Relevance-based channel selection in motor imagery brain-computer interface

Objective.Channel selection in the electroencephalogram (EEG)-based brain-computer interface (BCI) has been extensively studied for over two decades, with the goal being to select optimal subject-specific channels that can enhance the overall decoding efficacy of the BCI. With the emergence of deep...

Full description

Saved in:
Bibliographic Details
Main Authors: Nagarajan, Aarthy, Robinson, Neethu, Guan, Cuntai
Other Authors: School of Computer Science and Engineering
Format: Article
Language:English
Published: 2023
Subjects:
Online Access:https://hdl.handle.net/10356/166280
Tags: Add Tag
No Tags, Be the first to tag this record!
Institution: Nanyang Technological University
Language: English
id sg-ntu-dr.10356-166280
record_format dspace
spelling sg-ntu-dr.10356-1662802023-04-21T15:35:50Z Relevance-based channel selection in motor imagery brain-computer interface Nagarajan, Aarthy Robinson, Neethu Guan, Cuntai School of Computer Science and Engineering Engineering::Computer science and engineering Channel Selection Deep Learning Objective.Channel selection in the electroencephalogram (EEG)-based brain-computer interface (BCI) has been extensively studied for over two decades, with the goal being to select optimal subject-specific channels that can enhance the overall decoding efficacy of the BCI. With the emergence of deep learning (DL)-based BCI models, there arises a need for fresh perspectives and novel techniques to conduct channel selection. In this regard, subject-independent channel selection is relevant, since DL models trained using cross-subject data offer superior performance, and the impact of inherent inter-subject variability of EEG characteristics on subject-independent DL training is not yet fully understood.Approach.Here, we propose a novel methodology for implementing subject-independent channel selection in DL-based motor imagery (MI)-BCI, using layer-wise relevance propagation (LRP) and neural network pruning. Experiments were conducted using Deep ConvNet and 62-channel MI data from the Korea University EEG dataset.Main Results.Using our proposed methodology, we achieved a 61% reduction in the number of channels without any significant drop (p = 0.09) in subject-independent classification accuracy, due to the selection of highly relevant channels by LRP. LRP relevance-based channel selections provide significantly better accuracies compared to conventional weight-based selections while using less than 40% of the total number of channels, with differences in accuracies ranging from 5.96% to 1.72%. The performance of the adapted sparse-LRP model using only 16% of the total number of channels is similar to that of the adapted baseline model (p = 0.13). Furthermore, the accuracy of the adapted sparse-LRP model using only 35% of the total number of channels exceeded that of the adapted baseline model by 0.53% (p = 0.81). Analyses of channels chosen by LRP confirm the neurophysiological plausibility of selection, and emphasize the influence of motor, parietal, and occipital channels in MI-EEG classification.Significance.The proposed method addresses a traditional issue in EEG-BCI decoding, while being relevant and applicable to the latest developments in the field of BCI. We believe that our work brings forth an interesting and important application of model interpretability as a problem-solving technique. Submitted/Accepted version This work was partially supported by the RIE2020 AME Programmatic Fund, Singapore (No. A20G8b0102). 2023-04-19T08:07:00Z 2023-04-19T08:07:00Z 2023 Journal Article Nagarajan, A., Robinson, N. & Guan, C. (2023). Relevance-based channel selection in motor imagery brain-computer interface. Journal of Neural Engineering, 20(1), 016024-. https://dx.doi.org/10.1088/1741-2552/acae07 1741-2560 https://hdl.handle.net/10356/166280 10.1088/1741-2552/acae07 36548997 2-s2.0-85147046335 1 20 016024 en A20G8b0102 Journal of Neural Engineering © 2023 IOP Publishing Ltd. All rights reserved. This is an author-created, un-copyedited version of an article accepted for publication in Journal of Neural Engineering. IOP Publishing Ltd is not responsible for any errors or omissions in this version of the manuscript or any version derived from it. The definitive publisher authenticated version is available online at https://doi.org/10.1088/1741-2552/acae07. application/pdf
institution Nanyang Technological University
building NTU Library
continent Asia
country Singapore
Singapore
content_provider NTU Library
collection DR-NTU
language English
topic Engineering::Computer science and engineering
Channel Selection
Deep Learning
spellingShingle Engineering::Computer science and engineering
Channel Selection
Deep Learning
Nagarajan, Aarthy
Robinson, Neethu
Guan, Cuntai
Relevance-based channel selection in motor imagery brain-computer interface
description Objective.Channel selection in the electroencephalogram (EEG)-based brain-computer interface (BCI) has been extensively studied for over two decades, with the goal being to select optimal subject-specific channels that can enhance the overall decoding efficacy of the BCI. With the emergence of deep learning (DL)-based BCI models, there arises a need for fresh perspectives and novel techniques to conduct channel selection. In this regard, subject-independent channel selection is relevant, since DL models trained using cross-subject data offer superior performance, and the impact of inherent inter-subject variability of EEG characteristics on subject-independent DL training is not yet fully understood.Approach.Here, we propose a novel methodology for implementing subject-independent channel selection in DL-based motor imagery (MI)-BCI, using layer-wise relevance propagation (LRP) and neural network pruning. Experiments were conducted using Deep ConvNet and 62-channel MI data from the Korea University EEG dataset.Main Results.Using our proposed methodology, we achieved a 61% reduction in the number of channels without any significant drop (p = 0.09) in subject-independent classification accuracy, due to the selection of highly relevant channels by LRP. LRP relevance-based channel selections provide significantly better accuracies compared to conventional weight-based selections while using less than 40% of the total number of channels, with differences in accuracies ranging from 5.96% to 1.72%. The performance of the adapted sparse-LRP model using only 16% of the total number of channels is similar to that of the adapted baseline model (p = 0.13). Furthermore, the accuracy of the adapted sparse-LRP model using only 35% of the total number of channels exceeded that of the adapted baseline model by 0.53% (p = 0.81). Analyses of channels chosen by LRP confirm the neurophysiological plausibility of selection, and emphasize the influence of motor, parietal, and occipital channels in MI-EEG classification.Significance.The proposed method addresses a traditional issue in EEG-BCI decoding, while being relevant and applicable to the latest developments in the field of BCI. We believe that our work brings forth an interesting and important application of model interpretability as a problem-solving technique.
author2 School of Computer Science and Engineering
author_facet School of Computer Science and Engineering
Nagarajan, Aarthy
Robinson, Neethu
Guan, Cuntai
format Article
author Nagarajan, Aarthy
Robinson, Neethu
Guan, Cuntai
author_sort Nagarajan, Aarthy
title Relevance-based channel selection in motor imagery brain-computer interface
title_short Relevance-based channel selection in motor imagery brain-computer interface
title_full Relevance-based channel selection in motor imagery brain-computer interface
title_fullStr Relevance-based channel selection in motor imagery brain-computer interface
title_full_unstemmed Relevance-based channel selection in motor imagery brain-computer interface
title_sort relevance-based channel selection in motor imagery brain-computer interface
publishDate 2023
url https://hdl.handle.net/10356/166280
_version_ 1764208059561803776