Modeling composed nanoparticles of chitosan-N-acetylene-L-cysteine with support vector regression

The process of nanoemulsion was improved by optimizing the concentration of chitosan-N-acetylene-L-cysteine and sodium tripolyphosphate and the volume ratio between the two components. The prepared formulations were characterized in terms of particle size. Support vector regression (SVR) was built up and used to identify the parameters which could influence the particle size of the nanoemulsion. Data were divided into calibration and validation sets and then were modeled by SVR. It was found that the developed model was of high quality. This model was then used to explore the effect of composition and processing factors on the particle size of the nanoemulsion preparation. This study demonstrated that the SVR model may be used to optimize critical parameters to control preparation of this system and to obtain a dominant factor to control the final particle size.The process of nanoemulsion was improved by optimizing the concentration of chitosan-N-acetylene-L-cysteine and sodium tripolyphosphate and the volume ratio between the two components. The prepared formulations were characterized in terms of particle size. Support vector regression (SVR) was built up and used to identify the parameters which could influence the particle size of the nanoemulsion. Data were divided into calibration and validation sets and then were modeled by SVR. It was found that the developed model was of high quality. This model was then used to explore the effect of composition and processing factors on the particle size of the nanoemulsion preparation. This study demonstrated that the SVR model may be used to optimize critical parameters to control preparation of this system and to obtain a dominant factor to control the final particle size.