Optimization of the Sporogenous Medium of Irpex Lacteus Using Artificial Neural Networks and Genetic Algorithms

Artificial neural networks (ANN) and genetic algorithm (GA) were used to optimize sporulation medium components for improving spores concentration in I. lacteus fermentation broth. Single-factor test design was applied to select suitable sporulation medium components and incubation time. Then both response surface methodology (RSM) and artificial neural network (ANN) was applied to explore the optimum sporulation medium of I. lacteus. The results show the medium that consists of 3.78 g/L peptone, 2.44 g/L yeast extract, 4.93 g/L glucose, 0.19 g/L MgSO₄¡·7H₂O and 0.02 g/L VB1. The predictive maximum concentration of spore was 2.51×10⁵ /mL. The average concentration of spores in 3 validation experiments was 2.48×10⁵ /mL. The relative error was 1.19 %. This work found that ANN provided better fits to experimental data than conventional quadratic polynomials.