FETCH : A Fast and Efficient Technique for Channel Selection in EEG Wearable Systems
Amirshahi, Alireza ; Dan, Jonathan ; Miranda, José ; Aminifar, Amir LU
and Atienza, David
(2024)
5th Annual Conference on Health, Inference, and Learning, CHIL 2024
In Proceedings of Machine Learning Research
248.
p.397-409
- Abstract
The rapid development of wearable biomedical systems now enables real-time monitoring of electroencephalography (EEG) signals. Acquisition of these signals relies on electrodes. These systems must meet the design challenge of selecting an optimal set of electrodes that balances performance and usability constraints. The search for the optimal subset of electrodes from a larger set is a problem with combinatorial complexity. While existing research has primarily focused on search strategies that only explore limited combinations, our methodology proposes a computationally efficient way to explore all combinations. To avoid the computational burden associated with training the model for each combination, we leverage an innovative approach... (More)
The rapid development of wearable biomedical systems now enables real-time monitoring of electroencephalography (EEG) signals. Acquisition of these signals relies on electrodes. These systems must meet the design challenge of selecting an optimal set of electrodes that balances performance and usability constraints. The search for the optimal subset of electrodes from a larger set is a problem with combinatorial complexity. While existing research has primarily focused on search strategies that only explore limited combinations, our methodology proposes a computationally efficient way to explore all combinations. To avoid the computational burden associated with training the model for each combination, we leverage an innovative approach inspired by few-shot learning. Remarkably, this strategy covers all the wearable electrode combinations while significantly reducing training time compared to retraining the network on each possible combination. In the context of an epileptic seizure detection task, the proposed method achieves an AUC value of 0.917 with configurations using eight electrodes. This performance matches that of prior research but is achieved in significantly less time, transforming a process that would span months into a matter of hours on a single GPU device. Our work allows comprehensive exploration of electrode configurations in wearable biomedical device design, yielding insights that enhance performance and real-world feasibility.
(Less)
- author
- Amirshahi, Alireza
; Dan, Jonathan
; Miranda, José
; Aminifar, Amir
LU
and Atienza, David
- organization
- publishing date
- 2024
- type
- Chapter in Book/Report/Conference proceeding
- publication status
- published
- subject
- host publication
- Proceedings of the fifth Conference on Health, Inference, and Learning
- series title
- Proceedings of Machine Learning Research
- volume
- 248
- pages
- 13 pages
- publisher
- ML Research Press
- conference name
- 5th Annual Conference on Health, Inference, and Learning, CHIL 2024
- conference location
- New York, United States
- conference dates
- 2024-06-27 - 2024-06-28
- external identifiers
-
- scopus:85203840096
- ISSN
- 2640-3498
- language
- English
- LU publication?
- yes
- additional info
- Publisher Copyright: © 2024 A. Amirshahi, J. Dan, J. Miranda, A. Aminifar & D. Atienza.
- id
- 200e1565-a480-4ff4-8b93-cd135026f8ea
- alternative location
- https://proceedings.mlr.press/v248/amirshahi24a.html
- date added to LUP
- 2024-11-01 19:09:35
- date last changed
- 2025-04-04 15:21:21
@inproceedings{200e1565-a480-4ff4-8b93-cd135026f8ea,
abstract = {{<p>The rapid development of wearable biomedical systems now enables real-time monitoring of electroencephalography (EEG) signals. Acquisition of these signals relies on electrodes. These systems must meet the design challenge of selecting an optimal set of electrodes that balances performance and usability constraints. The search for the optimal subset of electrodes from a larger set is a problem with combinatorial complexity. While existing research has primarily focused on search strategies that only explore limited combinations, our methodology proposes a computationally efficient way to explore all combinations. To avoid the computational burden associated with training the model for each combination, we leverage an innovative approach inspired by few-shot learning. Remarkably, this strategy covers all the wearable electrode combinations while significantly reducing training time compared to retraining the network on each possible combination. In the context of an epileptic seizure detection task, the proposed method achieves an AUC value of 0.917 with configurations using eight electrodes. This performance matches that of prior research but is achieved in significantly less time, transforming a process that would span months into a matter of hours on a single GPU device. Our work allows comprehensive exploration of electrode configurations in wearable biomedical device design, yielding insights that enhance performance and real-world feasibility.</p>}},
author = {{Amirshahi, Alireza and Dan, Jonathan and Miranda, José and Aminifar, Amir and Atienza, David}},
booktitle = {{Proceedings of the fifth Conference on Health, Inference, and Learning}},
issn = {{2640-3498}},
language = {{eng}},
pages = {{397--409}},
publisher = {{ML Research Press}},
series = {{Proceedings of Machine Learning Research}},
title = {{FETCH : A Fast and Efficient Technique for Channel Selection in EEG Wearable Systems}},
url = {{https://proceedings.mlr.press/v248/amirshahi24a.html}},
volume = {{248}},
year = {{2024}},
}