Analyzing and Decoding Natural Reach-and-Grasp Actions Using Gel, Water and Dry EEG Systems

Schwarz, A. ; Escolano, C. ; Montesano, L. (Universidad de Zaragoza) ; Müller-Putz, G.R.

Resumen: Reaching and grasping is an essential part of everybody’s life, it allows meaningful interaction with the environment and is key to independent lifestyle. Recent electroencephalogram (EEG)-based studies have already shown that neural correlates of natural reach-and-grasp actions can be identified in the EEG. However, it is still in question whether these results obtained in a laboratory environment can make the transition to mobile applicable EEG systems for home use. In the current study, we investigated whether EEG-based correlates of natural reach-and-grasp actions can be successfully identified and decoded using mobile EEG systems, namely the water-based EEG-VersatileTM system and the dry-electrodes EEG-HeroTM headset. In addition, we also analyzed gel-based recordings obtained in a laboratory environment (g.USBamp/g.Ladybird, gold standard), which followed the same experimental parameters. For each recording system, 15 study participants performed 80 self-initiated reach-and-grasp actions toward a glass (palmar grasp) and a spoon (lateral grasp). Our results confirmed that EEG-based correlates of reach-and-grasp actions can be successfully identified using these mobile systems. In a single-trial multiclass-based decoding approach, which incorporated both movement conditions and rest, we could show that the low frequency time domain (LFTD) correlates were also decodable. Grand average peak accuracy calculated on unseen test data yielded for the water-based electrode system 62.3% (9.2% STD), whereas for the dry-electrodes headset reached 56.4% (8% STD). For the gel-based electrode system 61.3% (8.6% STD) could be achieved. To foster and promote further investigations in the field of EEG-based movement decoding, as well as to allow the interested community to make their own conclusions, we provide all datasets publicly available in the BNCI Horizon 2020 database (http://bnci-horizon-2020.eu/database/data-sets).

Idioma: Inglés

DOI: 10.3389/fnins.2020.00849

Año: 2020

Publicado en: Frontiers in neuroscience 14 (2020), 849 1-17
ISSN: 1662-4548

Factor impacto JCR: 4.677 (2020)

Categ. JCR: NEUROSCIENCES rank: 87 / 273 = 0.319 (2020) - Q2 - T1

Factor impacto SCIMAGO: 1.499 - Neuroscience (miscellaneous) (Q2)

Financiación: info:eu-repo/grantAgreement/EC/H2020/643955/EU/Restoration of upper limb function in individuals with high spinal cord injury by multimodal neuroprostheses for interaction in daily activities/MoreGrasp
Financiación: info:eu-repo/grantAgreement/EC/H2020/681231/EU/Non-invasive decoding of cortical patterns induced by goal directed movement intentions and artificial sensory feedback in humans/Feel your Reach

Tipo y forma: Artículo (Versión definitiva)

Área (Departamento): Área Lenguajes y Sistemas Inf. (Dpto. Informát.Ingenie.Sistms.)