Neo, Edward Ren Kai, Low, Jonathan Sze Choong, Goodship, Vannessa and Debattista, Kurt (2023) Deep learning for chemometric analysis of plastic spectral data from infrared and Raman databases. Resources, Conservation and Recycling, 188 . 106718. doi:10.1016/j.resconrec.2022.106718 ISSN 0921-3449.

Preview

PDF WRAP-Deep-learning-for-chemometric-analysis-of-plastic-spectral-data-from-infrared-and-Raman-databases-Neo-2023.pdf - Published Version - Requires a PDF viewer. Available under License Creative Commons: Attribution-Noncommercial 4.0. Download (4Mb) | Preview

Request Changes to record.

Abstract

Increasing plastic recycling rates is key to addressing plastic pollution. New technologies such as chemometric analysis of spectral data have shown great promises in improving the plastic sorting efficiency to boost recycling rates. In this work, a novel deep learning architecture, PolymerSpectraDecisionNet (PSDN) was developed, consisting of convolutional neural networks, residual networks and inception networks in a decision tree structure. To better represent the conditions in the plastic recycling industry, the models were built to identify the most widely recycled polymers – polyethylene, polypropylene and polyethylene terephthalate from open-sourced infrared and Raman spectral dataset containing over 20 different polymers. PSDN performed better than end-to-end neural networks, obtaining an accuracy of 0.949 and 0.967 with the Raman and infrared datasets respectively. The use of deep learning can also distinguish between weathered and unaged polymer samples, with accuracies of 0.954 for high density polyethylene and 0.906 for polyethylene terephthalate.

Item Type:	Journal Article
Subjects:	Q Science > QD Chemistry T Technology > TD Environmental technology. Sanitary engineering
Divisions:	Faculty of Science, Engineering and Medicine > Engineering > WMG (Formerly the Warwick Manufacturing Group)
Library of Congress Subject Headings (LCSH):	Plastic scrap -- Recycling, Plastics -- Recycling, Plastics industry and trade -- Waste disposal, Polymers -- Recycling, Chemometrics, Spectrum analysis
Journal or Publication Title:	Resources, Conservation and Recycling
Publisher:	Elsevier BV
ISSN:	0921-3449
Official Date:	January 2023
Dates:	Date Event January 2023 Published 21 October 2022 Available 12 October 2022 Accepted 27 May 2022 Submitted
Volume:	188
Number of Pages:	11
Article Number:	106718
DOI:	10.1016/j.resconrec.2022.106718
Status:	Peer Reviewed
Publication Status:	Published
Access rights to Published version:	Open Access (Creative Commons)
Date of first compliant deposit:	24 October 2022
Date of first compliant Open Access:	24 October 2022

Request changes or add full text files to a record

Repository staff actions (login required)

View Item

Downloads