Compact Firefly Algorithm with Deep Learning Based Chromatic Condition Predictive Model for Organic Synthesis Purification

Abstract

Chromatography is an effective method utilized in organic synthesis to purify and separate chemical compounds. There are many features which affect the efficacy and efficiency of chromatography, comprising the kind of chromatography utilized, the nature of instances, the type and size of columns, type of mobile phase, and flow rate. In recent times, Deep Learning (DL) has the potential to significantly increase the effectiveness and efficiency of chromatography for purification in organic synthesis allowing the analysis and optimizer of difficult procedures at a much quicker rate than is possible with classical approaches. With this motivation, this study develops a novel Compact Firefly Algorithm with Deep Learning based Chromatic Condition Predictive (CFADL-CCP) Model for Organic Synthesis Purification. The presented CFADL-CCP technique mainly predicts the chromatic conditions accurately and timely for organic synthesis purification. In the presented CFADL-CCP technique, two stage pipeline is involved. At the initial stage, the CFADL-CCP technique uses Deep Neural Network (DNN) model for prediction process. Next, in the second stage, the CFA is used for the optimal hyperparameter tuning of the DNN model which helps to accomplish enhanced predictive outcomes. To illustrate the enhanced predictive results of the CFADL-CCP method, an extensive range of simulations were performed. Extensive result analysis shows the betterment of the CFADL-CCP method over other compared methods.