Genetic algorithms-based approach for wavelength selection in spectrophotometric determination of vitamin B<inf>12</inf> in pharmaceutical tablets by partial least-squares

• Main Authors: L. Sratthaphut, N. Ruangwises
• Other Authors: Silpakorn University
• Format: Conference or Workshop Item
• Published: 2018
• Subjects: Engineering
• Online Access: https://repository.li.mahidol.ac.th/handle/123456789/14179
• Institution: Mahidol University

This study illustrated the genetic algorithms (GA) is useful tool in wavelength selection for the spectrophotometric determination of vitamin B 12 in pharmaceutical tablets by partial least-squares calibration procedure (PLS). Because of interference in the spectra, a training set of the mixtures of vitamin B 12 and tablet excipients was built to be used as calibration set for modeling. The absorption spectra of all solutions were recorded each 1 nm in the range 354-600 nm, using 0.1N hydrochloric acid as solvent. A validation set was employed to verify the models and a commercial sample was analysed. GA-PLS model leads to 86% improvement of predictive ability for vitamin B 12 , when comparing with full spectrum PLS model. It is concluded that only some variables in GA-PLS modeling are relevant for prediction and removing the non-relevant variables can improve the predictive capability. © 2010 Published by Elsevier Ltd.