Machine learning approach for predicting Fusarium culmorum and F. proliferatum growth and mycotoxin production in treatments with ethylene-vinyl alcohol copolymer films containing pure components of essential oils

Tarazona, Andrea; Mateo, Eva M.; Gómez, José V.; Gavara, Rafael; Jiménez, Misericordia; Mateo, Fernando

doi:10.1016/j.ijfoodmicro.2020.109012

Cited by 22 publications

(27 citation statements)

References 63 publications

Supporting

Mentioning

Contrasting

Order By: Relevance

“…One of the strategies and perhaps the most interesting one is the inclusion of EOs or their pure components in packaging systems such as films. Among them, EVOH films have given good results against mycotoxin-producing fungi and on the reduction or total inhibition of ochratoxin A, aflatoxins, fumonisins or zearalenone production [ 37 , 38 , 39 ]. However, according to these studies, the response of toxigenic fungi to EOs or their pure components may vary depending on the fungal species, substrate and environmental conditions.…”

Section: Discussionmentioning

confidence: 99%

“…In addition, EVOH copolymers exhibit a high transparency and interesting mechanical properties [ 34 , 35 , 36 ]. Recently, the ability of EVOH films supplemented with EOs or their pure components to control the growth of some toxigenic fungi and mycotoxin production has been reported [ 37 , 38 , 39 ]. Plastic films supplemented with EOs can be considered as antimicrobial packaging materials and also act as antioxidants.…”

Section: Introductionmentioning

confidence: 99%

“…The parameter used for error estimation, for example, the root-mean square error (RMSE) is averaged over all 10 trials. This decreases bias and variance [ 39 ]. To assess the generalization of the model, a test set not used in the training task is used to evaluate the developed model.…”

Section: Introductionmentioning

confidence: 99%

“…RF are ensembles of decision trees that can be used as nonlinear regression algorithms [ 51 ]. They have been applied in mycology for prediction [ 39 , 44 , 52 , 53 ]. XGBoost has also proven useful in previous mycological studies [ 39 , 53 ].…”

Section: Introductionmentioning

confidence: 99%

“…They have been applied in mycology for prediction [ 39 , 44 , 52 , 53 ]. XGBoost has also proven useful in previous mycological studies [ 39 , 53 ].…”

Section: Introductionmentioning

confidence: 99%

See 4 more Smart Citations

Comparative Analysis of Machine Learning Methods to Predict Growth of F. sporotrichioides and Production of T-2 and HT-2 Toxins in Treatments with Ethylene-Vinyl Alcohol Films Containing Pure Components of Essential Oils

Mateo

Gómez

Tarazona

et al. 2021

Toxins

Self Cite

View full text Add to dashboard Cite

The efficacy of ethylene-vinyl alcohol copolymer films (EVOH) incorporating the essential oil components cinnamaldehyde (CINHO), citral (CIT), isoeugenol (IEG), or linalool (LIN) to control growth rate (GR) and production of T-2 and HT-2 toxins by Fusarium sporotrichioides cultured on oat grains under different temperature (28, 20, and 15 °C) and water activity (aw) (0.99 and 0.96) regimes was assayed. GR in controls/treatments usually increased with increasing temperature, regardless of aw, but no significant differences concerning aw were found. Toxin production decreased with increasing temperature. The effectiveness of films to control fungal GR and toxin production was as follows: EVOH-CIT > EVOH-CINHO > EVOH-IEG > EVOH-LIN. With few exceptions, effective doses of EVOH-CIT, EVOH-CINHO, and EVOH-IEG films to reduce/inhibit GR by 50%, 90%, and 100% (ED50, ED90, and ED100) ranged from 515 to 3330 µg/culture in Petri dish (25 g oat grains) depending on film type, aw, and temperature. ED90 and ED100 of EVOH-LIN were >3330 µg/fungal culture. The potential of several machine learning (ML) methods to predict F. sporotrichioides GR and T-2 and HT-2 toxin production under the assayed conditions was comparatively analyzed. XGBoost and random forest attained the best performance, support vector machine and neural network ranked third or fourth depending on the output, while multiple linear regression proved to be the worst.

show abstract

Section: Discussionmentioning

confidence: 99%

Section: Introductionmentioning

confidence: 99%

Section: Introductionmentioning

confidence: 99%

Section: Introductionmentioning

confidence: 99%

“…They have been applied in mycology for prediction [ 39 , 44 , 52 , 53 ]. XGBoost has also proven useful in previous mycological studies [ 39 , 53 ].…”

Section: Introductionmentioning

confidence: 99%

See 3 more Smart Citations