Improved Pullulan Production and Process Optimization Using Novel GA–ANN and GA–ANFIS Hybrid Statistical Tools

Abstract

Pullulan production from Aureobasidium pullulans was explored to increase yield. Non-linear hybrid mathematical tools for optimization of process variables as well as the pullulan yield were analyzed. The one variable at a time (OVAT) approach was used to optimize the maximum pullulan yield of 35.16 ± 0.29 g/L. The tools predicted maximum pullulan yields of 39.4918 g/L (genetic algorithm coupled with artificial neural network (GA–ANN)) and 36.0788 g/L (GA coupled with adaptive network based fuzzy inference system (GA–ANFIS)). The best regression value (0.94799) of the Levenberg–Marquardt (LM) algorithm for ANN and the epoch error (6.1055 × 10−5) for GA–ANFIS point towards prediction precision and potentiality of data training models. The process parameters provided by both the tools corresponding to their predicted yield were revalidated by experiments. Among the two of them GA–ANFIS results were replicated with 98.82% accuracy. Thus GA–ANFIS predicted an optimum pullulan yield of 36.0788 g/L with a substrate concentration of 49.94 g/L, incubation period of 182.39 h, temperature of 27.41 °C, pH of 6.99, and agitation speed of 190.08 rpm.

Modeling of Carbon Dioxide Fixation Rate by Micro Algae Using Hybrid Artificial Intelligence and Fuzzy Logic Methods and Optimization by Genetic Algorithm

“…(Saraswat et al 2013). If the fitness values differ too extensively, the individuals with the least values replicate instantly, taking over the population gene pool too swiftly and preventing the GA from searching other areas of the solution space (Badhwar et al 2020;Armaghani et al 2019).…”

“…In the present study the elite count is 3 which signifies the number of individuals with the best fitness values in the present generation that are guaranteed to survive to the next generation. These individuals are better known as the elite children (Badhwar et al 2020;Kumar et al 2019).…”

“…The best fitness plot for the GA maps the convergence of the best fitness values of successive generations towards the final optimum value as shown in Figure 11c. In the present study, the population size is set to 100 (Badhwar et al 2020;Kumar et al 2019). Increasing the population size permits the genetic algorithm to explore more points and as a way to obtain a better result (Momeni et al 2014;Armaghani et al 2019).…”

“…The selection method used in the present study is stochastic uniform an individual can be chosen as a parent several times; in which case it gives its genes to multiple children. GA from searching other areas of the solution space (Badhwar et al 2020;Armaghani et al 2019).…”

Modeling and optimization of microwave puffing of rice using artificial neural network and genetic algorithm

“…The principle of GA involves the simulation of biological evolutionary processes based on genetics (crossover and mutation). Optimization based on integrated ANN-GA was applied in various food processing applications such as optimization of process variables for pullulan yield (Badhwar et al, 2020;Badhwar, Kumar, & Dubey, 2019), brewing process (Takahashi, Coelho de Oliveira, Fernández Núñez, & Rocha, 2019), fluidized bed drying of green tea leaves (Kalathingal, Basak, & Mitra, 2020), and tannase enzyme aided extraction of cashew apple juice (Abdullah, Pradhan, Aflah, & Mishra, 2020). However, minimal research had been carried out on both microwave rice puffing and process parameter optimization of the microwave puffing process.…”