Motor Imagery Classification for Brain Computer Interface Using Deep Metric Learning
Deep metric learning (DML) has achieved state-of-the-art results in several deep learning applications. However, this type of deep learning models has not been tested on the classification of electrical brain waves (EEG) for brain computer interface (BCI) applications. For the first time, we propose...
Published in: | IEEE Access |
---|---|
Main Authors: | , , |
Format: | Article in Journal/Newspaper |
Language: | English |
Published: |
IEEE
2020
|
Subjects: | |
Online Access: | https://doi.org/10.1109/ACCESS.2020.3002459 https://doaj.org/article/cebba99279fc423ba19a4e3f61b7fa0e |
id |
ftdoajarticles:oai:doaj.org/article:cebba99279fc423ba19a4e3f61b7fa0e |
---|---|
record_format |
openpolar |
spelling |
ftdoajarticles:oai:doaj.org/article:cebba99279fc423ba19a4e3f61b7fa0e 2023-05-15T16:01:21+02:00 Motor Imagery Classification for Brain Computer Interface Using Deep Metric Learning Haider Alwasiti Mohd Zuki Yusoff Kamran Raza 2020-01-01T00:00:00Z https://doi.org/10.1109/ACCESS.2020.3002459 https://doaj.org/article/cebba99279fc423ba19a4e3f61b7fa0e EN eng IEEE https://ieeexplore.ieee.org/document/9116935/ https://doaj.org/toc/2169-3536 2169-3536 doi:10.1109/ACCESS.2020.3002459 https://doaj.org/article/cebba99279fc423ba19a4e3f61b7fa0e IEEE Access, Vol 8, Pp 109949-109963 (2020) BCI metric learning EEG Stockwell transform Electrical engineering. Electronics. Nuclear engineering TK1-9971 article 2020 ftdoajarticles https://doi.org/10.1109/ACCESS.2020.3002459 2022-12-31T10:36:01Z Deep metric learning (DML) has achieved state-of-the-art results in several deep learning applications. However, this type of deep learning models has not been tested on the classification of electrical brain waves (EEG) for brain computer interface (BCI) applications. For the first time, we propose a triplet network to classify motor imagery (MI) EEG signals. Stockwell Transform has been used for converting the EEG signals in the time domain into the frequency domain, which resulted in improved DML classification accuracy in comparison to DML with Short Term Fourier Transform (0.647 vs. 0.431). DML model was trained with a topogram of concatenated 64 EEG channel spectrograms. The training batch was comprised of triplet pairs of the anchor, positive, and negative labeled epochs. The triplet network was able to train an embedding feature space that minimized the Euclidean distance between the embeddings of spectrograms of the same class and increased the distance between the embeddings of different labeled images. The proposed method has been tested on an EEG dataset of 109 untrained subjects. We showed that the DML classifier is able to converge with an extremely small number of training samples (~ 120 EEG trials) for only one subject per model, mitigating the well-known issue of the large inter-individual variability of human MI-BCI EEG which degrades the classification performance. The proposed preprocessing pipeline and the Triplet Network provide a promising method to classify MI-BCI EEG signals with much less training samples than the previous methods. Article in Journal/Newspaper DML Directory of Open Access Journals: DOAJ Articles IEEE Access 8 109949 109963 |
institution |
Open Polar |
collection |
Directory of Open Access Journals: DOAJ Articles |
op_collection_id |
ftdoajarticles |
language |
English |
topic |
BCI metric learning EEG Stockwell transform Electrical engineering. Electronics. Nuclear engineering TK1-9971 |
spellingShingle |
BCI metric learning EEG Stockwell transform Electrical engineering. Electronics. Nuclear engineering TK1-9971 Haider Alwasiti Mohd Zuki Yusoff Kamran Raza Motor Imagery Classification for Brain Computer Interface Using Deep Metric Learning |
topic_facet |
BCI metric learning EEG Stockwell transform Electrical engineering. Electronics. Nuclear engineering TK1-9971 |
description |
Deep metric learning (DML) has achieved state-of-the-art results in several deep learning applications. However, this type of deep learning models has not been tested on the classification of electrical brain waves (EEG) for brain computer interface (BCI) applications. For the first time, we propose a triplet network to classify motor imagery (MI) EEG signals. Stockwell Transform has been used for converting the EEG signals in the time domain into the frequency domain, which resulted in improved DML classification accuracy in comparison to DML with Short Term Fourier Transform (0.647 vs. 0.431). DML model was trained with a topogram of concatenated 64 EEG channel spectrograms. The training batch was comprised of triplet pairs of the anchor, positive, and negative labeled epochs. The triplet network was able to train an embedding feature space that minimized the Euclidean distance between the embeddings of spectrograms of the same class and increased the distance between the embeddings of different labeled images. The proposed method has been tested on an EEG dataset of 109 untrained subjects. We showed that the DML classifier is able to converge with an extremely small number of training samples (~ 120 EEG trials) for only one subject per model, mitigating the well-known issue of the large inter-individual variability of human MI-BCI EEG which degrades the classification performance. The proposed preprocessing pipeline and the Triplet Network provide a promising method to classify MI-BCI EEG signals with much less training samples than the previous methods. |
format |
Article in Journal/Newspaper |
author |
Haider Alwasiti Mohd Zuki Yusoff Kamran Raza |
author_facet |
Haider Alwasiti Mohd Zuki Yusoff Kamran Raza |
author_sort |
Haider Alwasiti |
title |
Motor Imagery Classification for Brain Computer Interface Using Deep Metric Learning |
title_short |
Motor Imagery Classification for Brain Computer Interface Using Deep Metric Learning |
title_full |
Motor Imagery Classification for Brain Computer Interface Using Deep Metric Learning |
title_fullStr |
Motor Imagery Classification for Brain Computer Interface Using Deep Metric Learning |
title_full_unstemmed |
Motor Imagery Classification for Brain Computer Interface Using Deep Metric Learning |
title_sort |
motor imagery classification for brain computer interface using deep metric learning |
publisher |
IEEE |
publishDate |
2020 |
url |
https://doi.org/10.1109/ACCESS.2020.3002459 https://doaj.org/article/cebba99279fc423ba19a4e3f61b7fa0e |
genre |
DML |
genre_facet |
DML |
op_source |
IEEE Access, Vol 8, Pp 109949-109963 (2020) |
op_relation |
https://ieeexplore.ieee.org/document/9116935/ https://doaj.org/toc/2169-3536 2169-3536 doi:10.1109/ACCESS.2020.3002459 https://doaj.org/article/cebba99279fc423ba19a4e3f61b7fa0e |
op_doi |
https://doi.org/10.1109/ACCESS.2020.3002459 |
container_title |
IEEE Access |
container_volume |
8 |
container_start_page |
109949 |
op_container_end_page |
109963 |
_version_ |
1766397247763775488 |