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: Mar 28, 2026

Author Spotlight: Enhancement of Salient Object Detection for Smart Grid Applications
03:31

Author Spotlight: Enhancement of Salient Object Detection for Smart Grid Applications

Published on: December 15, 2023

1.2K

ResSeMo: deep convolutional neural network integration for high-accuracy waste classification and efficient

Tao Liu1, Bingzheng Li2, Zihao Wang3

  • 1School of Public Administration, Northeast Agricultural University, Harbin, 150030, China.

Scientific Reports
|March 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

Microwave-assisted drying techniques to enhance the drying efficiency and quality of dried Gastrodia elata.

Journal of the science of food and agriculture·2025
Same author

Effects of innovative dry-blanching on moisture, cell wall structure, physicochemical properties and volatile compounds of microwave infrared coupled dried ginger (Zingiber officinale roscoe).

Food chemistry·2025
Same author

Octenyl succinic anhydride starch enhanced 3D printability of corn starch-based emulsion-filled gels incorporating egg yolk.

International journal of biological macromolecules·2024
Same author

A Lightweight SPI-Flash Controller Based on AMBA AHB-Lite Bus.

Micromachines·2024
Same author

Physicochemical properties, structure and biological activity of ginger polysaccharide: Effect of microwave infrared dual-field coupled drying.

International journal of biological macromolecules·2024
Same author

Sodium carboxymethyl cellulose hydrogels containing montmorillonite-NaClO<sub>2</sub> for postharvest preservation of Chinese bayberries.

Food chemistry·2024

A new lightweight deep learning model, ResSeMo, enhances urban waste classification accuracy and efficiency. It shows strong performance even in complex environments and against disturbances, supporting smart waste management systems.

Area of Science:

  • Computer Science
  • Artificial Intelligence
  • Environmental Science

Background:

  • Traditional waste classification methods struggle with efficiency and accuracy due to increasing urban waste.
  • Deep learning offers solutions but faces challenges in accuracy, processing speed, and adaptability for complex scenarios.

Purpose of the Study:

  • To propose a lightweight waste classification model, ResSeMo, that optimizes multi-module collaboration.
  • To enhance classification accuracy, reduce computational load, and improve robustness in complex environments.

Main Methods:

  • Developed ResSeMo by integrating ResNeXt's feature extraction, SENet's channel attention, and MobileNetV3's lightweight design.
  • Evaluated model performance on TrashNet and TACO datasets, including stability tests with noise and blur.
Keywords:
Deep convolutional neural networks (DeepCNN)High-accuracy recognitionLightweight integrationWaste classificationWaste processing optimization

More Related Videos

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

Deep Neural Networks for Image-Based Dietary Assessment

Published on: March 13, 2021

10.1K

Related Experiment Videos

Last Updated: Mar 28, 2026

Author Spotlight: Enhancement of Salient Object Detection for Smart Grid Applications
03:31

Author Spotlight: Enhancement of Salient Object Detection for Smart Grid Applications

Published on: December 15, 2023

1.2K
Deep Neural Networks for Image-Based Dietary Assessment
13:19

Deep Neural Networks for Image-Based Dietary Assessment

Published on: March 13, 2021

10.1K

Main Results:

  • ResSeMo achieved 91.3% accuracy on TrashNet and 86.9% on TACO.
  • Demonstrated high stability with minimal accuracy drops (4.1% on TrashNet, 6.4% on TACO) under Gaussian noise and random blur.
  • Outperformed traditional models like VGG16 in anti-disturbance capabilities.

Conclusions:

  • ResSeMo effectively improves waste classification accuracy and robustness.
  • The lightweight model is suitable for complex environments and provides a strong foundation for smart waste classification systems.