Modeling and Optimizing in vitro Sterilization of Chrysanthemum via Multilayer Perceptron-Non-dominated Sorting Genetic Algorithm-II (MLP-NSGAII).

摘要: In vitro sterilization is a primary step of plant tissue culture which the ultimate results in are directly depended on efficiency sterilization. Artificial intelligence models combination optimization algorithms could be beneficial computational approaches for modeling and optimizing culture. The aim this study was chrysanthemum, as case study, through Multilayer Perceptron- Non-dominated Sorting Genetic Algorithm-II (MLP-NSGAII). MLP used two outputs including contamination frequency (CF), explant viability (EV) based seven variables HgCl2, Ca(ClO)2, Nano-silver, H2O2, NaOCl, AgNO3, immersion times. Subsequently, were linked to NSGAII process, importance each input evaluated by sensitivity analysis. Results showed all R2 training testing data over 94%. According MLP-NSGAII, optimal CF (0%), EV (99.98%) can obtained from 1.62% NaOCl at 13.96 min time. analysis that more sensitive time less AgNO3. performance predicted optimized sterilants × times tested, indicated differences between validation negligible. Generally, MLP-NSGAII powerful methodology may pave way establishing new strategies