Deep learning-based electroencephalography analysis: a systematic review

@article{Roy2019DeepLE,
  title={Deep learning-based electroencephalography analysis: a systematic review},
  author={Yannick Roy and Hubert J. Banville and Isabela Albuquerque and Alexandre Gramfort and Tiago H. Falk and Jocelyn Faubert},
  journal={Journal of Neural Engineering},
  year={2019},
  volume={16}
}
Context. Electroencephalography (EEG) is a complex signal and can require several years of training, as well as advanced signal processing and feature extraction methodologies to be correctly interpreted. Recently, deep learning (DL) has shown great promise in helping make sense of EEG signals due to its capacity to learn good feature representations from raw data. Whether DL truly presents advantages as compared to more traditional EEG processing approaches, however, remains an open question… 

Towards Open-World EEG Decoding via Deep Learning

This article provides a comprehensive survey of DL methods for open-world EEG decoding, and identifies promising research directions to inspire future studies for EEG decoding in real-world applications.

Toward Open-World Electroencephalogram Decoding Via Deep Learning: A comprehensive survey

This article provides a comprehensive survey of DL methods for open-world EEG decoding and identifies promising research directions to inspire future studies for EEG decoding in real-world applications.

Uncovering the structure of clinical EEG signals with self-supervised learning

The results suggest that self-supervision may pave the way to a wider use of deep learning models on EEG data, and linear classifiers trained on SSL-learned features consistently outperformed purely supervised deep neural networks in low-labeled data regimes while reaching competitive performance when all labels were available.

Deep Convolutional Neural Network Applied to Electroencephalography: Raw Data vs Spectral Features

Interestingly, it is suggested that the same convolutional networks used to process EEG spectral features yield superior performance when applied to EEG raw data, as compared to spectral EEG features.

Deep Learning Methods in Electroencephalography

In this chapter, the state-of-the-art architectures and approaches to classification, segmentation, and enhancement of EEG recordings are described in applications to brain-computer interfaces, medical diagnostics and emotion recognition.

A novel explainable machine learning approach for EEG-based brain-computer interface systems

The interpretability of the deep CNN is explored to provide further insights into the activation mechanism of cortical sources during the preparation of hands’ sub-movements and shows a recurrent trend of spatial cortical activation across subjects.

Learning with self-supervision on EEG data

Results report that linear classifiers trained on SSL-learned features consistently outperformed purely supervised deep neural networks in low-labeled data regimes while reaching competitive performance when all labels were available, and suggest that self-supervision may pave the way to a wider use of deep learning models on EEG data.

Extracting Interpretable EEG Features from a Deep Learning Model to Assess the Quality of Human-Robot Co-manipulation

A novel computational approach to increase the interpretability of results from deep learning algorithm using two popular saliency detection algorithms: integrated gradients and ablation attribution method is proposed.

Data augmentation for learning predictive models on EEG: a systematic comparison

This work proposes a unified and exhaustive analysis of the main existing EEG augmentations, which are compared in a common experimental setting and highlights the best data augmentations to consider for sleep stage classi-cation and motor imagery brain computer interfaces.
...

References

SHOWING 1-10 OF 470 REFERENCES

Deep RNN learning for EEG based functional brain state inference

This study uses a similarity or coherence analysis between sub-band spectrum of individual trial which invalidates the effect of noise and shows that in the multiclass scenario the proposed algorithm performs at par with state-of-art results, whereas in two class scenario, the proposed algorithms outperforms most of the reported results.

Know Your Mind: Adaptive Brain Signal Classification with Reinforced Attentive Convolutional Neural Networks

A generic EEG signal classification framework that accommodates a wide range of applications and outperforms the state-of-the-art baselines and achieves the accuracy of more than 97% on all the datasets with low latency and good resilience of handling complex EEG signals across various domains is proposed.

Hierarchical internal representation of spectral features in deep convolutional networks trained for EEG decoding

Insight is provided into how ConvNets hierarchically represent spectral EEG features in their intermediate layers and it is suggested that convolutional neural networks can exploit and might help to better understand the compositional structure of EEG time series.

A Large-Scale Evaluation Framework for EEG Deep Learning Architectures

It is argued that the deep learning EEG framework as described here could help to tap the full potential of deep learning for BCI applications.

Deep Classification of Epileptic Signals

A new classification approach for EEG time series based on Recurrent Neural Networks (RNNs) via the use of Long- Short Term Memory (LSTM) networks is described, which reinforces the benefits of deep learning to be further attended in clinical applications and neuroscientific research.

ChronoNet: A Deep Recurrent Neural Network for Abnormal EEG Identification

One of the first steps in interpreting an EEG session - identifying whether the brain activity is abnormal or normal is identified and a novel recurrent neural network (RNN) architecture termed ChronoNet is proposed which is inspired by recent developments from the field of image classification and designed to work efficiently with EEG data.

Preference Classification Using Electroencephalography (EEG) and Deep Learning

It is shown that inter-subject variability introduces significant classification problems when larger cohorts of test subjects are used and that deep learning shows promising results in terms of addressing this inter- subject variability problem in EEG-based preference classification.

Individual Recognition in Schizophrenia using Deep Learning Methods with Random Forest and Voting Classifiers: Insights from Resting State EEG Streams

This study proposes new individual recognition schemes based on spatio-temporal resting state Electroencephalography (EEG) data and modified deep learning architectures which aim to automatically extract an individual's unique features are developed to conduct classification.

Deep Feature Learning for EEG Recordings

This work introduces and compares several strategies for learning discriminative features from electroencephalography (EEG) recordings using deep learning techniques and evaluated the different techniques using the publicly available OpenMIIR dataset of EEG recordings taken while participants listened to and imagined music.

Automatic Analysis of EEGs Using Big Data and Hybrid Deep Learning Architectures

This approach delivers a sensitivity above 90% while maintaining a specificity below 5%.
...