Robust Motor Imagery Classification Using Sparse Representations and Grouping Structures

The classification of Motor Imagery (MI) tasks constitutes one of the most challenging problems in Brain Computer Interfaces (BCI) mostly due to the varying conditions of its operation. These conditions may vary with respect to the number of electrodes, the time and effort that can be invested by th...

Descripción completa

Guardado en:

Detalles Bibliográficos
Autores principales:	Vangelis P. Oikonomou, Spiros Nikolopoulos, Ioannis Kompatsiaris
Formato:	article
Lenguaje:	EN
Publicado:	IEEE 2020
Materias:	Motor imagery sparse representation classification group sparsity collaborative representation classification Electrical engineering. Electronics. Nuclear engineering TK1-9971
Acceso en línea:	https://doaj.org/article/60fbede0a5354170938cd0a139579945
Etiquetas:	Agregar Etiqueta Sin Etiquetas, Sea el primero en etiquetar este registro!

id	oai:doaj.org-article:60fbede0a5354170938cd0a139579945
record_format	dspace
spelling	oai:doaj.org-article:60fbede0a5354170938cd0a1395799452021-11-13T00:00:44ZRobust Motor Imagery Classification Using Sparse Representations and Grouping Structures2169-353610.1109/ACCESS.2020.2997116https://doaj.org/article/60fbede0a5354170938cd0a1395799452020-01-01T00:00:00Zhttps://ieeexplore.ieee.org/document/9099226/https://doaj.org/toc/2169-3536The classification of Motor Imagery (MI) tasks constitutes one of the most challenging problems in Brain Computer Interfaces (BCI) mostly due to the varying conditions of its operation. These conditions may vary with respect to the number of electrodes, the time and effort that can be invested by the user for training/calibrating the system prior to its use, as well as the duration or even the type of the imaginary task that is most convenient for the user. Hence, it is desirable to design classification schemes that are not only accurate in terms of the classification output but also robust to changes in the operational conditions. Towards this goal, we propose a new sparse representation classification scheme that extends current sparse representation schemes by exploiting the group sparsity of relevant features. Based on this scheme each test signal is represented as a linear combination of train trials that are further constrained to belong in the same MI class. Our expectation is that this constrained linear combination exploiting the grouping structure of the training data will lead to representations that are more robust to varying operational conditions. Moreover, in order to avoid overfitting and provide a model with good generalization abilities we adopt the bayesian framework and, in particular, the Variational Bayesian Framework since we use a specific approximate posterior to exploit the grouping structure of the data. We have evaluated the proposed algorithm on two MI datasets using electroencephalograms (EEG) that allowed us to simulate different operational conditions like the number of available channels, the number of training trials, the type of MI tasks, as well as the duration of each trial. Results have shown that the proposed method presents state-of-the-art performance against well known classification methods in MI BCI literature.Vangelis P. OikonomouSpiros NikolopoulosIoannis KompatsiarisIEEEarticleMotor imagerysparse representation classificationgroup sparsitycollaborative representation classificationElectrical engineering. Electronics. Nuclear engineeringTK1-9971ENIEEE Access, Vol 8, Pp 98572-98583 (2020)
institution	DOAJ
collection	DOAJ
language	EN
topic	Motor imagery sparse representation classification group sparsity collaborative representation classification Electrical engineering. Electronics. Nuclear engineering TK1-9971
spellingShingle	Motor imagery sparse representation classification group sparsity collaborative representation classification Electrical engineering. Electronics. Nuclear engineering TK1-9971 Vangelis P. Oikonomou Spiros Nikolopoulos Ioannis Kompatsiaris Robust Motor Imagery Classification Using Sparse Representations and Grouping Structures
description	The classification of Motor Imagery (MI) tasks constitutes one of the most challenging problems in Brain Computer Interfaces (BCI) mostly due to the varying conditions of its operation. These conditions may vary with respect to the number of electrodes, the time and effort that can be invested by the user for training/calibrating the system prior to its use, as well as the duration or even the type of the imaginary task that is most convenient for the user. Hence, it is desirable to design classification schemes that are not only accurate in terms of the classification output but also robust to changes in the operational conditions. Towards this goal, we propose a new sparse representation classification scheme that extends current sparse representation schemes by exploiting the group sparsity of relevant features. Based on this scheme each test signal is represented as a linear combination of train trials that are further constrained to belong in the same MI class. Our expectation is that this constrained linear combination exploiting the grouping structure of the training data will lead to representations that are more robust to varying operational conditions. Moreover, in order to avoid overfitting and provide a model with good generalization abilities we adopt the bayesian framework and, in particular, the Variational Bayesian Framework since we use a specific approximate posterior to exploit the grouping structure of the data. We have evaluated the proposed algorithm on two MI datasets using electroencephalograms (EEG) that allowed us to simulate different operational conditions like the number of available channels, the number of training trials, the type of MI tasks, as well as the duration of each trial. Results have shown that the proposed method presents state-of-the-art performance against well known classification methods in MI BCI literature.
format	article
author	Vangelis P. Oikonomou Spiros Nikolopoulos Ioannis Kompatsiaris
author_facet	Vangelis P. Oikonomou Spiros Nikolopoulos Ioannis Kompatsiaris
author_sort	Vangelis P. Oikonomou
title	Robust Motor Imagery Classification Using Sparse Representations and Grouping Structures
title_short	Robust Motor Imagery Classification Using Sparse Representations and Grouping Structures
title_full	Robust Motor Imagery Classification Using Sparse Representations and Grouping Structures
title_fullStr	Robust Motor Imagery Classification Using Sparse Representations and Grouping Structures
title_full_unstemmed	Robust Motor Imagery Classification Using Sparse Representations and Grouping Structures
title_sort	robust motor imagery classification using sparse representations and grouping structures
publisher	IEEE
publishDate	2020
url	https://doaj.org/article/60fbede0a5354170938cd0a139579945
work_keys_str_mv	AT vangelispoikonomou robustmotorimageryclassificationusingsparserepresentationsandgroupingstructures AT spirosnikolopoulos robustmotorimageryclassificationusingsparserepresentationsandgroupingstructures AT ioanniskompatsiaris robustmotorimageryclassificationusingsparserepresentationsandgroupingstructures
_version_	1718430321084465152

Robust Motor Imagery Classification Using Sparse Representations and Grouping Structures

Ejemplares similares