6533b7d0fe1ef96bd125abda

RESEARCH PRODUCT

Artificial neural network for quantitative determination of total protein in yogurt by infrared spectrometry

Keyvan GhasemiMiguel De La GuardiaMohammadreza KhanmohammadiAmir Bagheri GarmarudiSalvador Garrigues

subject

ChemometricsAbsorbanceChromatographyArtificial neural networkChemistryApproximation errorSample preparationBiological systemQuantitative analysis (chemistry)SpectroscopyBackpropagationDykstra's projection algorithmAnalytical Chemistry

description

Abstract A method has been introduced for quantitative determination of protein content in yogurt samples based on the characteristic absorbance of protein in 1800–1500 cm− 1 spectral region by mid-FTIR spectroscopy and chemometrics. Successive Projection Algorithm (SPA) wavelength selection procedure, coupled with feed forward Back-Propagation Artificial Neural Network (BP-ANN) model was the benefited chemometric technique. Relative Error of Prediction (REP) in BP-ANN and SPA-BP-ANN methods for training set was 7.25 and 3.70 respectively. Considering the complexity of the sample, the ANN model was found to be reliable, while the proposed method is rapid and simple, without any sample preparation step.

yearjournalcountryeditionlanguage
2009-01-01Microchemical Journal
https://doi.org/10.1016/j.microc.2008.07.003