Jove
Visualize
Contact Us
JoVE
x logofacebook logolinkedin logoyoutube logo
ABOUT JoVE
OverviewLeadershipBlogJoVE Help Center
AUTHORS
Publishing ProcessEditorial BoardScope & PoliciesPeer ReviewFAQSubmit
LIBRARIANS
TestimonialsSubscriptionsAccessResourcesLibrary Advisory BoardFAQ
RESEARCH
JoVE JournalMethods CollectionsJoVE Encyclopedia of ExperimentsArchive
EDUCATION
JoVE CoreJoVE BusinessJoVE Science EducationJoVE Lab ManualFaculty Resource CenterFaculty Site
Terms & Conditions of Use
Privacy Policy
Policies

Related Experiment Videos

Artificial neural networks for multicomponent kinetic determinations

M Blanco1, J Coello, H Iturriaga

  • 1Departamento de Química, Universidad Autónoma de Barcelona, Spain.

Analytical Chemistry
|December 15, 1995
PubMed
Summary
This summary is machine-generated.

Related Concept Videos

You might also read

Related Articles

Articles linked to this work by shared authors, journal, and citation graph.

Sort by
Same author

Effect of sainfoin proanthocyanidins on milk fatty acids from ewes rearing suckling lambs.

Animal : an international journal of animal bioscience·2023
Same author

Durvalumab plus tremelimumab for the treatment of advanced neuroendocrine neoplasms of gastroenteropancreatic and lung origin.

Nature communications·2023
Same author

Possibility of genetic therapy for inherited retinal conditions.

Archivos de la Sociedad Espanola de Oftalmologia·2022
Same author

Modelling beef cows' individual response to short nutrient restriction in different lactation stages.

Animal : an international journal of animal bioscience·2022
Same author

Field pea can replace soybean meal-corn mixtures in the fattening concentrate of young bulls improving the digestibility.

Research in veterinary science·2022
Same author

Effects of feeding sainfoin proanthocyanidins to lactating ewes on intake, milk production and plasma metabolites.

Animal : an international journal of animal bioscience·2022

Artificial neural networks (ANN) effectively resolve complex chemical mixtures from kinetic data. ANN outperformed partial least-squares (PLS) and principal component regression (PCR), especially in nonlinear systems with analyte interactions.

Area of Science:

  • Analytical Chemistry
  • Computational Chemistry

Background:

  • Kinetic measurements are crucial for analyzing chemical mixtures.
  • Multivariate calibration methods like PLS and PCR are standard but can struggle with complex systems.

Purpose of the Study:

  • To evaluate an artificial neural network (ANN) for resolving binary mixtures using kinetic data.
  • To compare ANN performance against PLS and PCR, particularly in nonlinear scenarios.

Main Methods:

  • An ANN procedure utilizing principal component model scores as input was developed.
  • Simulated kinetic curves with added noise and analyte interactions were used for testing.
  • Real-world mixture analysis of Fe(III), Co(II), and Zn(II) was performed using stopped-flow injection and a diode array detector.

Related Experiment Videos

Main Results:

  • ANN showed comparable results to PLS and PCR in linear systems.
  • ANN significantly outperformed PLS and PCR in resolving mixtures with analyte interactions (nonlinear systems).
  • ANN successfully resolved a complex mixture of three metal ions, demonstrating superior performance over PCR and PLS.

Conclusions:

  • ANN provides a robust and superior method for mixture resolution from kinetic data, especially when analyte interactions are present.
  • ANN offers enhanced accuracy and reliability compared to traditional methods like PLS and PCR for complex analytical challenges.