Adaptive neural network classifier for decoding MEG signals

Ivan Zubarev*, Rasmus Zetter, Hanna Leena Halme, Lauri Parkkonen

*Corresponding author for this work

Research output: Contribution to journalArticleScientificpeer-review

2 Citations (Scopus)
181 Downloads (Pure)

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).

Original languageEnglish
Pages (from-to)425-434
Number of pages10
JournalNeuroImage
Volume197
DOIs
Publication statusPublished - 15 Aug 2019
MoE publication typeA1 Journal article-refereed

Keywords

  • Brain–computer interface
  • Convolutional neural network
  • Magnetoencephalography

Fingerprint Dive into the research topics of 'Adaptive neural network classifier for decoding MEG signals'. Together they form a unique fingerprint.

  • Equipment

    Science-IT

    Mikko Hakala (Manager)

    School of Science

    Facility/equipment: Facility

  • Cite this