Computer match prediction for fluorescent dyes by neural networks

Abstract

Fluorescent dyes present difficulties for match prediction due to their variable excitation and emission characteristics, which depend on a variety of factors. An empirical approach is therefore favoured, such as that used in the artificial neural network method. In this paper, the production of a database with four acid dyes (two fluorescent and two non-fluorescent) is described, along with the large number of mixture dyeings that were carried out. The data were used to construct a network connecting reflectance values with concentrations in formulations. The results show that, although time consuming, this approach is viable and accurate