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

Global warming scenarios for the Eastern Adriatic Sea indicate a higher risk of invasiveness of non-native marine organisms relative to current climate conditions.

Marine life science & technology·2024
Same author

pH-Dependent Behavior of Novel 5-FU Delivery System in Environmental Conditions Comparable to the Gastro-Intestinal Tract.

Pharmaceutics·2023
Same author

Novel flexible sensing technology for nondestructive detection on live fish health/quality during waterless and low-temperature transportation.

Biosensors & bioelectronics·2023
Same author

Impact of COVID-19 on Croatian mariculture: Findings from the first national surveys.

Marine policy·2022
Same author

Comparative screening the life-time composition and crystallinity variation in gilthead seabream otoliths Sparus aurata from different marine environments.

Scientific reports·2022
Same author

Rapid and Application-Tailored Assessment Tool for Biogenic Powders from Crustacean Shell Waste: Fourier Transform-Infrared Spectroscopy Complemented with X-ray Diffraction, Scanning Electron Microscopy, and Nuclear Magnetic Resonance Spectroscopy.

ACS omega·2021

Related Experiment Video

Updated: Jun 12, 2025

Necropsy-based Wild Fish Health Assessment
07:57

Necropsy-based Wild Fish Health Assessment

Published on: September 11, 2018

17.1K

Supervised learning-based artificial senses for non-destructive fish quality classification.

Rehan Saeed1, Branko Glamuzina2, Mai Thi Tuyet Nga3

  • 1Beijing Laboratory of Food Quality and Safety, College of Engineering, China Agricultural University, Beijing, 100083, PR China; Department of Automation, School of Information Science and Technology, University of Science and Technology of China, Hefei, Anhui, 230027, PR China.

Biosensors & Bioelectronics
|September 17, 2024
PubMed
Summary

This study introduces an artificial sensory system for early fish quality prediction, outperforming human senses. It accurately detects spoilage using gas and texture data, paving the way for automated food supply chains.

Keywords:
Fish qualityMachine learningNeural networkSensorTexture

More Related Videos

Long-term Behavioral Tracking of Freely Swimming Weakly Electric Fish
10:56

Long-term Behavioral Tracking of Freely Swimming Weakly Electric Fish

Published on: March 6, 2014

12.5K
Anesthesia-free Heartbeat Measurements in Freely Moving Zebrafish
03:57

Anesthesia-free Heartbeat Measurements in Freely Moving Zebrafish

Published on: April 18, 2025

279

Related Experiment Videos

Last Updated: Jun 12, 2025

Necropsy-based Wild Fish Health Assessment
07:57

Necropsy-based Wild Fish Health Assessment

Published on: September 11, 2018

17.1K
Long-term Behavioral Tracking of Freely Swimming Weakly Electric Fish
10:56

Long-term Behavioral Tracking of Freely Swimming Weakly Electric Fish

Published on: March 6, 2014

12.5K
Anesthesia-free Heartbeat Measurements in Freely Moving Zebrafish
03:57

Anesthesia-free Heartbeat Measurements in Freely Moving Zebrafish

Published on: April 18, 2025

279

Area of Science:

  • Food Science
  • Sensory Science
  • Artificial Intelligence

Background:

  • Current human sensory methods are insufficient for automated fish quality monitoring and controlled storage.
  • Single quality index monitoring fails to predict freshness loss, impacting consumer acceptance.
  • Automating fish quality assessment is crucial for the food supply chain.

Purpose of the Study:

  • To develop and validate a comprehensive artificial sensory system for early fish quality prediction.
  • To integrate multiple sensor data for enhanced accuracy in freshness assessment.
  • To enable automated quality control in fish supply chains.

Main Methods:

  • Utilized a multi-parametric approach including gas sensors, texturometer, pH meter, camera, and TVB-N analysis on rainbow trout.
  • Applied data preprocessing and correlation analysis to identify key quality parameters (trimethylamine, ammonia, CO2, hardness, adhesiveness).
  • Developed a back-propagation neural network model using identified gas and textural parameters for quality classification.

Main Results:

  • Achieved approximately 99% prediction accuracy in classifying fresh and spoiled fish using gas and textural data.
  • Identified key parameters like trimethylamine, ammonia, carbon dioxide, hardness, and adhesiveness crucial for quality prediction.
  • Demonstrated the system's capability for early detection of freshness loss in fish.

Conclusions:

  • The developed artificial sensory system effectively predicts fish quality and detects early signs of spoilage.
  • Multiparametric fusion of texture and gas data significantly enhances prediction accuracy.
  • The system shows strong potential for complete automation of fish quality monitoring in the food supply chain.