Noise Robustness Low-Rank Learning Algorithm for Electroencephalogram Signal Classification

Electroencephalogram (EEG) is often used in clinical epilepsy treatment to monitor electrical signal changes in the brain of patients with epilepsy. With the development of signal processing and artificial intelligence technology, artificial intelligence classification method plays an important role...

Descripción completa

Guardado en:

Detalles Bibliográficos
Autores principales:	Ming Gao, Runmin Liu, Jie Mao
Formato:	article
Lenguaje:	EN
Publicado:	Frontiers Media S.A. 2021
Materias:	electroencephalogram epilepsy noise robustness low-rank learning pinball loss function Neurosciences. Biological psychiatry. Neuropsychiatry RC321-571
Acceso en línea:	https://doaj.org/article/668c5978e05a4c63a6db624176ed2e57
Etiquetas:	Agregar Etiqueta Sin Etiquetas, Sea el primero en etiquetar este registro!

id	oai:doaj.org-article:668c5978e05a4c63a6db624176ed2e57
record_format	dspace
spelling	oai:doaj.org-article:668c5978e05a4c63a6db624176ed2e572021-11-30T19:00:45ZNoise Robustness Low-Rank Learning Algorithm for Electroencephalogram Signal Classification1662-453X10.3389/fnins.2021.797378https://doaj.org/article/668c5978e05a4c63a6db624176ed2e572021-11-01T00:00:00Zhttps://www.frontiersin.org/articles/10.3389/fnins.2021.797378/fullhttps://doaj.org/toc/1662-453XElectroencephalogram (EEG) is often used in clinical epilepsy treatment to monitor electrical signal changes in the brain of patients with epilepsy. With the development of signal processing and artificial intelligence technology, artificial intelligence classification method plays an important role in the automatic recognition of epilepsy EEG signals. However, traditional classifiers are easily affected by impurities and noise in epileptic EEG signals. To solve this problem, this paper develops a noise robustness low-rank learning (NRLRL) algorithm for EEG signal classification. NRLRL establishes a low-rank subspace to connect the original data space and label space. Making full use of supervision information, it considers the local information preservation of samples to ensure the low-rank representation of within-class compactness and between-classes dispersion. The asymmetric least squares support vector machine (aLS-SVM) is embedded into the objective function of NRLRL. The aLS-SVM finds the maximum quantile distance between the two classes of samples based on the pinball loss function, which further improves the noise robustness of the model. Several classification experiments with different noise intensity are designed on the Bonn data set, and the experiment results verify the effectiveness of the NRLRL algorithm.Ming GaoRunmin LiuJie MaoFrontiers Media S.A.articleelectroencephalogramepilepsynoise robustnesslow-rank learningpinball loss functionNeurosciences. Biological psychiatry. NeuropsychiatryRC321-571ENFrontiers in Neuroscience, Vol 15 (2021)
institution	DOAJ
collection	DOAJ
language	EN
topic	electroencephalogram epilepsy noise robustness low-rank learning pinball loss function Neurosciences. Biological psychiatry. Neuropsychiatry RC321-571
spellingShingle	electroencephalogram epilepsy noise robustness low-rank learning pinball loss function Neurosciences. Biological psychiatry. Neuropsychiatry RC321-571 Ming Gao Runmin Liu Jie Mao Noise Robustness Low-Rank Learning Algorithm for Electroencephalogram Signal Classification
description	Electroencephalogram (EEG) is often used in clinical epilepsy treatment to monitor electrical signal changes in the brain of patients with epilepsy. With the development of signal processing and artificial intelligence technology, artificial intelligence classification method plays an important role in the automatic recognition of epilepsy EEG signals. However, traditional classifiers are easily affected by impurities and noise in epileptic EEG signals. To solve this problem, this paper develops a noise robustness low-rank learning (NRLRL) algorithm for EEG signal classification. NRLRL establishes a low-rank subspace to connect the original data space and label space. Making full use of supervision information, it considers the local information preservation of samples to ensure the low-rank representation of within-class compactness and between-classes dispersion. The asymmetric least squares support vector machine (aLS-SVM) is embedded into the objective function of NRLRL. The aLS-SVM finds the maximum quantile distance between the two classes of samples based on the pinball loss function, which further improves the noise robustness of the model. Several classification experiments with different noise intensity are designed on the Bonn data set, and the experiment results verify the effectiveness of the NRLRL algorithm.
format	article
author	Ming Gao Runmin Liu Jie Mao
author_facet	Ming Gao Runmin Liu Jie Mao
author_sort	Ming Gao
title	Noise Robustness Low-Rank Learning Algorithm for Electroencephalogram Signal Classification
title_short	Noise Robustness Low-Rank Learning Algorithm for Electroencephalogram Signal Classification
title_full	Noise Robustness Low-Rank Learning Algorithm for Electroencephalogram Signal Classification
title_fullStr	Noise Robustness Low-Rank Learning Algorithm for Electroencephalogram Signal Classification
title_full_unstemmed	Noise Robustness Low-Rank Learning Algorithm for Electroencephalogram Signal Classification
title_sort	noise robustness low-rank learning algorithm for electroencephalogram signal classification
publisher	Frontiers Media S.A.
publishDate	2021
url	https://doaj.org/article/668c5978e05a4c63a6db624176ed2e57
work_keys_str_mv	AT minggao noiserobustnesslowranklearningalgorithmforelectroencephalogramsignalclassification AT runminliu noiserobustnesslowranklearningalgorithmforelectroencephalogramsignalclassification AT jiemao noiserobustnesslowranklearningalgorithmforelectroencephalogramsignalclassification
_version_	1718406328208064512

Noise Robustness Low-Rank Learning Algorithm for Electroencephalogram Signal Classification

Ejemplares similares