Artificial neural networks and partial least squares regression for pseudo-first-order with respect to the reagent multicomponent kinetic-spectrophotometric determinations

Blanco, M.; Coello, J.; Iturriaga, H.; Maspoch, S.; Redón, M.; Villegas, Núria

doi:10.1039/an9962100395

Cited by 41 publications

(13 citation statements)

References 21 publications

Supporting

Mentioning

Contrasting

Unclassified

Order By: Relevance

“…The results are similar to those obtained when mixtures of amines react with salycilaldehyde to yield colored products, which has been previously explored using ANN, except that in this latter case unsuspected components were absent in the test samples [4].…”

Section: Data Setsupporting

confidence: 88%

“…This phenomenon arises, for example, when significant interactions occur among sample components [1,2], or in fluorescence spectroscopy, due to the exponential relationship between emission and concentration [3]. They also appear in kinetic-spectroscopic systems, when a reaction product is followed which is the result of a pseudo first-order kinetics with respect to reagent [4], or when the analyte intervenes as a catalyst [5][6][7]. When the data structure is intrinsically non-linear, classical calibration methods with linear underlying models cannot be successfully applied.…”

Section: Introductionmentioning

confidence: 99%

See 1 more Smart Citation

A combined artificial neural network/residual bilinearization approach for obtaining the second‐order advantage from three‐way non‐linear data

Olivieri¹

2005

Journal of Chemometrics

View full text Add to dashboard Cite

Three-way instrumental data offer the second-order advantage to analysts, a property of great utility in the field of complex sample analysis in the presence of unsuspected components as potential interferents. The available multivariate methodologies for obtaining this advantage are all based on linear models, and hence they are not applicable to spectral information behaving in a non-linear manner with respect to target analyte concentrations. This work describes the combination of a backpropagation artificial neural network model with a technique known as residual bilinearization, applicable to second-order spectral information. The joint model allows one to efficiently extract analyte concentrations from intrinsically non-linear data, even in the presence of unsuspected constituents. Simulations have been performed by mimicking deviations from linearity brought about by: (1) exponential relationship between fluorescence and concentration, (2) kinetic evolution of responsive reaction products and (3) analytes acting as reaction catalysts. In all of these cases, successful prediction of the analyte concentrations was achieved on large test sample sets, which included the presence of overlapping components not included in the training step. The new method not only obtains the second-order advantage, but also correctly retrieves the contribution of the unsuspected components to the total test sample signals. The comparison with a multivariate methodology based on partial least-squares regression with second-order advantage shows that the presently described method displays better predictive ability.

show abstract

Section: Data Setsupporting

confidence: 88%

Section: Introductionmentioning

confidence: 99%

A combined artificial neural network/residual bilinearization approach for obtaining the second‐order advantage from three‐way non‐linear data

Olivieri¹

2005

Journal of Chemometrics

View full text Add to dashboard Cite

show abstract

“…35,36 Artificial neural networks (ANN) are a type of nonlinear processing tools that are Table 3 Statistical parameters for the optimized PLS and ANN models in determination of DA appropriate for an extensive variety of applications. 37,38 The most common network architecture is multilayer feed-forward networks with the back-propagation learning algorithm. It is possible to get great results in multivariate calibration issues using ANN.…”

Section: Multivariate Calibrationmentioning

confidence: 99%

Digital videometrics analysis for the kinetic determination of dopamine in the presence of ascorbic acid based on the formation of silver nanoparticles

et al. 2015

View full text Add to dashboard Cite

A simple, cost-effective and rapid method for visual detection of dopamine (DA) and ascorbic acid (AsA) based on the video-image analysis has been developed. The method is based on the formation of silver nanoparticles by reaction of dopamine and/or ascorbic acid with silver nitrate. The video of produced brown color during the reaction was recorded and then the framed images were extracted. Changes in the red, blue and green (RGB) elements of the images as function of time produced kinetic profiles, which were very similar to spectrophotometric study. By fix-time analysis of the kinetic profiles, linear calibration curves were obtained for dopamine and ascorbic acid in the concentration ranges of 4.95 ×10 -6 -2.38×10 -5 M and 9.80 ×10 -6 -7.63× 10 -5 M, with detection limits of 2.5 ×10 -6 M and 3.10 ×10 -6 M, respectively. Then the imaging-based kinetic profiles were used for multicomponent analysis based on partial least squares (PLS) and principal component analysis-artificial neural network (PC-ANN) models. This is the first attempt to use image analysis for the kinetic determination of dopamine in the presence of ascorbic acid with the aid of chemometrics methods. In this manner, accurate determination of dopamine in the presence of ascorbic acid using a very simple instrumentation was achieved. The root mean square error for estimation of dopamine in the synthetic binary mixtures was about 6%.

show abstract

“…; • the ability to process complex kinetic systems [10,11,12,13,14,15] (interactions between analytes, the effects of slight interferences from species reacting with a general reagent or perturbations in the data matrix); and • the resolution of mixtures of absorbent species that overlap strongly [2,16,17].…”

Section: Introductionmentioning

confidence: 99%

Kinetic-spectrophotometric determination of theophylline, dyphylline, and proxyphylline by use of partial least-squares regression

Iturriaga

Coello

Maspoch

et al. 2002

Analytical and Bioanalytical Chemistry

View full text Add to dashboard Cite

A kinetic-spectrophotometric method for the determination of theophylline, dyphylline and proxyphylline, based on their azo coupling reaction with the diazonium ion of sulfanilic acid after a treatment with alkali, is proposed. The absorbance is recorded from 340 to 600 nm every second during reaction for 90 s, and calibration is performed by partial least-squares regression, using first derivative spectra values. Mixtures containing 2.5-13 micro g mL(-1) dyphylline and proxyphylline, and 2-9 micro g mL(-1) theophylline were successfully resolved with root mean squared errors of prediction (RMSEP) of 0.4, 0.3, and 0.2 for dyphylline, proxyphylline, and theophylline, respectively. The proposed method was satisfactorily applied to the determination of the three compounds in a commercially available pharmaceutical preparation and provided results similar to those obtained by HPLC.

show abstract

Artificial neural networks and partial least squares regression for pseudo-first-order with respect to the reagent multicomponent kinetic-spectrophotometric determinations

Cited by 41 publications

References 21 publications

A combined artificial neural network/residual bilinearization approach for obtaining the second‐order advantage from three‐way non‐linear data

A combined artificial neural network/residual bilinearization approach for obtaining the second‐order advantage from three‐way non‐linear data

Digital videometrics analysis for the kinetic determination of dopamine in the presence of ascorbic acid based on the formation of silver nanoparticles

Kinetic-spectrophotometric determination of theophylline, dyphylline, and proxyphylline by use of partial least-squares regression

Contact Info

Product

Resources

About