September 26, 2025 11:09
Waste Classification Model Optimization with Modified MobileNetV3 for Efficient Waste Management
Oleh : itspublikasi | | Source : -
Abstract
The increase in population and economic activity has a significant impact on the amount of waste. Data in 2023 states that waste in Indonesia still cannot be managed properly. One solution to overcome this problem is through recycling with waste sorting as a crucial stage. This research develops a waste classification model using modified MobileNetV3S. The classification process is performed using Convolutional Neural Network (CNN) method and parameter fine-tuning. This model is able to classify five different categories of waste, namely plastic bottles, leaves, plastic sheets, paper, and metal. The results show that the validation accuracy reaches 96.2% with a loss value of 0.049. These results can significantly contribute to better and sustainable waste management efforts.
Keywords
Waste Management; Classification; MobileNetV3S; Fine-Tuning
Full Text:
Related News
-
Waste Classification Model Optimization with Modified MobileNetV3 for Efficient Waste Management
Putri Andani, Ramadian Ridho Illahi, I Wayan Sudiarta, Marzuki Marzuki, Arif Budianto Abstract The increase in population and
September 26, 2025 11:09 -
Quantum Square Wells with Capacitive Walls: A Toy Model for Quantum Capacitors
Arifin Achmad Abstract This research aims to determine the energy quantization in a one-dimensional infinite square well modified
September 26, 2025 11:09 -
The Influence of Cross Equatorial Northerly Surge (CENS) and El Niño Southern Oscillation (ENSO) on Atmospheric Dynamics in Western Indonesia
Jhon Paul Estomihi Togatorop, Sayful Amri, Jerremy Mezac Sopacua Abstract Indonesia is located between the Asian and Australian
September 26, 2025 11:09 -
Image Quality Assessment of In-House Phantom for Pediatric Computed Tomography
Audiena Gelung Prayitno, Dafa Miftahuddin, Aditya Prayugo Hariyanto, Muhammad Roslan Abdul Gani, Endarko Endarko Abstract The study aimed
September 26, 2025 11:09
