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: Jun 16, 2026

Deep Neural Networks for Image-Based Dietary Assessment
13:19

Deep Neural Networks for Image-Based Dietary Assessment

Published on: March 13, 2021

Multimodal Sensor Fusion for Non-Destructive Tea Quality Evaluation: Deep Learning-Enabled Methods, Applications, and

Xinyu Hu1, Meng Zhang1, Biyue Yang1

  • 1School of Agricultural Engineering, Jiangsu University, Zhenjiang 212013, China.

Foods (Basel, Switzerland)
|May 27, 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

Selective Inactivation Strategies for Vegetable Raw Materials: Regulating Microbial Communities to Ensure the Safety and Quality of Fermented Vegetables.

Foods (Basel, Switzerland)·2025
Same author

Analysis of Microbial Diversity Dominating Nitrite Enzymatic Degradation and Acidic Degradation in the Fermentation Broth of Northeast Sauerkraut.

Foods (Basel, Switzerland)·2025
Same author

Oerskovia flava sp. nov., a deoxynivalenol (DON)-degrading actinomycete isolated from the rhizosphere soil of long-term continuous cropping cucumber.

Antonie van Leeuwenhoek·2024
Same author

Nocardioides limicola sp. nov., an alkaliphilic alkane degrading bacterium isolated from oilfield alkali-saline soil.

Antonie van Leeuwenhoek·2024
Same author

Cold Plasma Controls Nitrite Hazards by Modulating Microbial Communities in Pickled Radish.

Foods (Basel, Switzerland)·2023
Same author

Alcanivorax limicola sp. nov., isolated from a soda alkali-saline soil.

Archives of microbiology·2022

This review explores advanced multimodal sensing and deep learning for non-destructive tea quality evaluation. Combining complementary sensors significantly enhances accuracy, but challenges in data standardization and model interpretability remain for practical deployment.

Area of Science:

  • Food Science and Technology
  • Analytical Chemistry
  • Artificial Intelligence in Agriculture

Background:

  • Traditional tea quality assessment relies on subjective sensory evaluation and destructive lab methods.
  • There is a growing need for rapid, non-destructive, and data-driven approaches in tea quality evaluation.
  • Multimodal sensing integrated with deep learning offers a promising avenue for objective tea quality assessment.

Purpose of the Study:

  • To review recent advancements in multimodal sensing and deep learning for tea quality evaluation.
  • To emphasize sensor complementarity, data-fusion strategies, applications, and deployment limitations.
  • To identify future research directions for practical implementation.

Main Methods:

  • Review of major sensing modalities: machine vision, spectroscopy (NIR, MIR, Raman, fluorescence), hyperspectral imaging, electronic nose/tongue.
Keywords:
data fusiondeep learningmultimodal sensingnon-destructive evaluationsensor complementaritytea quality

Related Experiment Videos

Last Updated: Jun 16, 2026

Deep Neural Networks for Image-Based Dietary Assessment
13:19

Deep Neural Networks for Image-Based Dietary Assessment

Published on: March 13, 2021

  • Analysis of deep learning integration for data fusion and quality prediction.
  • Examination of applications in grading, chemical composition prediction, aroma/flavor characterization, fermentation monitoring, and safety assessment.

    • Main Results:

    • Multimodal sensing approaches outperform single-sensor systems when modalities provide complementary information.
    • Applications demonstrated across diverse tea types (green, black, dark, matcha, jasmine).
    • Key limitations identified: small/non-standardized datasets, insufficient validation, sensor instability, model transferability issues, high computational cost, and poor interpretability.

    Conclusions:

    • Multimodal sensing and deep learning show significant potential for objective and non-destructive tea quality evaluation.
    • Overcoming challenges in data standardization, validation, and model interpretability is crucial for practical translation.
    • Future research should focus on standardized datasets, interpretable models, and robust multi-sensor platforms for deployable solutions.