A fast artificial neural network approach for dynamic light scattering time series processing

Abstract

This paper presents a simple alternative to dynamic light scattering (DLS) time series processing by using an artificial neural network. A simple experiment for recording a DLS time series is presented. The reference method for DLS time series processing consisted of fitting the analytical form of the Lorentzian line to the frequency spectrum of the recorded scattered light intensity. An artificial neural network with one hidden layer was designed and trained. The training data consisted of a big set of autocorrelations of simulated time series for monodispersed spherical particles with diameters in the range 10–1200 µm. The neural network output precision was tested both on simulated and on experimental time series recorded on fluids containing nanoparticles and microparticles. The errors of the artificial neural network output relative to the reference diameters were small enough and the data processing procedure was three orders of magnitude faster, proving that, in spite of the simplicity, the artificial neural networks approach can be a faster alternative for DLS time series processing.