Combining Statistical Analysis and Machine Learning for EEG Scalp Topograms Classification

Incorporating brain-computer interfaces (BCIs) into daily life requires reducing the reliance of decoding algorithms on the calibration or enabling calibration with the minimal burden on the user. A potential solution could be a pre-trained decoder demonstrating a reasonable accuracy on the naive op...

Descripción completa

Guardado en:

Detalles Bibliográficos
Autores principales:	Alexander Kuc, Sergey Korchagin, Vladimir A. Maksimenko, Natalia Shusharina, Alexander E. Hramov
Formato:	article
Lenguaje:	EN
Publicado:	Frontiers Media S.A. 2021
Materias:	EEG topograms convolutional neural network CNN ambiguous stimuli pre-trained decoder Neurosciences. Biological psychiatry. Neuropsychiatry RC321-571
Acceso en línea:	https://doaj.org/article/5743091b38de46a7bf8fadbfca948492
Etiquetas:	Agregar Etiqueta Sin Etiquetas, Sea el primero en etiquetar este registro!

id	oai:doaj.org-article:5743091b38de46a7bf8fadbfca948492
record_format	dspace
spelling	oai:doaj.org-article:5743091b38de46a7bf8fadbfca9484922021-11-16T05:34:44ZCombining Statistical Analysis and Machine Learning for EEG Scalp Topograms Classification1662-513710.3389/fnsys.2021.716897https://doaj.org/article/5743091b38de46a7bf8fadbfca9484922021-11-01T00:00:00Zhttps://www.frontiersin.org/articles/10.3389/fnsys.2021.716897/fullhttps://doaj.org/toc/1662-5137Incorporating brain-computer interfaces (BCIs) into daily life requires reducing the reliance of decoding algorithms on the calibration or enabling calibration with the minimal burden on the user. A potential solution could be a pre-trained decoder demonstrating a reasonable accuracy on the naive operators. Addressing this issue, we considered ambiguous stimuli classification tasks and trained an artificial neural network to classify brain responses to the stimuli of low and high ambiguity. We built a pre-trained classifier utilizing time-frequency features corresponding to the fundamental neurophysiological processes shared between subjects. To extract these features, we statistically contrasted electroencephalographic (EEG) spectral power between the classes in the representative group of subjects. As a result, the pre-trained classifier achieved 74% accuracy on the data of newly recruited subjects. Analysis of the literature suggested that a pre-trained classifier could help naive users to start using BCI bypassing training and further increased accuracy during the feedback session. Thus, our results contribute to using BCI during paralysis or limb amputation when there is no explicit user-generated kinematic output to properly train a decoder. In machine learning, our approach may facilitate the development of transfer learning (TL) methods for addressing the cross-subject problem. It allows extracting the interpretable feature subspace from the source data (the representative group of subjects) related to the target data (a naive user), preventing the negative transfer in the cross-subject tasks.Alexander KucSergey KorchaginVladimir A. MaksimenkoVladimir A. MaksimenkoVladimir A. MaksimenkoNatalia ShusharinaAlexander E. HramovAlexander E. HramovAlexander E. HramovFrontiers Media S.A.articleEEG topogramsconvolutional neural networkCNNambiguous stimulipre-trained decoderNeurosciences. Biological psychiatry. NeuropsychiatryRC321-571ENFrontiers in Systems Neuroscience, Vol 15 (2021)
institution	DOAJ
collection	DOAJ
language	EN
topic	EEG topograms convolutional neural network CNN ambiguous stimuli pre-trained decoder Neurosciences. Biological psychiatry. Neuropsychiatry RC321-571
spellingShingle	EEG topograms convolutional neural network CNN ambiguous stimuli pre-trained decoder Neurosciences. Biological psychiatry. Neuropsychiatry RC321-571 Alexander Kuc Sergey Korchagin Vladimir A. Maksimenko Vladimir A. Maksimenko Vladimir A. Maksimenko Natalia Shusharina Alexander E. Hramov Alexander E. Hramov Alexander E. Hramov Combining Statistical Analysis and Machine Learning for EEG Scalp Topograms Classification
description	Incorporating brain-computer interfaces (BCIs) into daily life requires reducing the reliance of decoding algorithms on the calibration or enabling calibration with the minimal burden on the user. A potential solution could be a pre-trained decoder demonstrating a reasonable accuracy on the naive operators. Addressing this issue, we considered ambiguous stimuli classification tasks and trained an artificial neural network to classify brain responses to the stimuli of low and high ambiguity. We built a pre-trained classifier utilizing time-frequency features corresponding to the fundamental neurophysiological processes shared between subjects. To extract these features, we statistically contrasted electroencephalographic (EEG) spectral power between the classes in the representative group of subjects. As a result, the pre-trained classifier achieved 74% accuracy on the data of newly recruited subjects. Analysis of the literature suggested that a pre-trained classifier could help naive users to start using BCI bypassing training and further increased accuracy during the feedback session. Thus, our results contribute to using BCI during paralysis or limb amputation when there is no explicit user-generated kinematic output to properly train a decoder. In machine learning, our approach may facilitate the development of transfer learning (TL) methods for addressing the cross-subject problem. It allows extracting the interpretable feature subspace from the source data (the representative group of subjects) related to the target data (a naive user), preventing the negative transfer in the cross-subject tasks.
format	article
author	Alexander Kuc Sergey Korchagin Vladimir A. Maksimenko Vladimir A. Maksimenko Vladimir A. Maksimenko Natalia Shusharina Alexander E. Hramov Alexander E. Hramov Alexander E. Hramov
author_facet	Alexander Kuc Sergey Korchagin Vladimir A. Maksimenko Vladimir A. Maksimenko Vladimir A. Maksimenko Natalia Shusharina Alexander E. Hramov Alexander E. Hramov Alexander E. Hramov
author_sort	Alexander Kuc
title	Combining Statistical Analysis and Machine Learning for EEG Scalp Topograms Classification
title_short	Combining Statistical Analysis and Machine Learning for EEG Scalp Topograms Classification
title_full	Combining Statistical Analysis and Machine Learning for EEG Scalp Topograms Classification
title_fullStr	Combining Statistical Analysis and Machine Learning for EEG Scalp Topograms Classification
title_full_unstemmed	Combining Statistical Analysis and Machine Learning for EEG Scalp Topograms Classification
title_sort	combining statistical analysis and machine learning for eeg scalp topograms classification
publisher	Frontiers Media S.A.
publishDate	2021
url	https://doaj.org/article/5743091b38de46a7bf8fadbfca948492
work_keys_str_mv	AT alexanderkuc combiningstatisticalanalysisandmachinelearningforeegscalptopogramsclassification AT sergeykorchagin combiningstatisticalanalysisandmachinelearningforeegscalptopogramsclassification AT vladimiramaksimenko combiningstatisticalanalysisandmachinelearningforeegscalptopogramsclassification AT vladimiramaksimenko combiningstatisticalanalysisandmachinelearningforeegscalptopogramsclassification AT vladimiramaksimenko combiningstatisticalanalysisandmachinelearningforeegscalptopogramsclassification AT nataliashusharina combiningstatisticalanalysisandmachinelearningforeegscalptopogramsclassification AT alexanderehramov combiningstatisticalanalysisandmachinelearningforeegscalptopogramsclassification AT alexanderehramov combiningstatisticalanalysisandmachinelearningforeegscalptopogramsclassification AT alexanderehramov combiningstatisticalanalysisandmachinelearningforeegscalptopogramsclassification
_version_	1718426666627235840

Combining Statistical Analysis and Machine Learning for EEG Scalp Topograms Classification

Ejemplares similares