Firefly algorithm versus genetic algorithm as powerful variable selection tools and their effect on different multivariate calibration models in spectroscopy: A comparative study

•A comparative study between FA and GA for variable selection was developed.•FA introduced simpler and faster models than GA with the same predictabilities.•Can be applied for the analysis of the dosage form that contains CIP with no interference from MET and excipients

For the first time, a new variable selection method based on swarm intelligence namely firefly algorithm is coupled with three different multivariate calibration models namely, concentration residual augmented classical least squares, artificial neural network and support vector regression in UV spectral data. A comparative study between the firefly algorithm and the well-known genetic algorithm was developed. The discussion revealed the superiority of using this new powerful algorithm over the well-known genetic algorithm. Moreover, different statistical tests were performed and no significant differences were found between all the models regarding their predictabilities. This ensures that simpler and faster models were obtained without any deterioration of the quality of the calibration.

Graphical abstractFigure optionsDownload full-size imageDownload as PowerPoint slide