Municipal solid waste classification using transfer learning

Marco Tianyu Chen

doi:10.1117/12.2687046

24 October 2023 Municipal solid waste classification using transfer learning

Marco Tianyu Chen

Proceedings Volume 12804, Second International Conference on Sustainable Technology and Management (ICSTM 2023); 128040K (2023) https://doi.org/10.1117/12.2687046
Event: 2nd International Conference on Sustainable Technology and Management (ICSTM2023), 2023, Dongguan, China

Abstract

Municipal solid waste (MSW), also known as “common trash,” denotes daily objects that can be found within standard households. As annual MSW production rates rise, a system-assisted nonintuitive waste classification that benefits global citizens is in rapid development. In this paper, MSW classification in China, one of the biggest MSW producers in the world, is discussed. There are four types in China’s MSW paradigm: dry (general), wet (kitchen), hazardous, and recyclable. Four pre-trained convolutional neural networks, including ResNet50, MobileNetV3, EfficientNetV2, and InceptionV3 are employed to process a dataset containing roughly 28,000 images with a transfer learning approach.

Citation Download Citation

Marco Tianyu Chen "Municipal solid waste classification using transfer learning", Proc. SPIE 12804, Second International Conference on Sustainable Technology and Management (ICSTM 2023), 128040K (24 October 2023); https://doi.org/10.1117/12.2687046

ACCESS THE FULL ARTICLE

INSTITUTIONAL
Select your institution to access the SPIE Digital Library.

SELECT YOUR INSTITUTION

PERSONAL
Sign in with your SPIE account to access your personal subscriptions or to use specific features such as save to my library, sign up for alerts, save searches, etc.

PERSONAL SIGN IN

No SPIE Account? Create one

PURCHASE THIS CONTENT

SUBSCRIBE TO DIGITAL LIBRARY

50 downloads per 1-year subscription

Members: $195

Non-members: $335 ADD TO CART

25 downloads per 1 - year subscription

Members: $145

Non-members: $250 ADD TO CART

PURCHASE SINGLE ARTICLE

Includes PDF, HTML & Video, when available