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

Neural networks in high-performance liquid chromatography optimization: response surface modeling

H J Metting1, P M Coenegracht

  • 1Chemometrics Research Group, University Centre for Pharmacy, Groningen, Netherlands.

Journal of Chromatography. A
|March 29, 1996
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

High throughput therapeutic drug monitoring of clozapine and metabolites in serum by on-line coupling of solid phase extraction with liquid chromatography-mass spectrometry.

Journal of chromatography. B, Analytical technologies in the biomedical and life sciences·2006
Same author

Simultaneous resolution of overlapping peaks in high-performance liquid chromatography and micellar electrokinetic chromatography with diode array detection using augmented iterative target transformation factor analysis.

Journal of chromatography. A·2005
Same author

Resolution optimisation in micellar electrokinetic chromatography using empirical models.

Journal of chromatography. A·2000
Same author

Artificial neural network predictions of urinary calculus compositions analyzed with infrared spectroscopy.

Clinical chemistry·1994
Same author

Chemometrics in bioanalytical sample preparation. A fractionated combined mixture and factorial design for the modelling of the recovery of five tricyclic amines from plasma after liquid-liquid extraction prior to high-performance liquid chromatography.

Journal of chromatography·1993
Same author

Development of a laboratory robotic system for automated bioanalytical methods--I. The determination of theophylline in human plasma: a comparison between the robotized and manual method.

Journal of pharmaceutical and biomedical analysis·1990

Artificial neural networks show promise for optimizing High-Performance Liquid Chromatography (HPLC) methods. They provide comparable or superior predictive results compared to traditional regression models for response surface modeling.

Area of Science:

  • Analytical Chemistry
  • Computational Chemistry

Background:

  • High-Performance Liquid Chromatography (HPLC) method development often involves complex optimization processes.
  • Response surface modeling is crucial for efficiently optimizing HPLC parameters.
  • Traditional methods like linear and non-linear regression have limitations in modeling complex responses.

Purpose of the Study:

  • To evaluate the effectiveness of artificial neural networks (ANNs) for response surface modeling in HPLC optimization.
  • To compare ANN performance against established (non-)linear regression techniques.
  • To explore methods for optimizing ANN architecture and preventing overfitting.

Main Methods:

  • Artificial neural networks were employed for response surface modeling.
  • The number of hidden nodes in ANNs was optimized using a lateral inhibition method.

Related Experiment Videos

  • Cross-validation, specifically the leave-one-out method (LOOM), was utilized to control overfitting.
  • Literature data sets for both linear and non-linear response surfaces (capacity factors) were used for evaluation.

    • Main Results:

    • ANNs demonstrated promising capabilities for HPLC method development.
    • Predictive performance of ANNs was found to be better than or comparable to linear and non-linear regression models.
    • The optimized ANN architecture and cross-validation approach effectively managed model complexity and generalization.

    Conclusions:

    • Artificial neural networks offer a powerful alternative for response surface modeling in HPLC.
    • ANNs can enhance the efficiency and accuracy of HPLC method development.
    • Further investigation into ANNs for chromatographic optimization is warranted.