Abstract

The use of near-infrared reflectance spectroscopy (NIRS) calibrations to predict the ingredient composition in compound feeds (i.e., inclusion percentage of each ingredient) is a complex task, regarding both the nature of the parameters to be predicted, since they are not well-defined chemical entities, and the heterogeneousness of the matrices/formulas in which each ingredient participates. The present paper evaluates the use of nonlinear regression methods, such as artificial neural networks (ANN), for developing NIRS calibrations to predict these parameters. Two of the most representative ingredients in the Spanish compound feed formulations (wheat and sunflower meal) were selected for evaluating ANN possibilities, using a large spectral library comprising a total of 7523 commercial compound feed samples; 7423 were used as training set and 100 as validation set. Three general models of networks were studied: multilayer perceptron with back-propagation training (BP), multilayer perceptron with Levenberg–Maquartd training (LM), and radial basis function nets (RBF); moreover, in accordance with a factorial design, more complex architectures were evaluated gradually, changing the number of hidden layers and hidden neurons, for the determination of the optimal network topology. For both ingredients, the best results were obtained using ANN with BP training, showing prediction error values (SEP) of 2.72% and 0.66% for wheat and sunflower meal, respectively. These SEP values showed a significant improvement (19%–49% for sunflower meal and wheat, respectively) in comparison with those obtained using calibrations developed with linear methods.

Construction of a predictive model for concentration of nickel and vanadium in vacuum residues of crude oils using artificial neural networks and LIBS

José L. Tarazona, Jáder Guerrero, Rafael Cabanzo, and E. Mejía-Ospino
Appl. Opt. 51(7) B108-B114 (2012)

Non-invasive prediction of hemoglobin levels by principal component and back propagation artificial neural network

Haiquan Ding, Qipeng Lu, Hongzhi Gao, and Zhongqi Peng
Biomed. Opt. Express 5(4) 1145-1152 (2014)

Quantitative analysis of tin alloy combined with artificial neural network prediction

Seong Y. Oh, Fang-Yu Yueh, and Jagdish P. Singh
Appl. Opt. 49(13) C36-C41 (2010)

Energetic materials identification by laser-induced breakdown spectroscopy combined with artificial neural network

Amir Hossein Farhadian, Masoud Kavosh Tehrani, Mohammad Hossein Keshavarz, and Seyyed Mohammad Reza Darbani
Appl. Opt. 56(12) 3372-3377 (2017)

Pattern recognition of visible and near-infrared spectroscopy from bayberry juice by use of partial least squares and a backpropagation neural network

Haiyan Cen, Yidan Bao, and Yong He
Appl. Opt. 45(29) 7679-7683 (2006)