Adaptive neural network classifier for decoding MEG signals

Tutkimustuotos: Lehtiartikkelivertaisarvioitu

Standard

Adaptive neural network classifier for decoding MEG signals. / Zubarev, Ivan; Zetter, Rasmus; Halme, Hanna Leena; Parkkonen, Lauri.

julkaisussa: NeuroImage, Vuosikerta 197, 15.08.2019, s. 425-434.

Tutkimustuotos: Lehtiartikkelivertaisarvioitu

Harvard

APA

Vancouver

Author

Bibtex - Lataa

@article{c8b2785380b64b02a25e59815448ee7d,
title = "Adaptive neural network classifier for decoding MEG signals",
abstract = "We introduce two Convolutional Neural Network (CNN )classifiers optimized for inferring brain states from magnetoencephalographic (MEG) measurements. Network design follows a generative model of the electromagnetic (EEG and MEG) brain signals allowing explorative analysis of neural sources informing classification. The proposed networks outperform traditional classifiers as well as more complex neural networks when decoding evoked and induced responses to different stimuli across subjects. Importantly, these models can successfully generalize to new subjects in real-time classification enabling more efficient brain–computer interfaces (BCI).",
keywords = "Brain–computer interface, Convolutional neural network, Magnetoencephalography",
author = "Ivan Zubarev and Rasmus Zetter and Halme, {Hanna Leena} and Lauri Parkkonen",
note = "| openaire: EC/H2020/678578/EU//HRMEG",
year = "2019",
month = "8",
day = "15",
doi = "10.1016/j.neuroimage.2019.04.068",
language = "English",
volume = "197",
pages = "425--434",
journal = "NeuroImage",
issn = "1053-8119",

}

RIS - Lataa

TY - JOUR

T1 - Adaptive neural network classifier for decoding MEG signals

AU - Zubarev, Ivan

AU - Zetter, Rasmus

AU - Halme, Hanna Leena

AU - Parkkonen, Lauri

N1 - | openaire: EC/H2020/678578/EU//HRMEG

PY - 2019/8/15

Y1 - 2019/8/15

N2 - We introduce two Convolutional Neural Network (CNN )classifiers optimized for inferring brain states from magnetoencephalographic (MEG) measurements. Network design follows a generative model of the electromagnetic (EEG and MEG) brain signals allowing explorative analysis of neural sources informing classification. The proposed networks outperform traditional classifiers as well as more complex neural networks when decoding evoked and induced responses to different stimuli across subjects. Importantly, these models can successfully generalize to new subjects in real-time classification enabling more efficient brain–computer interfaces (BCI).

AB - We introduce two Convolutional Neural Network (CNN )classifiers optimized for inferring brain states from magnetoencephalographic (MEG) measurements. Network design follows a generative model of the electromagnetic (EEG and MEG) brain signals allowing explorative analysis of neural sources informing classification. The proposed networks outperform traditional classifiers as well as more complex neural networks when decoding evoked and induced responses to different stimuli across subjects. Importantly, these models can successfully generalize to new subjects in real-time classification enabling more efficient brain–computer interfaces (BCI).

KW - Brain–computer interface

KW - Convolutional neural network

KW - Magnetoencephalography

UR - http://www.scopus.com/inward/record.url?scp=85065419441&partnerID=8YFLogxK

U2 - 10.1016/j.neuroimage.2019.04.068

DO - 10.1016/j.neuroimage.2019.04.068

M3 - Article

VL - 197

SP - 425

EP - 434

JO - NeuroImage

JF - NeuroImage

SN - 1053-8119

ER -

ID: 34091183