Optimizing Industrial E-Waste Recycling with Attention-Driven Deep Learning for PCB Segmentation Using Hyperspectral Imaging

Trishna Barman; Sonya Coleman; Dermot Kerr; JP Quinn; Shane Harrigan

doi:10.1109/CIETES63869.2025.10995066

Optimizing Industrial E-Waste Recycling with Attention-Driven Deep Learning for PCB Segmentation Using Hyperspectral Imaging

Trishna Barman
, Sonya Coleman
, Dermot Kerr
, JP Quinn
, Shane Harrigan

Research output: Chapter in Book/Report/Conference proceeding › Conference contribution › peer-review

3 Citations (Scopus)

Abstract

Recently, the generation of electronic waste (E-waste) has increased significantly due to rapid changes in
consumer demand and advancements in technology. Recycling
E-waste is essential for boosting the economy and advancing
the sustainability of the electronics industry. Printed circuit
boards (PCBs) contribute significantly to E-waste, as they are
widely used in various electronic devices. However, a challenge in
recycling E-waste is the rapidly and diversely changing material
composition. To enhance the efficacy of E-waste recycling, an
automated, non-invasive method is essential for process control and decision-making. By exploiting hyperspectral imaging
(HSI), which offers spectroscopic analysis to accurately identify
materials, this paper presents attention-based deep learning
segmentation models to accurately identify components in PCBs.
This approach allows for the automatic extraction of information
from E-waste, leading to more efficient and optimized recycling
practices.

Original language	English
Title of host publication	2025 IEEE Symposia on Computational Intelligence for Energy, Transport and Environmental Sustainability, CIETES 2025
Subtitle of host publication	2025 IEEE Symposium on Computational Intelligence for Energy, Transport and Environmental Sustainability
Publisher	IEEE
Pages	1-7
Number of pages	7
ISBN (Electronic)	979-8-3315-0825-8
ISBN (Print)	979-8-3315-0825-8, 979-8-3315-0826-5
DOIs	https://doi.org/10.1109/CIETES63869.2025.10995066
Publication status	Published (in print/issue) - 20 Mar 2025

Publication series

Name	2025 IEEE Symposia on Computational Intelligence for Energy, Transport and Environmental Sustainability, CIETES 2025

Bibliographical note

Publisher Copyright:
© 2025 IEEE.

Data Access Statement

PCB-Vision dataset: https://rodare.hzdr.de/record/2704

Funding

This research is funded by Innovate UK under the Smart Manufacturing Data Hub project (contract no. 10017032) - www.smdh.uk.

Funders	Funder number
Innovate UK	10017032
Innovate UK

UN SDGs

This output contributes to the following UN Sustainable Development Goals (SDGs)

SDG 12 Responsible Consumption and Production

Keywords

Electronic waste (E-waste)
Hyperspectral Imaging
Deep learning (DL)
Automatic visual inspection
Printed circuit board (PCB)
Recycling
Hyperspectral imaging

Access to Document

10.1109/CIETES63869.2025.10995066

Cite this

Barman, T., Coleman, S., Kerr, D., Quinn, JP., & Harrigan, S. (2025). Optimizing Industrial E-Waste Recycling with Attention-Driven Deep Learning for PCB Segmentation Using Hyperspectral Imaging. In 2025 IEEE Symposia on Computational Intelligence for Energy, Transport and Environmental Sustainability, CIETES 2025: 2025 IEEE Symposium on Computational Intelligence for Energy, Transport and Environmental Sustainability (pp. 1-7). (2025 IEEE Symposia on Computational Intelligence for Energy, Transport and Environmental Sustainability, CIETES 2025). IEEE. https://doi.org/10.1109/CIETES63869.2025.10995066

Barman, Trishna ; Coleman, Sonya ; Kerr, Dermot et al. / Optimizing Industrial E-Waste Recycling with Attention-Driven Deep Learning for PCB Segmentation Using Hyperspectral Imaging. 2025 IEEE Symposia on Computational Intelligence for Energy, Transport and Environmental Sustainability, CIETES 2025: 2025 IEEE Symposium on Computational Intelligence for Energy, Transport and Environmental Sustainability. IEEE, 2025. pp. 1-7 (2025 IEEE Symposia on Computational Intelligence for Energy, Transport and Environmental Sustainability, CIETES 2025).

@inproceedings{e32b50a8c8e148a0a0dc3ea8dc318621,

title = "Optimizing Industrial E-Waste Recycling with Attention-Driven Deep Learning for PCB Segmentation Using Hyperspectral Imaging",

abstract = "Recently, the generation of electronic waste (E-waste) has increased significantly due to rapid changes in consumer demand and advancements in technology. Recycling E-waste is essential for boosting the economy and advancing the sustainability of the electronics industry. Printed circuit boards (PCBs) contribute significantly to E-waste, as they are widely used in various electronic devices. However, a challenge in recycling E-waste is the rapidly and diversely changing material composition. To enhance the efficacy of E-waste recycling, an automated, non-invasive method is essential for process control and decision-making. By exploiting hyperspectral imaging (HSI), which offers spectroscopic analysis to accurately identify materials, this paper presents attention-based deep learning segmentation models to accurately identify components in PCBs. This approach allows for the automatic extraction of information from E-waste, leading to more efficient and optimized recycling practices.",

keywords = "Electronic waste (E-waste), Hyperspectral Imaging, Deep learning (DL), Automatic visual inspection, Printed circuit board (PCB), Recycling, Hyperspectral imaging",

author = "Trishna Barman and Sonya Coleman and Dermot Kerr and JP Quinn and Shane Harrigan",

note = "Publisher Copyright: {\textcopyright} 2025 IEEE.",

year = "2025",

month = mar,

day = "20",

doi = "10.1109/CIETES63869.2025.10995066",

language = "English",

isbn = "979-8-3315-0825-8",

series = "2025 IEEE Symposia on Computational Intelligence for Energy, Transport and Environmental Sustainability, CIETES 2025",

publisher = "IEEE",

pages = "1--7",

booktitle = "2025 IEEE Symposia on Computational Intelligence for Energy, Transport and Environmental Sustainability, CIETES 2025",

address = "United States",

}

Barman, T, Coleman, S , Kerr, D , Quinn, JP & Harrigan, S 2025, Optimizing Industrial E-Waste Recycling with Attention-Driven Deep Learning for PCB Segmentation Using Hyperspectral Imaging. in 2025 IEEE Symposia on Computational Intelligence for Energy, Transport and Environmental Sustainability, CIETES 2025: 2025 IEEE Symposium on Computational Intelligence for Energy, Transport and Environmental Sustainability. 2025 IEEE Symposia on Computational Intelligence for Energy, Transport and Environmental Sustainability, CIETES 2025, IEEE, pp. 1-7. https://doi.org/10.1109/CIETES63869.2025.10995066

Optimizing Industrial E-Waste Recycling with Attention-Driven Deep Learning for PCB Segmentation Using Hyperspectral Imaging. / Barman, Trishna; Coleman, Sonya ; Kerr, Dermot et al.
2025 IEEE Symposia on Computational Intelligence for Energy, Transport and Environmental Sustainability, CIETES 2025: 2025 IEEE Symposium on Computational Intelligence for Energy, Transport and Environmental Sustainability. IEEE, 2025. p. 1-7 (2025 IEEE Symposia on Computational Intelligence for Energy, Transport and Environmental Sustainability, CIETES 2025).

Research output: Chapter in Book/Report/Conference proceeding › Conference contribution › peer-review

TY - GEN

T1 - Optimizing Industrial E-Waste Recycling with Attention-Driven Deep Learning for PCB Segmentation Using Hyperspectral Imaging

AU - Barman, Trishna

AU - Coleman, Sonya

AU - Kerr, Dermot

AU - Quinn, JP

AU - Harrigan, Shane

PY - 2025/3/20

Y1 - 2025/3/20

N2 - Recently, the generation of electronic waste (E-waste) has increased significantly due to rapid changes in consumer demand and advancements in technology. Recycling E-waste is essential for boosting the economy and advancing the sustainability of the electronics industry. Printed circuit boards (PCBs) contribute significantly to E-waste, as they are widely used in various electronic devices. However, a challenge in recycling E-waste is the rapidly and diversely changing material composition. To enhance the efficacy of E-waste recycling, an automated, non-invasive method is essential for process control and decision-making. By exploiting hyperspectral imaging (HSI), which offers spectroscopic analysis to accurately identify materials, this paper presents attention-based deep learning segmentation models to accurately identify components in PCBs. This approach allows for the automatic extraction of information from E-waste, leading to more efficient and optimized recycling practices.

AB - Recently, the generation of electronic waste (E-waste) has increased significantly due to rapid changes in consumer demand and advancements in technology. Recycling E-waste is essential for boosting the economy and advancing the sustainability of the electronics industry. Printed circuit boards (PCBs) contribute significantly to E-waste, as they are widely used in various electronic devices. However, a challenge in recycling E-waste is the rapidly and diversely changing material composition. To enhance the efficacy of E-waste recycling, an automated, non-invasive method is essential for process control and decision-making. By exploiting hyperspectral imaging (HSI), which offers spectroscopic analysis to accurately identify materials, this paper presents attention-based deep learning segmentation models to accurately identify components in PCBs. This approach allows for the automatic extraction of information from E-waste, leading to more efficient and optimized recycling practices.

KW - Electronic waste (E-waste)

KW - Hyperspectral Imaging

KW - Deep learning (DL)

KW - Automatic visual inspection

KW - Printed circuit board (PCB)

KW - Recycling

KW - Hyperspectral imaging

UR - https://pure.ulster.ac.uk/en/publications/e32b50a8-c8e1-48a0-a0dc-3ea8dc318621

UR - https://www.scopus.com/pages/publications/105007696605

U2 - 10.1109/CIETES63869.2025.10995066

DO - 10.1109/CIETES63869.2025.10995066

M3 - Conference contribution

SN - 979-8-3315-0825-8

SN - 979-8-3315-0826-5

T3 - 2025 IEEE Symposia on Computational Intelligence for Energy, Transport and Environmental Sustainability, CIETES 2025

SP - 1

EP - 7

BT - 2025 IEEE Symposia on Computational Intelligence for Energy, Transport and Environmental Sustainability, CIETES 2025

PB - IEEE

ER -

Barman T, Coleman S , Kerr D , Quinn JP, Harrigan S. Optimizing Industrial E-Waste Recycling with Attention-Driven Deep Learning for PCB Segmentation Using Hyperspectral Imaging. In 2025 IEEE Symposia on Computational Intelligence for Energy, Transport and Environmental Sustainability, CIETES 2025: 2025 IEEE Symposium on Computational Intelligence for Energy, Transport and Environmental Sustainability. IEEE. 2025. p. 1-7. (2025 IEEE Symposia on Computational Intelligence for Energy, Transport and Environmental Sustainability, CIETES 2025). doi: 10.1109/CIETES63869.2025.10995066

Optimizing Industrial E-Waste Recycling with Attention-Driven Deep Learning for PCB Segmentation Using Hyperspectral Imaging

Abstract

Publication series

Bibliographical note

Data Access Statement

Funding

UN SDGs

Keywords

Access to Document

Other files and links

Fingerprint

Cite this