Virtual EEG-electrodes: Convolutional neural networks as a method for upsampling or restoring channels

Svantesson, Mats; Olausson, Håkan; Eklund, Anders; Thordstein, Magnus

doi:10.1016/j.jneumeth.2021.109126

Cited by 19 publications

(16 citation statements)

References 31 publications

Supporting

Mentioning

Contrasting

Order By: Relevance

“…Another avenue of research is to study the potential of EEG learned graphs as a backbone on which spatial filtering of EEG maps can be performed—e.g. for interpolation of missing channels (Banville et al, 2022; Svantesson et al, 2021)—via spectral graph diffusion filtering schemes (Abramian et al, 2021; Tarun et al, 2020). Finally, the proposed EEG-based graph learning and spectral representation via GSP can be readily extended to other data modalities, in particular, fMRI (Itani and Thanou, 2021; Preti and Van De Ville, 2019), near-infrared spectroscopy (Petrantonakis and Kompatsiaris, 2018), or Magnetoencephalography (Tewarie et al, 2019; Sareen et al, 2021).…”

Section: Discussionmentioning

confidence: 99%

Spectral Representation of EEG Data using Learned Graphs with Application to Motor Imagery Decoding

Miri

Abootalebi

Saeedi-Sourck

et al. 2022

Preprint

View full text Add to dashboard Cite

Objective: This paper presents a graph signal processing (GSP)-based approach for decoding two-class motor imagery EEG data via deriving task-specific discriminative features. Methods: First, a graph learning (GL) method is used to learn subject-specific graphs from EEG signals. Second, by diagonalizing the normalized Laplacian matrix of each subject graph, an orthonormal basis is obtained using which the graph Fourier transform (GFT) of the EEG signals is computed. Third, the GFT coefficients are mapped into a discriminative subspace for differentiating two class data using a projection matrix obtained by the Fukunaga-Koontz transform (FKT). Finally, an SVM classifier is trained and tested on the variance of the resulting features to differentiate motor imagery classes. Results: The proposed method is evaluated on Dataset IVa of the BCI Competition III and its performance is compared to i) using features extracted on a graph constructed by Pearson correlation coefficients and ii) three state-of-the-art alternative methods. Conclusion: Experimental results indicate the superiority of the proposed method over alternative methods, reflecting the added benefit of integrating elements from GL, GSP and FKT. Significance: The proposed method and results underpin the importance of integrating spatial and temporal characteristics of EEG signals in extracting features that can more powerfully differentiate motor imagery classes.

show abstract

Section: Discussionmentioning

confidence: 99%

Spectral Representation of EEG Data using Learned Graphs with Application to Motor Imagery Decoding

Miri

Abootalebi

Saeedi-Sourck

et al. 2022

Preprint

View full text Add to dashboard Cite

show abstract

“…Finally, generic machine learning models have been proposed to recover missing or corrupted channels. For instance, generative adversarial networks (GANs) have previously been trained to recover dense EEG montages from a few electrodes [36,37]. Other similar methods have been proposed, e.g., using long short-term memory (LSTM) neural networks [38], autoencoders [39], or tensor decomposition and compressed sensing [40,41].…”

Section: State-of-the-art Approaches To Noise-robust Eeg Processingmentioning

confidence: 99%

“…Signal Space Separation (SSS) for MEG [49] Might not work if too few channels available; Additional preprocessing step; Preprocessing might discard important information for learning task ICA-based denoising [26,27,28] Automated correction Autoreject [33], FASTER [31], PREP [32] Expensive preprocessing step Model-based interpolation/ reconstruction Deep learning-based superresolution (GAN, LSTM, AE, etc.) [50,51,36,37,39] Separate training step; Additional inference step to reconstruct at test time; Requires separate procedure to detect corrupted channels Tensor decomposition, compressed sensing [41,40] Interpretable denoising Channel corruptioninvariant architecture…”

Section: Spatial Projectionbased Approachesmentioning

confidence: 99%

See 1 more Smart Citation

Robust learning from corrupted EEG with dynamic spatial filtering

Banville¹,

Wood²,

Aimone³

et al. 2021

Preprint

View full text Add to dashboard Cite

Building machine learning models using EEG recorded outside of the laboratory setting requires methods robust to noisy data and randomly missing channels. This need is particularly great when working with sparse EEG montages (1-6 channels), often encountered in consumergrade or mobile EEG devices. Neither classical machine learning models nor deep neural networks trained end-to-end on EEG are typically designed or tested for robustness to corruption, and especially to randomly missing channels. While some studies have proposed strategies for using data with missing channels, these approaches are not practical when sparse montages are used and computing power is limited (e.g., wearables, cell phones). To tackle this problem, we propose dynamic spatial filtering (DSF), a multi-head attention module that can be plugged in before the first layer of a neural network to handle missing EEG channels by learning to focus on good channels and to ignore bad ones. We tested DSF on public EEG data encompassing ∼4,000 recordings with simulated channel corruption and on a private dataset of ∼100 at-home recordings of mobile EEG with natural corruption. Our proposed approach achieves the same performance as baseline models when no noise is applied, but outperforms baselines by as much as 29.4% accuracy when significant channel corruption is present. Moreover, DSF outputs are interpretable, making it possible to monitor channel importance in real-time. This approach has the potential to enable the analysis of EEG in challenging settings where channel corruption hampers the reading of brain signals.

show abstract

“…For example, Huang et al [11] proposed a separable convolutional neural network(CNN) with bilinear interpolation in brain-computer interface for EEG classification. Svantesson et al [38] utilized CNN as interpolation method to upsample and restore channels, which finally recreate EEG signals with a higher accuracy. In the field of EEG-based emotion recognition, interpolation algorithms are still relatively scarce.…”

Section: Eeg Interpolation Algorithmsmentioning

confidence: 99%

SFE-Net: EEG-based Emotion Recognition with Symmetrical Spatial Feature Extraction

Deng

Zhu

Yang

2021

Preprint

View full text Add to dashboard Cite

Emotion recognition based on EEG (electroencephalography) has been widely used in human-computer interaction, distance education and health care. However, the conventional methods ignore the adjacent and symmetrical characteristics of EEG signals, which also contain salient information related to emotion. In this paper, we present a spatial folding ensemble network (SFENet) for EEG feature extraction and emotion recognition. Firstly, for the undetected area between EEG electrodes, we employ an improved Bicubic-EEG interpolation algorithm for EEG channel information completion, which allows us to extract a wider range of adjacent space features. Then, motivated by the spatial symmetry mechanism of human brain, we fold the input EEG channel data with five different symmetrical strategies: the left-right folds, the right-left folds, the top-bottom folds, the bottom-top folds, and the entire double-sided brain folding, which enable the proposed network to extract the information of space features of EEG signals more effectively. Finally, 3DCNN based spatial and temporal extraction and multi voting strategy of ensemble learning are employed to model a new neural network. With this network, the spatial features of different symmetric folding signlas can be extracted simultaneously, which greatly improves the robustness and accuracy of feature recognition. The experimental results on DEAP and SEED data sets show that the proposed algorithm has comparable performance in term of recognition accuracy. CCS CONCEPTS• Computing methodologies → Neural networks; Shape representations; Object identification.

show abstract

Virtual EEG-electrodes: Convolutional neural networks as a method for upsampling or restoring channels

Cited by 19 publications

References 31 publications

Spectral Representation of EEG Data using Learned Graphs with Application to Motor Imagery Decoding

Spectral Representation of EEG Data using Learned Graphs with Application to Motor Imagery Decoding

Robust learning from corrupted EEG with dynamic spatial filtering

SFE-Net: EEG-based Emotion Recognition with Symmetrical Spatial Feature Extraction

Contact Info

Product

Resources

About