This study investigated the effects of various disinfectants and immersion time on in vitro seed sterilization and germination of petunia. The utility of three artificial neural networks (ANNs) as modeling tools was also evaluated. The results showed that the GRNN algorithm displayed superior predictive accuracy compared to the MLP and RBF models. The non-dominated sorting genetic algorithm-II (NSGA-II) was reliable for optimizing the disinfectant concentration and immersion time.
The process of optimizing in vitro seed sterilization and germination is a complicated task since this process is influenced by interactions of many factors (e.g., genotype, disinfectants, pH of the media, temperature, light, immersion time). This study investigated the role of various types and concentrations of disinfectants (i.e., NaOCl, Ca(ClO)(2), HgCl2, H2O2, NWCN-Fe, MWCNT) as well as immersion time in successful in vitro seed sterilization and germination of petunia. Also, the utility of three artificial neural networks (ANNs) (e.g., multilayer perceptron (MLP), radial basis function (RBF), and generalized regression neural network (GRNN)) as modeling tools were evaluated to analyze the effect of disinfectants and immersion time on in vitro seed sterilization and germination. Moreover, non-dominated sorting genetic algorithm-II (NSGA-II) was employed for optimizing the selected prediction model. The GRNN algorithm displayed superior predictive accuracy in comparison to MLP and RBF models. Also, the results showed that NSGA-II can be considered as a reliable multi-objective optimization algorithm for finding the optimal level of disinfectants and immersion time to simultaneously minimize contamination rate and maximize germination percentage. Generally, GRNN-NSGA-II as an up-to-date and reliable computational tool can be applied in future plant in vitro culture studies.
作者
我是这篇论文的作者
点击您的名字以认领此论文并将其添加到您的个人资料中。
推荐
暂无数据