Journal
INDUSTRIAL CROPS AND PRODUCTS
Volume 65, Issue -, Pages 7-13Publisher
ELSEVIER SCIENCE BV
DOI: 10.1016/j.indcrop.2014.11.039
Keywords
Artificial neural network (ANN); Aspergillus jiavus; Cinnamomum cassia; Response surface methodology (RSM); Thymus vulgaris
Categories
Funding
- Ministry of Education, Science and Technological Development of the Republic of Serbia [01175034]
Ask authors/readers for more resources
Antifungal effect of individual thyme (Thymus vulgaris L) and cinnamon (Cinnamomum cassia L.) essential oils (EOs) and mixture of thereof on Aspergillus flavus spores was investigated. In order to optimize the process variables (time of action, concentration of individual or mixture EOs and their mass ratio) for the antifungal effect of EO mixture, two models were developed: the response surface methodology (RSM) and artificial neural network (ANN) combined with genetic algorithm (GA). In RSM model, three factors were involved in Box-Behnken design that was applied for the experiment. Based on the mean relative percent deviation (MRPD), both models provided a good quality prediction for the antifungal effect in terms of all three process variables. RSM and ANN-GA techniques predicted the 0.5% as an optimum percentage concentration of EO mixture in EOs mass ratio T. vulgaris:C. cassia 1:1, ensuring the highest antifungal effect of 95.8% and 96.4% after 65 min. Both models were found useful for the optimization of the antifungal effect in vitro. ANN-GA was found more accurate in comparison to RSM due to its lower value of MRPD. Therefore, ANN-GA can be generally used for optimization and prediction of antimicrobial effects of 605 and their mixtures. (C) 2014 Elsevier B.V. All rights reserved.
Authors
I am an author on this paper
Click your name to claim this paper and add it to your profile.
Reviews
Recommended
No Data Available