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

Bidirectional Loop Engineering Uncovers a Structural Determinant for Product Specificity in GH46 Family Chitosanases.

Journal of agricultural and food chemistry·2026
Same author

Addition of angiogenesis inhibitors to CDK4/6 inhibitors and fulvestrant in hormone receptor-positive, HER2-negative advanced breast cancer.

Chinese medical journal·2026
Same author

Icariin ameliorates gestational diabetes mellitus by targeting the S100A9-mediated RAGE pathway to activate mitophagy.

Placenta·2026
Same author

N-(4-Hydroxyphenethyl)-(4E)-decenamide derived from natural phytochemical of Anacyclus root ameliorates diabetic retinopathy by inhibiting angiogenesis via PARK7.

Journal of ethnopharmacology·2026
Same author

Toward Precision Biodiversity Detection: An Edge-Deployable Framework for Mitigating Data Redundancy.

Ecology and evolution·2026
Same author

Phonon and thermodynamic properties of goldene under external stress.

Physical chemistry chemical physics : PCCP·2026

Related Experiment Video

Updated: May 10, 2025

Construction of Models for Nondestructive Prediction of Ingredient Contents in Blueberries by Near-infrared Spectroscopy Based on HPLC Measurements
10:25

Construction of Models for Nondestructive Prediction of Ingredient Contents in Blueberries by Near-infrared Spectroscopy Based on HPLC Measurements

Published on: June 28, 2016

10.5K

Near-Infrared Spectroscopy Combined with Explainable Machine Learning for Storage Time Prediction of Frozen Antarctic

Lin Li1,2, Rong Cao1, Ling Zhao1

  • 1Yellow Sea Fisheries Research Institute, Chinese Academy of Fishery Sciences, Qingdao 266071, China.

Foods (Basel, Switzerland)
|April 26, 2025
PubMed
Summary

This study predicts Antarctic krill storage time using near-infrared spectroscopy (NIRS) and machine learning. A LightGBM model accurately assesses frozen krill quality, ensuring sustainable protein safety.

Keywords:
Antarctic krillinterpretable machine learninglight gradient boosting machinenear-infrared spectroscopystorage time

More Related Videos

Laser-Induced Fluorescence Emission L.I.F.E. as Novel Non-Invasive Tool for In-Situ Measurements of Biomarkers in Cryospheric Habitats
13:38

Laser-Induced Fluorescence Emission L.I.F.E. as Novel Non-Invasive Tool for In-Situ Measurements of Biomarkers in Cryospheric Habitats

Published on: October 26, 2019

7.8K
Cryogenic Sample Loading into a Magic Angle Spinning Nuclear Magnetic Resonance Spectrometer that Preserves Cellular Viability
06:42

Cryogenic Sample Loading into a Magic Angle Spinning Nuclear Magnetic Resonance Spectrometer that Preserves Cellular Viability

Published on: September 1, 2020

3.4K

Related Experiment Videos

Last Updated: May 10, 2025

Construction of Models for Nondestructive Prediction of Ingredient Contents in Blueberries by Near-infrared Spectroscopy Based on HPLC Measurements
10:25

Construction of Models for Nondestructive Prediction of Ingredient Contents in Blueberries by Near-infrared Spectroscopy Based on HPLC Measurements

Published on: June 28, 2016

10.5K
Laser-Induced Fluorescence Emission L.I.F.E. as Novel Non-Invasive Tool for In-Situ Measurements of Biomarkers in Cryospheric Habitats
13:38

Laser-Induced Fluorescence Emission L.I.F.E. as Novel Non-Invasive Tool for In-Situ Measurements of Biomarkers in Cryospheric Habitats

Published on: October 26, 2019

7.8K
Cryogenic Sample Loading into a Magic Angle Spinning Nuclear Magnetic Resonance Spectrometer that Preserves Cellular Viability
06:42

Cryogenic Sample Loading into a Magic Angle Spinning Nuclear Magnetic Resonance Spectrometer that Preserves Cellular Viability

Published on: September 1, 2020

3.4K

Area of Science:

  • Food Science
  • Analytical Chemistry
  • Machine Learning

Background:

  • Antarctic krill (Euphausia superba) is a sustainable protein source, but frozen storage impacts quality and safety.
  • Accurate quality assessment of frozen krill is crucial for industrial processing and consumer safety.
  • Traditional quality assessment methods can be time-consuming and may not reflect real-time conditions.

Purpose of the Study:

  • To develop a novel, rapid method for assessing the quality of frozen Antarctic krill based on storage time prediction.
  • To correlate traditional chemical quality indicators with storage duration.
  • To build and validate predictive models using near-infrared spectroscopy (NIRS) and machine learning algorithms.

Main Methods:

  • Monitored traditional chemical quality indicators of Antarctic krill over a 12-month storage period.
  • Applied near-infrared spectroscopy (NIRS) coupled with four regression machine learning algorithms.
  • Optimized spectral preprocessing and hyperparameters, focusing on the LightGBM model.

Main Results:

  • The LightGBM model achieved high predictive performance for storage time (R² = 0.9882, RMSE = 0.3724).
  • Model interpretation showed a strong correlation between NIR features and chemical indicators of quality degradation.
  • NIRS combined with LightGBM effectively predicted quality changes during frozen storage.

Conclusions:

  • NIRS coupled with LightGBM offers a rapid and effective technique for evaluating frozen Antarctic krill quality.
  • This approach has significant potential for industrial implementation in the krill processing industry.
  • Ensures the safety and quality of Antarctic krill as a sustainable protein source.