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 Concept Videos

You might also read

Related Articles

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

Sort by
Same author

Strategic use of calibration transfer to minimize experimental runs for multivariate calibrations within the QbD design space.

Journal of pharmaceutical and biomedical analysis·2025
Same author

Calibration transfer and maintenance in the pharmaceutical industry: a systematic review.

European journal of pharmaceutical sciences : official journal of the European Federation for Pharmaceutical Sciences·2025
Same author

Effects of tableting process parameters and powder lubrication levels on tablet surface temperature and moisture content.

Pharmaceutical development and technology·2023
Same author

Wafer-scale detachable monocrystalline germanium nanomembranes for the growth of III-V materials and substrate reuse.

Nanoscale advances·2023
Same author

Moisture Behavior of Pharmaceutical Powder during the Tableting Process.

Pharmaceutics·2023
Same author

Insights into tablet sticking: a quantitative case study with an ibuprofen and methocarbamol-based formulation.

Pharmaceutical development and technology·2023

Related Experiment Video

Updated: Oct 12, 2025

O-cresol Concentration Online Measurement Based On Near Infrared Spectroscopy Via Partial Least Square Regression
06:50

O-cresol Concentration Online Measurement Based On Near Infrared Spectroscopy Via Partial Least Square Regression

Published on: November 8, 2019

6.7K

Evaluating the impact of NIR pre-processing methods via multiblock partial least-squares.

Giverny Robert1, Ryan Gosselin1

  • 1Department of Chemical and Biotechnological Engineering, Université de Sherbrooke, 2500 boulevard de l'Université, Sherbrooke, Québec, J1K 2R1, Canada.

Analytica Chimica Acta
|November 24, 2021
PubMed
Summary
This summary is machine-generated.

Selecting the best pre-processing for near-infrared (NIR) spectral data is crucial for accurate predictions. Multiblock partial least squares (MBPLS) with superloadings efficiently compares techniques, optimizing regression models without extensive computation.

Keywords:
ChemometricsMBPLSNIRPre-processing

More Related Videos

Qualitative and Comparative Cortical Activity Data Analyses from a Functional Near-Infrared Spectroscopy Experiment Applying Block Design
06:18

Qualitative and Comparative Cortical Activity Data Analyses from a Functional Near-Infrared Spectroscopy Experiment Applying Block Design

Published on: December 3, 2020

3.9K
Swin-PSAxialNet: An Efficient Multi-Organ Segmentation Technique
04:48

Swin-PSAxialNet: An Efficient Multi-Organ Segmentation Technique

Published on: July 5, 2024

554

Related Experiment Videos

Last Updated: Oct 12, 2025

O-cresol Concentration Online Measurement Based On Near Infrared Spectroscopy Via Partial Least Square Regression
06:50

O-cresol Concentration Online Measurement Based On Near Infrared Spectroscopy Via Partial Least Square Regression

Published on: November 8, 2019

6.7K
Qualitative and Comparative Cortical Activity Data Analyses from a Functional Near-Infrared Spectroscopy Experiment Applying Block Design
06:18

Qualitative and Comparative Cortical Activity Data Analyses from a Functional Near-Infrared Spectroscopy Experiment Applying Block Design

Published on: December 3, 2020

3.9K
Swin-PSAxialNet: An Efficient Multi-Organ Segmentation Technique
04:48

Swin-PSAxialNet: An Efficient Multi-Organ Segmentation Technique

Published on: July 5, 2024

554

Area of Science:

  • Chemometrics
  • Spectroscopy
  • Data Science

Background:

  • Near-infrared (NIR) spectroscopy is widely used for predicting physical and chemical properties.
  • Directly using raw spectral data often leads to poor predictive model performance.
  • Various pre-processing techniques exist to enhance spectral data quality, but selection is challenging.

Purpose of the Study:

  • To develop an efficient method for comparing and selecting pre-processing techniques for NIR spectral data.
  • To optimize the combination of pre-processing methods for improved regression model performance.
  • To reduce the computational cost associated with selecting optimal pre-processing strategies.

Main Methods:

  • Implementation of multiblock partial least squares (MBPLS) for simultaneous analysis of pre-processing impacts.
  • Utilization of superloadings for qualitative and quantitative assessment of pre-processed spectral data.
  • Testing the proposed approach on artificial signals and real NIR spectra from corn samples.

Main Results:

  • The MBPLS approach effectively compares the influence of different pre-processing techniques on spectral data.
  • Superloadings provide valuable insights for selecting appropriate pre-processing methods or combinations.
  • The method facilitates informed decision-making for analysts, leading to better predictive models.

Conclusions:

  • Multiblock partial least squares (MBPLS) offers an efficient and comprehensive tool for optimizing NIR spectral data pre-processing.
  • The proposed method aids in selecting optimal pre-processing strategies, improving regression model accuracy.
  • This approach enhances the utility of NIR spectroscopy by streamlining the pre-processing selection workflow.