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

Wavelength selection for multivariate calibration using a genetic algorithm: a novel initialization strategy.

Héctor C Goicoechea1, Alejandro C Olivieri

  • 1Cátedra de Química Analítica I, Facultad de Bioquímica y Ciencias Biológicas, Universidad Nacional del Litoral, Ciudad Universitaria, Santa Fe (3000), Argentina.

Journal of Chemical Information and Computer Sciences
|October 16, 2002
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

Chemometric electrochemical fingerprinting of thermal stress in honeybee larvae: a tool for discrimination and welfare assessment.

Analytical and bioanalytical chemistry·2026
Same author

Ciprofloxacin and glyphosate co-exposure alters soybean development and reprograms metabolic pathways.

Environmental science and pollution research international·2026
Same author

Old advice on multivariate calibration: still in force, but not always followed. A tutorial.

Analytica chimica acta·2026
Same author

Multi-way data modelling for enhancing classification performance: Fluorescence data as a case of study.

Analytica chimica acta·2026
Same author

Comprehensive chemical fingerprinting by LC×LC-fluorescence and data-driven chemometric modelling for unsupervised classification.

Talanta·2025
Same author

Hazards of using multivariate curve resolution for processing first-order spectral data. A rotational ambiguity analysis.

Analytica chimica acta·2025
Same journal

Future Papers.

Journal of chemical information and computer sciences·2016
Same journal

Future Papers.

Journal of chemical information and computer sciences·2016
Same journal

Future Papers.

Journal of chemical information and computer sciences·2016
Same journal

Future Papers.

Journal of chemical information and computer sciences·2016
Same journal

Future Papers.

Journal of chemical information and computer sciences·2016
Same journal

Future Papers.

Journal of chemical information and computer sciences·2016
See all related articles

A new genetic algorithm approach improves variable selection for partial least-squares calibration by using iterative reinitialization. This method enhances predictive accuracy without needing separate test data, outperforming other strategies for diluted analytes.

Area of Science:

  • Chemometrics
  • Machine Learning
  • Spectroscopy

Background:

  • Variable selection is crucial for enhancing partial least-squares (PLS) multivariate calibration.
  • Genetic algorithms (GAs) are increasingly used for variable selection, but initialization and overfitting remain key challenges.
  • Effective sensor selection is vital for accurate predictive modeling in chemometrics.

Purpose of the Study:

  • To introduce a novel iterative reinitialization procedure for genetic algorithms in sensor selection.
  • To address the critical issues of initialization and overfitting in genetic algorithm-based variable selection.
  • To evaluate the performance of the new method compared to existing strategies for PLS calibration.

Main Methods:

  • Development of a new GA procedure with iterative reinitialization based on statistical sensor analysis.

Related Experiment Videos

  • Monte Carlo simulations using a theoretical three-component system to assess PLS regression with variable selection.
  • Application of the novel GA to five experimental datasets, including UV-visible and near-infrared spectroscopy.

    • Main Results:

    • The proposed iterative reinitialization method demonstrated excellent results for sensor selection without requiring independent test sets.
    • Simulations showed significant benefits of variable selection for PLS regression, especially for diluted analytes.
    • The new GA approach proved effective in determining analyte concentrations in pharmaceutical mixtures and octane numbers in gasoline.

    Conclusions:

    • The novel iterative reinitialization strategy effectively overcomes limitations of traditional genetic algorithms in variable selection.
    • This approach enhances the predictive performance of partial least-squares calibration, particularly in challenging scenarios with diluted analytes.
    • The method offers a robust and efficient solution for sensor selection problems in analytical chemistry and spectroscopy.