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 Video

Updated: Jul 7, 2026

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

Deep Learning-Based Prediction and Regulation for Remaining Shelf Life of Blueberries.

Chengzhi Wang1, Xuhang He1, Yuzhen Zhu2

  • 1College of Advanced Materials and Future Technology, Beijing Technology and Business University, Beijing, China.

Journal of Food Science
|July 5, 2026
PubMed
Summary

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

In Situ Construction of a Li<sub>2</sub>S/Li<sub>x</sub>Sn Mixed Conductive Interlayer for Dendrite-Free Garnet-Based Solid-State Lithium Metal Batteries.

Small (Weinheim an der Bergstrasse, Germany)·2026
Same author

Bioinspired Rhombic VO<sub>2</sub> Metasurface with Low Solar Absorptance for Self-adaptive All-Weather Building Thermal Management.

ACS applied materials & interfaces·2026
Same author

Early onset primary angle closure and foveal retinoschisis associated with a pseudo-homozygous CRB1 pathogenic variant.

Documenta ophthalmologica. Advances in ophthalmology·2026
Same author

Efficacy of abdominal drainage in perforated appendicitis: a retrospective single-center study using AAST grading and inverse probability treatment weighting analysis.

BMC gastroenterology·2026
Same author

Multi-omics study on traditional Xiaoqu of Fangxian Huangjiu: Unveiling interactions among physicochemical factors, microbiome and volatile flavor compounds.

Food chemistry: X·2026
Same author

From agri-food wastes to high-value products: research progress, technological innovation, and challenges in the resource recycling of Chinese Baijiu by-products.

Bioresource technology·2026

This study introduces an AHP-PCA-LSTM model to accurately predict blueberry shelf life, outperforming traditional methods. A Gaussian process regression model optimizes storage temperatures, reducing waste and enhancing fruit quality for consumers.

Area of Science:

  • Agricultural Science
  • Food Science
  • Data Science

Background:

  • Blueberry quality rapidly declines during storage, necessitating accurate shelf-life prediction.
  • Current methods lack precision in forecasting remaining shelf life and optimizing storage conditions.

Purpose of the Study:

  • To develop a novel closed-loop framework for precise remaining shelf-life estimation and temperature-based regulation of blueberries.
  • To enhance blueberry supply chain management through predictive modeling and uncertainty quantification.

Main Methods:

  • An analytic hierarchy process-principal component analysis-long short-term memory (AHP-PCA-LSTM) architecture was developed for shelf-life prediction.
  • Gaussian process regression (GPR) with Bayesian optimization was used for temperature-based regulation.
Keywords:
blueberry preservationdeep learningneural networkprediction and regulationremaining shelf life

Related Experiment Videos

Last Updated: Jul 7, 2026

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

  • An autoencoder constructed a "freshness" index, validated against fruit decay and sensory data.

    • Main Results:

    • The AHP-PCA-LSTM model achieved a high-precision forecasting error rate of 2.5%, significantly outperforming Arrhenius models.
    • Catalase was identified as the primary quality determinant (0.34 weight).
    • GPR successfully mapped nonlinear freshness-temperature dependencies, enabling optimal storage condition deduction.

    Conclusions:

    • The integrated AHP-PCA-LSTM and GPR framework provides a robust system for predicting blueberry shelf life and optimizing storage.
    • This approach offers a paradigm for advanced supply chain management, reducing food waste and ensuring consumer quality.
    • Quantification of predictive uncertainty via 95% confidence intervals enhances system reliability.