Cargando…

Spiking Neural Network for Augmenting Electroencephalographic Data for Brain Computer Interfaces

With the advent of advanced machine learning methods, the performance of brain–computer interfaces (BCIs) has improved unprecedentedly. However, electroencephalography (EEG), a commonly used brain imaging method for BCI, is characterized by a tedious experimental setup, frequent data loss due to art...

Descripción completa

Detalles Bibliográficos
Autores principales: Singanamalla, Sai Kalyan Ranga, Lin, Chin-Teng
Formato: Online Artículo Texto
Lenguaje:English
Publicado: Frontiers Media S.A. 2021
Materias:
Acceso en línea:https://www.ncbi.nlm.nih.gov/pmc/articles/PMC8047134/
https://www.ncbi.nlm.nih.gov/pubmed/33867928
http://dx.doi.org/10.3389/fnins.2021.651762
_version_ 1783678983931428864
author Singanamalla, Sai Kalyan Ranga
Lin, Chin-Teng
author_facet Singanamalla, Sai Kalyan Ranga
Lin, Chin-Teng
author_sort Singanamalla, Sai Kalyan Ranga
collection PubMed
description With the advent of advanced machine learning methods, the performance of brain–computer interfaces (BCIs) has improved unprecedentedly. However, electroencephalography (EEG), a commonly used brain imaging method for BCI, is characterized by a tedious experimental setup, frequent data loss due to artifacts, and is time consuming for bulk trial recordings to take advantage of the capabilities of deep learning classifiers. Some studies have tried to address this issue by generating artificial EEG signals. However, a few of these methods are limited in retaining the prominent features or biomarker of the signal. And, other deep learning-based generative methods require a huge number of samples for training, and a majority of these models can handle data augmentation of one category or class of data at any training session. Therefore, there exists a necessity for a generative model that can generate synthetic EEG samples with as few available trials as possible and generate multi-class while retaining the biomarker of the signal. Since EEG signal represents an accumulation of action potentials from neuronal populations beneath the scalp surface and as spiking neural network (SNN), a biologically closer artificial neural network, communicates via spiking behavior, we propose an SNN-based approach using surrogate-gradient descent learning to reconstruct and generate multi-class artificial EEG signals from just a few original samples. The network was employed for augmenting motor imagery (MI) and steady-state visually evoked potential (SSVEP) data. These artificial data are further validated through classification and correlation metrics to assess its resemblance with original data and in-turn enhanced the MI classification performance.
format Online
Article
Text
id pubmed-8047134
institution National Center for Biotechnology Information
language English
publishDate 2021
publisher Frontiers Media S.A.
record_format MEDLINE/PubMed
spelling pubmed-80471342021-04-16 Spiking Neural Network for Augmenting Electroencephalographic Data for Brain Computer Interfaces Singanamalla, Sai Kalyan Ranga Lin, Chin-Teng Front Neurosci Neuroscience With the advent of advanced machine learning methods, the performance of brain–computer interfaces (BCIs) has improved unprecedentedly. However, electroencephalography (EEG), a commonly used brain imaging method for BCI, is characterized by a tedious experimental setup, frequent data loss due to artifacts, and is time consuming for bulk trial recordings to take advantage of the capabilities of deep learning classifiers. Some studies have tried to address this issue by generating artificial EEG signals. However, a few of these methods are limited in retaining the prominent features or biomarker of the signal. And, other deep learning-based generative methods require a huge number of samples for training, and a majority of these models can handle data augmentation of one category or class of data at any training session. Therefore, there exists a necessity for a generative model that can generate synthetic EEG samples with as few available trials as possible and generate multi-class while retaining the biomarker of the signal. Since EEG signal represents an accumulation of action potentials from neuronal populations beneath the scalp surface and as spiking neural network (SNN), a biologically closer artificial neural network, communicates via spiking behavior, we propose an SNN-based approach using surrogate-gradient descent learning to reconstruct and generate multi-class artificial EEG signals from just a few original samples. The network was employed for augmenting motor imagery (MI) and steady-state visually evoked potential (SSVEP) data. These artificial data are further validated through classification and correlation metrics to assess its resemblance with original data and in-turn enhanced the MI classification performance. Frontiers Media S.A. 2021-04-01 /pmc/articles/PMC8047134/ /pubmed/33867928 http://dx.doi.org/10.3389/fnins.2021.651762 Text en Copyright © 2021 Singanamalla and Lin. https://creativecommons.org/licenses/by/4.0/This is an open-access article distributed under the terms of the Creative Commons Attribution License (CC BY). The use, distribution or reproduction in other forums is permitted, provided the original author(s) and the copyright owner(s) are credited and that the original publication in this journal is cited, in accordance with accepted academic practice. No use, distribution or reproduction is permitted which does not comply with these terms.
spellingShingle Neuroscience
Singanamalla, Sai Kalyan Ranga
Lin, Chin-Teng
Spiking Neural Network for Augmenting Electroencephalographic Data for Brain Computer Interfaces
title Spiking Neural Network for Augmenting Electroencephalographic Data for Brain Computer Interfaces
title_full Spiking Neural Network for Augmenting Electroencephalographic Data for Brain Computer Interfaces
title_fullStr Spiking Neural Network for Augmenting Electroencephalographic Data for Brain Computer Interfaces
title_full_unstemmed Spiking Neural Network for Augmenting Electroencephalographic Data for Brain Computer Interfaces
title_short Spiking Neural Network for Augmenting Electroencephalographic Data for Brain Computer Interfaces
title_sort spiking neural network for augmenting electroencephalographic data for brain computer interfaces
topic Neuroscience
url https://www.ncbi.nlm.nih.gov/pmc/articles/PMC8047134/
https://www.ncbi.nlm.nih.gov/pubmed/33867928
http://dx.doi.org/10.3389/fnins.2021.651762
work_keys_str_mv AT singanamallasaikalyanranga spikingneuralnetworkforaugmentingelectroencephalographicdataforbraincomputerinterfaces
AT linchinteng spikingneuralnetworkforaugmentingelectroencephalographicdataforbraincomputerinterfaces