Effects of local and global spatial patterns in EEG motor-imagery classification using convolutional neural network
- 13 August 2020
- journal article
- research article
- Published by Taylor & Francis in Brain-Computer Interfaces
- Vol. 7 (3-4) , 47-56
Abstract
An emerging idea in electroencephalogram motor-imagery (EEG-MI) classification is the ‘EEG-as-image’ approach. It aims to capture local EEG signal dynamics by preserving the spatial relationships of EEG channels. We hypothesize that due to the global nature of EEG modulations, a better approach is to apply global unmixing filters.Keywords
This publication has 30 references indexed in Scilit:
- Optimizing spatial patterns with sparse filter bands for motor-imagery based brain–computer interfaceJournal of Neuroscience Methods, 2015
- Parallel convolutional-linear neural network for motor imagery classification2015
- EMD-Based Temporal and Spectral Features for the Classification of EEG Signals Using Supervised LearningIEEE Transactions on Neural Systems and Rehabilitation Engineering, 2015
- Going deeper with convolutions2015
- Probabilistic Common Spatial Patterns for Multichannel EEG AnalysisIEEE Transactions on Pattern Analysis and Machine Intelligence, 2014
- EEG Data Space Adaptation to Reduce Intersession Nonstationarity in Brain-Computer InterfaceNeural Computation, 2013
- Classification of covariance matrices using a Riemannian-based kernel for BCI applicationsNeurocomputing, 2013
- Multiclass Brain–Computer Interface Classification by Riemannian GeometryIEEE Transactions on Biomedical Engineering, 2012
- Review of the BCI Competition IVFrontiers in Neuroscience, 2012
- Filter Bank Common Spatial Pattern Algorithm on BCI Competition IV Datasets 2a and 2bFrontiers in Neuroscience, 2012