2014-06-06T06:49:12Z
dc.date.available	2014-06-06T06:49:12Z
dc.date.issued	2009	en
dc.identifier.issn	09574174	en
dc.identifier.uri	http://dx.doi.org/10.1016/j.eswa.2007.09.022	en
dc.identifier.uri	http://62.217.125.90/xmlui/handle/123456789/4485
dc.subject	Modelling	en
dc.subject	Neural networks	en
dc.subject	Polynomial regression	en
dc.subject	Predictive mycology	en
dc.subject.other	Artificial intelligence	en
dc.subject.other	Mathematical models	en
dc.subject.other	Microbiology	en
dc.subject.other	Microorganisms	en
dc.subject.other	Network protocols	en
dc.subject.other	pH effects	en
dc.subject.other	Sensor networks	en
dc.subject.other	Statistical methods	en
dc.subject.other	Vegetation	en
dc.subject.other	Animal feeding	en
dc.subject.other	Coefficient of determination	en
dc.subject.other	Enumeration techniques	en
dc.subject.other	Experimental data	en
dc.subject.other	Fungal growth	en
dc.subject.other	Joint effect	en
dc.subject.other	Microbial growth	en
dc.subject.other	Modelling	en
dc.subject.other	Monascus	en
dc.subject.other	Non-linear	en
dc.subject.other	PH levels	en
dc.subject.other	Polynomial modeling	en
dc.subject.other	Polynomial regression	en
dc.subject.other	Predictive micro-biology	en
dc.subject.other	Predictive mycology	en
dc.subject.other	Specific growth rate	en
dc.subject.other	Statistical indices	en
dc.subject.other	Statistical modelling	en
dc.subject.other	Neural networks	en
dc.title	Application of neural networks as a non-linear modelling technique in food mycology	en
heal.type	journalArticle	en
heal.identifier.primary	10.1016/j.eswa.2007.09.022	en
heal.publicationDate	2009	en
heal.abstract	Fungal growth leads to spoilage of food and animal feeds and to formation of mycotoxins and potentially allergenic spores. There is a growing interest in modelling microbial growth as an alternative to time-consuming, traditional, microbiological enumeration techniques. Several statistical models have been reported to describe the growth of different micro-organisms however the nature of neural networks, as highly non-linear approximator schemes, considers them as an alternative methodology. The application of neural networks in predictive microbiology is presented in this paper. This technique was used to build up a model of the joint effect of water activity, pH level and temperature to predict the maximum specific growth rate of the ascomycetous fungus Monascus ruber. Neural network and polynomial models were compared against the experimental data using six statistical indices namely, coefficient of determination (R2), root mean square error (RMSE), mean relative percentage error (MRPE), mean absolute percentage error (MAPE), standard error of prediction (SEP), bias (Bf) and accuracy (Af) factors. Graphical plots were also used for model comparison. The performance of the learning-based systems provide encouraging results while sensitivity analysis showed that from the three environmental factors the most influential on fungal growth was temperature, followed by water activity and pH to a lesser extend. Neural networks offer an alternative and powerful technique to model microbial kinetic parameters and could thus become an additional tool in predictive mycology. © 2007 Elsevier Ltd. All rights reserved.	en
heal.journalName	Expert Systems with Applications	en
dc.identifier.issue	1	en
dc.identifier.volume	36	en
dc.identifier.doi	10.1016/j.eswa.2007.09.022	en
dc.identifier.spage	121	en
dc.identifier.epage	131	en