EEG-Based Classification of the Driver Alertness State

GMLVQ (Generalized Matrix Relevance Learning Vector Quantization) is a method of machine learning with an adaptive metric. While training, the prototype vectors as well as the weight matrix of the metric are adapted simultaneously. The method is presented in more detail and compared with other machi...

Descripción completa

Guardado en:

Detalles Bibliográficos
Autores principales:	Golz Martin, Thomas Sebastian, Schenka Adolf
Formato:	article
Lenguaje:	EN
Publicado:	De Gruyter 2020
Materias:	electroencephalogram eeg driving simulation drowsiness classification machine learning generalized matrix relevance learning vector quantization support-vector machine gradient boosting machine Medicine R
Acceso en línea:	https://doaj.org/article/2fe0652486ea4b6abe10ba89fbee5bf7
Etiquetas:	Agregar Etiqueta Sin Etiquetas, Sea el primero en etiquetar este registro!

id	oai:doaj.org-article:2fe0652486ea4b6abe10ba89fbee5bf7
record_format	dspace
spelling	oai:doaj.org-article:2fe0652486ea4b6abe10ba89fbee5bf72021-12-05T14:10:42ZEEG-Based Classification of the Driver Alertness State2364-550410.1515/cdbme-2020-3091https://doaj.org/article/2fe0652486ea4b6abe10ba89fbee5bf72020-09-01T00:00:00Zhttps://doi.org/10.1515/cdbme-2020-3091https://doaj.org/toc/2364-5504GMLVQ (Generalized Matrix Relevance Learning Vector Quantization) is a method of machine learning with an adaptive metric. While training, the prototype vectors as well as the weight matrix of the metric are adapted simultaneously. The method is presented in more detail and compared with other machine learning methods employing a fixed metric. It was investigated how accurately the methods can assign the 6-channel EEG of 25 young drivers, who drove overnight in the simulation lab, to the two classes of mild and severe drowsiness. Results of cross-validation show that GMLVQ is at 81.7 ± 1.3 % mean classification accuracy. It is not as accurate as support-vector machines (SVM) and gradient boosting machines (GBM) and cannot exploit the potential of learning adaptive metrics in the case of EEG data. However, information is provided on the relevance of each signal feature from the weighting matrix.Golz MartinThomas SebastianSchenka AdolfDe Gruyterarticleelectroencephalogrameegdriving simulationdrowsinessclassificationmachine learninggeneralized matrix relevance learning vector quantizationsupport-vector machinegradient boosting machineMedicineRENCurrent Directions in Biomedical Engineering, Vol 6, Iss 3, Pp 353-356 (2020)
institution	DOAJ
collection	DOAJ
language	EN
topic	electroencephalogram eeg driving simulation drowsiness classification machine learning generalized matrix relevance learning vector quantization support-vector machine gradient boosting machine Medicine R
spellingShingle	electroencephalogram eeg driving simulation drowsiness classification machine learning generalized matrix relevance learning vector quantization support-vector machine gradient boosting machine Medicine R Golz Martin Thomas Sebastian Schenka Adolf EEG-Based Classification of the Driver Alertness State
description	GMLVQ (Generalized Matrix Relevance Learning Vector Quantization) is a method of machine learning with an adaptive metric. While training, the prototype vectors as well as the weight matrix of the metric are adapted simultaneously. The method is presented in more detail and compared with other machine learning methods employing a fixed metric. It was investigated how accurately the methods can assign the 6-channel EEG of 25 young drivers, who drove overnight in the simulation lab, to the two classes of mild and severe drowsiness. Results of cross-validation show that GMLVQ is at 81.7 ± 1.3 % mean classification accuracy. It is not as accurate as support-vector machines (SVM) and gradient boosting machines (GBM) and cannot exploit the potential of learning adaptive metrics in the case of EEG data. However, information is provided on the relevance of each signal feature from the weighting matrix.
format	article
author	Golz Martin Thomas Sebastian Schenka Adolf
author_facet	Golz Martin Thomas Sebastian Schenka Adolf
author_sort	Golz Martin
title	EEG-Based Classification of the Driver Alertness State
title_short	EEG-Based Classification of the Driver Alertness State
title_full	EEG-Based Classification of the Driver Alertness State
title_fullStr	EEG-Based Classification of the Driver Alertness State
title_full_unstemmed	EEG-Based Classification of the Driver Alertness State
title_sort	eeg-based classification of the driver alertness state
publisher	De Gruyter
publishDate	2020
url	https://doaj.org/article/2fe0652486ea4b6abe10ba89fbee5bf7
work_keys_str_mv	AT golzmartin eegbasedclassificationofthedriveralertnessstate AT thomassebastian eegbasedclassificationofthedriveralertnessstate AT schenkaadolf eegbasedclassificationofthedriveralertnessstate
_version_	1718371831538253824

EEG-Based Classification of the Driver Alertness State

Ejemplares similares