Optimization of ultrasound-assisted extraction of phenolic-saponin content from Carthamus caeruleus L. rhizome and predictive model based on support vector regression optimized by dragonfly algorithm

Jujube stones based highly efficient activated carbon for methylene blue adsorption: Kinetics and isotherms modeling, thermodynamics and mechanism study, optimization via response surface methodology and machine learning approaches

“…Where X i is the actual value of the ith variable; x i is the coded value of X i ; X 0 is the actual value of X i at the center point, and ΔX i is the step change (Han et al 2013;Moussa et al 2022).…”

“…The knowledge of each Kernel function was also optimized for their specific parameters (Kernel Scale [sigmaM, sigmaF] and sigma) (see Figure 1). For this, the dragonfly algorithm was used to optimize the specific parameters of each Kernel function, since this optimization algorithm has been used to solve a wide variety of optimization problems including solving different machine learning optimization problems (Moussa et al 2022). Numerous studies have proved that machine learning performance has been improved when the hyper-parameters were optimized using the Dragonfly algorithm (Moussa et al 2022).…”

“…In order to improve the performance of the previously developed model, especially in the validation phase, the GPR model was coupled to the Dragonfly (DA) algorithm, which was used to optimize the specific parameters of each Kernel function, since this optimization algorithm has been used to solve a wide variety of optimization problems (Moussa et al 2022). Among these solving different machine learning optimization problems, fundamental values and penalty parameters were optimized by the DA using training data (Moussa et al 2022). It was confirmed by numerous studies that machine learning performance was improved when hyper-parameters were optimized using the Dragonfly algorithm (Moussa et al 2022).…”

Box–Behnken design for the optimisation of Kabachnik–Fields reaction catalysed by natural kaolinite clay under eco-friendly conditions

“…This means that the Box-Behnken design can save time and reagents. [42][43][44][45][46][47][48][49] This design is tailored for factors at three levels, allowing for a more thorough exploration of the effects of factors not only at low and high levels but also at the medium level.…”

Ultrasound‐assisted protein extraction from mosambi peel support vector regression and genetic algorithm‐based modeling and optimization

“…SVR performs linear regression in the higher dimension and tries to fit the best line within the predefined error range. Due to their advantages, SVR has been used for predictive modeling of many foods' process like drying (Qadri et al, 2020; Qu et al, 2020), the mass of fruits (Abdel‐Sattar et al, 2021), extraction (Moussa et al, 2022; Wang et al, 2018), encapsulation (Tao et al, 2017), de‐bittering (Younis et al, 2019), characterization (Ciaburro et al, 2021), etc. A genetic algorithm is a global search optimization technique inspired by a species' genetic evolution.…”