Starch‐based edible films are gaining huge interest in food packaging industries. In the present work, avocado seed starch (ASS) was extracted and used to develop an edible film. The influence of four important process factors, starch, agar, sorbitol, and Tween‐20, was studied on one of the important barrier properties, water‐vapor permeability (WP), of developed edible film. The three‐level RSM design with Box–Behnken approach was carried out to investigate the film property, WP. ASS‐based edible films were prepared by the casting method. The results revealed that the increment in the contents of Tween‐20 and sorbitol reduces the WP of the film. Using the response surface analysis, the effect of the aforementioned factors was analyzed; they showed significant impact on WP. To predict the influence of the selected process parameters, a second‐order polynomial equation was constructed. Additionally, Pareto analysis of variance was employed over the obtained results to investigate the significance of the developed process model.

In vitro, sterilization is one of the key components for proceeding with plant tissue cultures. Since the effectiveness of sterilization has a direct impact on the culture's final outcomes, there is a crucial need for optimization of the sterilization process. However, compared with traditional optimizing methods, the use of computational approaches through artificial intelligence-based process modeling and optimization algorithms provides a precise optimal condition for in vitro culturing. This study aimed to optimise in vitro sterilization of grape rootstock 3309C using RSM, ANN, and genetic algorithm (GA) techniques. In this context, two output responses, namely, Clean Culture and Explant Viability, were optimised using the models developed by RSM and ANN, followed by a GA, to obtain a globally optimal solution. The most influential independent factors, such as HgCl₂, NaOCl, AgNO₃, and immersion time, were considered input variables. The significance of the developed models was investigated with statistical and non-statistical techniques and was optimised to determine the significance of selected inputs. The optimal clean culture of 91%, and the explant viability of 89% can be obtained from 1.62% NaOCl at a 13.96 min immersion time, according to MLP-NSGAII. Sensitivity analysis revealed that the clean culture and explant viability were less sensitive to AgNO₃ and more sensitive to immersion time. Results showed that the differences between the GA predicted and validation data were significant after the performance validation of predicted and optimised sterilising agents with immersion time combinations were tested. In general, GA, a potent methodology, may open the door to the development of new computational methods in plant tissue culture.

Gesho (Rhamnus prinoides) is a medicinal plant with antioxidant and anti-inflammatory activities commonly used in the ethnomedicinal systems of Africa. Using a three-layer neural network, four culture conditions viz., concentration of agar, duration of light exposure, temperature of culture, and relative humidity were used to calculate the callus differentiation rate of gesho. With the ability to quickly identify optimal solutions using high-speed computers, synthetic neural networks have emerged as a rapid, reliable, and accurate fitting technique. They also have the self-directed learning capability that is essential for accurate prediction. The network's final architecture for four selected variables and its performance has been confirmed with high correlation coefficient (R², 0.9984) between the predicted and actual outputs and the root-mean-square error of 0.0249, were developed after ten-fold cross validation as the training function. In vitro research had been conducted using the genetic algorithm’s suggestions for the optimal culture conditions. The outcomes demonstrated that the actual gesho differentiation rate was 93.87%, which was just 1.86% lesser than the genetic algorithm's predicted value. The projected induced differentiation rate was 87.62%, the actual value was 84.79%, and the predicted value was 2.83% higher than Response Surface Methods optimisation. The environment for the growth of plant tissue can be accurately and efficiently optimised using a genetic algorithm and an artificial neural network. Further biological investigations will presumably utilise this technology.