Qualitative and quantitative aspects of the application of genetic algorithm-based variable selection in polarography and stripping voltammetry

摘要: Abstract A genetic algorithm (GA) is successfully applied as a variable selection method in the multivariate analysis with partial least squares (PLS) regression of several polarographic and stripping voltammetric data sets, where different interferences are present (coupled reactions, formation intermetallic compounds, overlapping signals matrix effect). In most cases, results corresponding to this better than those obtained when all variables considered. Such case determination benzaldehyde, dimerization reaction occurs simultaneously electrochemical reactions. general, an improvement precision achieved for test samples by using GA. On other hand, GA provides valuable qualitative information that, every case, significant tool detect understand chemical phenomena related each analysis.