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

Attenuated Total Reflectance (ATR) Infrared Spectroscopy: Overview01:13

Attenuated Total Reflectance (ATR) Infrared Spectroscopy: Overview

415
Attenuated total reflectance (ATR) infrared spectroscopy is a powerful analytical technique used to study the composition of materials. It is widely employed in chemistry, materials science, forensic science, and other fields where sample characterization is required. ATR has several advantages over traditional transmission IR spectroscopy, including the requirement of little to no sample preparation and the ability to analyze a wide range of samples.
The ATR process begins by directing a beam...
415

You might also read

Related Articles

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

Sort by
Same author

A novel flexible composite polymer electrolyte with robust interfaces and synergistic ion channels for solid-state sodium metal batteries.

Journal of colloid and interface science·2026
Same author

Luminescent hydrogel-enabled electrochemiluminescent aptasensor and portable analyzer for on-site quantification of acetamiprid in vegetables.

Journal of hazardous materials·2026
Same author

Dietary Paeonol Supplementation Alleviates Waterborne Cadmium-Induced Damages in Gut Barrier Function in Largemouth Bass (Micropterus salmoides).

Biological trace element research·2026
Same author

Cross-linked time-resolved fluorescence immunochromatographic strip for the detection of neonicotinoid pesticide residues: Competitive principle, rapid, reliable and environmentally friendly pretreatment.

Food research international (Ottawa, Ont.)·2026
Same author

Correction: The genome of Phlebotomus chinensis, the primary vector of visceral leishmaniasis in China: insights from chromosome-level assembly and comparative analysis.

Infectious diseases of poverty·2026
Same author

Ultrasensitive and Rapid Detection of Pesticide Residues in Vegetables by Aptamer-Functionalized Carbon Nanotube Field-Effect Transistor Biosensors.

Journal of agricultural and food chemistry·2026

Related Experiment Video

Updated: Jul 16, 2025

RGB and Spectral Root Imaging for Plant Phenotyping and Physiological Research: Experimental Setup and Imaging Protocols
11:37

RGB and Spectral Root Imaging for Plant Phenotyping and Physiological Research: Experimental Setup and Imaging Protocols

Published on: August 8, 2017

16.2K

A multivariate algorithm for identifying contaminated peanut using visible and near-infrared hyperspectral imaging.

Zhen Guo1, Jing Zhang2, Jiashuai Sun1

  • 1School of Agricultural Engineering and Food Science, Shandong University of Technology, No. 266 Xincun Xilu, Zibo, Shandong, 255049, China; Shandong Provincial Engineering Research Center of Vegetable Safety and Quality Traceability, No. 266 Xincun Xilu, Zibo, Shandong, 255049, China; Zibo City Key Laboratory of Agricultural Product Safety Traceability, No. 266 Xincun Xilu, Zibo, Shandong, 255049, China.

Talanta
|September 18, 2023
PubMed
Summary

A new UMAP-ISOGA-CNN algorithm optimizes deep learning models for food safety. It identifies Aspergillus flavus contamination and storage time in peanuts using hyperspectral imaging.

Keywords:
Convolutional neural networkGenetic algorithmHyperspectral imagingPeanut kernelUniform manifold approximation and projection

More Related Videos

Author Spotlight: Unraveling Plant Responses to Abiotic Stresses Using the PlantScreen Robotic Platform
06:28

Author Spotlight: Unraveling Plant Responses to Abiotic Stresses Using the PlantScreen Robotic Platform

Published on: June 7, 2024

1.8K
Applying Hyperspectral Reflectance Imaging to Investigate the Palettes and the Techniques of Painters
07:05

Applying Hyperspectral Reflectance Imaging to Investigate the Palettes and the Techniques of Painters

Published on: June 18, 2021

2.5K

Related Experiment Videos

Last Updated: Jul 16, 2025

RGB and Spectral Root Imaging for Plant Phenotyping and Physiological Research: Experimental Setup and Imaging Protocols
11:37

RGB and Spectral Root Imaging for Plant Phenotyping and Physiological Research: Experimental Setup and Imaging Protocols

Published on: August 8, 2017

16.2K
Author Spotlight: Unraveling Plant Responses to Abiotic Stresses Using the PlantScreen Robotic Platform
06:28

Author Spotlight: Unraveling Plant Responses to Abiotic Stresses Using the PlantScreen Robotic Platform

Published on: June 7, 2024

1.8K
Applying Hyperspectral Reflectance Imaging to Investigate the Palettes and the Techniques of Painters
07:05

Applying Hyperspectral Reflectance Imaging to Investigate the Palettes and the Techniques of Painters

Published on: June 18, 2021

2.5K

Area of Science:

  • Machine Learning
  • Food Science
  • Spectroscopy

Background:

  • Accurate detection of food contamination and spoilage is crucial for public health and the food industry.
  • Traditional methods for assessing food quality can be time-consuming and may not detect early signs of spoilage or contamination.
  • Deep learning offers potential for rapid and accurate food quality assessment, but model optimization is complex.

Purpose of the Study:

  • To introduce a novel algorithm, Uniform Manifold Approximation and Projection-Improved Simultaneous Optimization Genetic Algorithm-Convolutional Neural Network (UMAP-ISOGA-CNN), for optimizing deep learning models.
  • To apply this algorithm to identify peanut kernels contaminated with Aspergillus flavus and determine their storage time using hyperspectral imaging.
  • To visualize and understand the feature space of the developed deep learning model.

Main Methods:

  • Development of the UMAP-ISOGA-CNN algorithm, which simultaneously optimizes Convolutional Neural Network (CNN) architecture, hyperparameters, and optimizer.
  • Utilization of Uniform Manifold Approximation and Projection (UMAP) for visualizing the feature space of the ISOGA-CNN model.
  • Integration of visible and near-infrared hyperspectral imaging for data acquisition on peanut kernels.

Main Results:

  • The UMAP-ISOGA-CNN algorithm successfully optimized the CNN model for identifying peanut kernel contamination and storage time.
  • Hyperspectral imaging combined with the UMAP-ISOGA-CNN algorithm demonstrated effectiveness in distinguishing between fresh and contaminated peanuts.
  • UMAP provided valuable insights into the feature representation learned by the ISOGA-CNN model.

Conclusions:

  • The UMAP-ISOGA-CNN algorithm is a powerful tool for optimizing deep learning models in food safety applications.
  • This approach enhances the ability to monitor food freshness and detect contaminants like Aspergillus flavus.
  • The study contributes to a better understanding of deep learning mechanisms and has practical implications for the food industry.