Synapse
⌘+K
Synapse
PulseExploreClubsResearchersJournals
Instagram
HomeClubsExplore
October 1, 2025Journal of Scientific Reports-AOpen Access

Deep learning-based automated garbage image classification using light-weight models

View Full Paper
Ask AI
Bookmark
Share

Authors

GYGözde Yolcu

Discussion

Loading...

Member takes

Overview

Deep learning demonstrates high accuracy in garbage classification using light-weight models, suggesting improved waste management solutions.

Key Points

  • EfficientNetb2 achieved an accuracy of 0.9768 in classifying five types of waste, showing its effectiveness.
  • Transfer learning significantly improved the performance of models, with EfficientNetb2 outperforming models trained from scratch by 18%.
  • The study utilized light-weight models suitable for embedded systems, emphasizing the reduced processing load required for deployment.
  • High accuracy on a second dataset indicates strong generalization ability of the trained models, potentially enhancing smart city waste management.

Cite This Study

Gözde Yolcu (2025) studied this question.

synapsesocial.com/papers/68dd91dafe798ba2fc499189https://doi.org/10.59313/jsr-a.1669471
View Full Paper
Ask AI
Bookmark
Share

Also Consider

Synapse has enriched 5 closely related papers on similar clinical questions. Consider them for comparative context:

  1. 1Analysis of Machine Learning Recognition Method for Garbage Classification2025
  2. 2Garbage Classification Using Deep Learning2024
  3. 3Image-Based Waste Classification Using a Hybrid Deep Learning Architecture with Transfer Learning and Edge AI Deployment2026 · 3 citations
  4. 4GarbageNet: A Unified Learning Framework for Robust Garbage Classification2021 · 62 citations
  5. 5A Strong and Durable Neural Network System for Optimal Biodegradable Garbage Categorization2025