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

Removing uncertain variables based on ensemble partial least squares.

Da Chen1, Wensheng Cai, Xueguang Shao

  • 1Research Center for Analytical Sciences, State Key Laboratory of Functional Polymer Materials for Adsorption and Separation, Department of Chemistry, Nankai University, Tianjin 300071, PR China.

Analytica Chimica Acta
|August 19, 2007
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

Data mining from process monitoring of typical polluting enterprise.

Environmental monitoring and assessment·2023
Same author

A Micromechanical-Based Semi-Empirical Model for Predicting the Compressive Strength Degradation of Concrete under External Sulfate Attack.

Materials (Basel, Switzerland)·2023
Same author

Bell pepper derived nitrogen-doped carbon dots as a pH-modulated fluorescence switching sensor with high sensitivity for visual sensing of 4-nitrophenol.

Food chemistry·2023
Same author

The utility of P-I-R classification in predicting the on-treatment histological and clinical outcomes of patients with hepatitis B and advanced liver fibrosis.

Hepatology (Baltimore, Md.)·2023
Same author

Application of urea-based magnetic covalent organic framework as sorbent for the determination of coumarin and its derivatives in food samples combined with liquid chromatography-mass spectrometry.

Food chemistry·2023
Same author

The prognosis of gliomas with different molecular subtypes in the era of intensity-modulated radiation therapy (IMRT).

Aging·2023
Same journal

Smartphone-assisted fluorescence and colorimetric dual-mode sensor for visual quantitative detection of nitrite and nitrate in real samples.

Analytica chimica acta·2026
Same journal

Folding integrated all-paper photoelectrochemical immunoassay using annealed ZnO for point-of-care detection of ferritin.

Analytica chimica acta·2026
Same journal

Dual-mode electrochemical-SERS detection of chloramphenicol based on dual-signal enhancement.

Analytica chimica acta·2026
Same journal

Multi-screening of beta-lactam antibiotics in milk based on Fe<sub>3</sub>O<sub>4</sub>@phage/bacteria system and aggregation induced emission luminogen.

Analytica chimica acta·2026
Same journal

A porous phosphate-rich β-cyclodextrin polymer for efficient and broad-spectrum enrichment of antibiotics.

Analytica chimica acta·2026
Same journal

Corrigendum to "LUMIN: A novel algorithm for automated mixture quantification using 1D <sup>1</sup>H NMR spectra" [Analytica Chimica Acta 1411 (2026) 345639].

Analytica chimica acta·2026
See all related articles

A new strategy, removing uncertain variables based on ensemble partial least squares (RUV-EPLS), enhances calibration models by eliminating uncertain variables. This method improves stability and predictive ability, even with complex matrices and outliers.

Area of Science:

  • Chemometrics
  • Spectroscopy
  • Analytical Chemistry

Background:

  • Multivariate calibration models are essential for analyzing complex datasets.
  • Partial Least Squares (PLS) regression is widely used but can be sensitive to variable uncertainty and outliers.
  • Ensemble Partial Least Squares (EPLS) offers improved robustness but requires careful variable selection.

Purpose of the Study:

  • To propose a novel strategy, RUV-EPLS, for enhancing multivariate calibration models.
  • To improve the stability and predictive performance of calibration models by removing uncertain variables.
  • To develop a practical and effective method for handling complex matrices and potential outliers in spectral data.

Main Methods:

  • Development of the Removing Uncertain Variables based on Ensemble Partial Least Squares (RUV-EPLS) strategy.

Related Experiment Videos

  • Evaluation of uncertainty in PLS regression coefficients using a stability criterion.
  • Elimination of variables with high regression coefficient uncertainty.
  • Construction of new EPLS models with selected variables.
  • Utilization of an F-test based criterion to control PLS member model quality.

    • Main Results:

    • The RUV-EPLS strategy effectively identifies and removes uncertain variables.
    • The developed method demonstrates reduced sensitivity to outliers compared to other calibration techniques.
    • Selected variables are confirmed to be informative for the target compounds.
    • Reliable and high-quality calibration models are achieved using RUV-EPLS.
    • Validation on near-infrared (NIR) spectra confirms the strategy's effectiveness and universality.

    Conclusions:

    • RUV-EPLS is a valuable method for improving the stability and predictive ability of multivariate calibration.
    • The strategy is particularly useful for complex matrices that may contain outliers.
    • The F-test criterion ensures practical implementation and quality control of the calibration models.