Multimodal Classification with Deep Convolutional-Recurrent Neural Networks for Electroencephalography

@article{Tan2017MultimodalCW,
  title={Multimodal Classification with Deep Convolutional-Recurrent Neural Networks for Electroencephalography},
  author={Chuanqi Tan and Fuchun Sun and Wenchang Zhang and Jianhua Chen and Chunfang Liu},
  journal={ArXiv},
  year={2017},
  volume={abs/1807.10641}
}
Electroencephalography (EEG) has become the most significant input signal for brain computer interface (BCI) based systems. However, it is very difficult to obtain satisfactory classification accuracy due to traditional methods can not fully exploit multimodal information. Herein, we propose a novel approach to modeling cognitive events from EEG data by reducing it to a video classification problem, which is designed to preserve the multimodal information of EEG. In addition, optical flow is… 
Cross-Subject EEG Signal Classification with Deep Neural Networks Applied to Motor Imagery
TLDR
A deep learning neural network architecture to classify SMR signals due to its success for some previous works and to visualize the learned features and to prevent learning problem like overfitting is presented.
Image-based Motor Imagery EEG Classification using Convolutional Neural Network
  • Tao Yang, K. Phua, R. So
  • Computer Science
    2019 IEEE EMBS International Conference on Biomedical & Health Informatics (BHI)
  • 2019
TLDR
This study shows that the image-based CNN method improves the classification performance, and the inclusion of Delta band improves classification performance for the current dataset.
EEG-based image classification via a region-level stacked bi-directional deep learning framework
TLDR
A region-level stacked bi-directional deep learning framework for EEG-based image classification inspired by the hemispheric lateralization of human brains is proposed to extract additional information at regional level to strengthen and emphasize the differences between two hemispheres.
Spatial-Frequency Feature Learning and Classification of Motor Imagery EEG Based on Deep Convolution Neural Network
TLDR
A novel deep learning methodology which can be used for spatial-frequency feature learning and classification of motor imagery EEG and Superior classification performance indicates that the proposed method is a promising pattern recognition algorithm for MI-based BCI system.
Multi-class motor imagery EEG classification method with high accuracy and low individual differences based on hybrid neural network
TLDR
Experimental results show that the proposed deep learning method improves the accuracy of multi-classification and overcomes the impact of individual differences on classification by training neural network subject-dependent, which promotes the development of actual brain-computer interface systems.
Application of Convolutional Neural Network Method in Brain Computer Interface
TLDR
Convolutional Neural Networks (CNN) holds great promises, which has been extensively employed for feature classification in BCI based on various EEG signals, and is reviewed in this paper.
Universal Joint Feature Extraction for P300 EEG Classification Using Multi-Task Autoencoder
TLDR
The event-related potential encoder network (ERPENet) is proposed, a multi-task autoencoder-based model that can be applied to any ERP-related tasks and its capability to handle various kinds of ERP datasets and its robustness across multiple recording setups, enabling joint training across datasets is proposed.
Electroencephalography Classification in Brain-Computer Interface with Manifold Constraints Transfer
TLDR
A sophisticated electroencephalography (EEG) signal representation is constructed and an efficient EEG feature extractor is obtained through manifold constraints-based joint adversarial training with training data from other domains.
An Attentional-LSTM for Improved Classification of Brain Activities Evoked by Images
TLDR
The results demonstrate that the proposed RA-BiLSTM not only achieves effective classification of brain activities on evoked image categories, but also significantly outperforms the existing state of the arts.
...
...

References

SHOWING 1-10 OF 23 REFERENCES
Learning Representations from EEG with Deep Recurrent-Convolutional Neural Networks
TLDR
This work transforms EEG activities into a sequence of topology-preserving multi-spectral images, as opposed to standard EEG analysis techniques that ignore such spatial information, and trains a deep recurrent-convolutional network inspired by state-of-the-art video classification to learn robust representations from the sequence of images.
Spatial and spectral features fusion for EEG classification during motor imagery in BCI
TLDR
A algorithm for EEG classification with the ability to fuse multiple features and fuse these features with a fusion algorithm in orchestrate way to improve the accuracy of classification is proposed.
Feature learning from incomplete EEG with denoising autoencoder
A Deep Learning Method for Classification of EEG Data Based on Motor Imagery
TLDR
The performance of the proposed DBN was tested with different combinations of hidden units and hidden layers on multiple subjects, the experimental results showed that the proposed method performs better with 8 hidden layers, and there was an improvement of 4 – 6% for certain cases.
Convolutional Neural Networks for P300 Detection with Application to Brain-Computer Interfaces
  • H. Cecotti, A. Gräser
  • Computer Science
    IEEE Transactions on Pattern Analysis and Machine Intelligence
  • 2011
TLDR
A new method for the detection of P300 waves is presented, based on a convolutional neural network (CNN), which provides a new way for analyzing brain activities due to the receptive field of the CNN models.
Using Convolutional Neural Networks to Recognize Rhythm Stimuli from Electroencephalography Recordings
TLDR
Convolutional neural networks are applied to analyze and classify EEG data recorded within a rhythm perception study in Kigali, Rwanda which comprises 12 East African and 12 Western rhythmic stimuli - each presented in a loop for 32 seconds to 13 participants.
Optimal spatial filtering of single trial EEG during imagined hand movement.
TLDR
It is demonstrated that spatial filters for multichannel EEG effectively extract discriminatory information from two populations of single-trial EEG, recorded during left- and right-hand movement imagery.
Beyond short snippets: Deep networks for video classification
TLDR
This work proposes and evaluates several deep neural network architectures to combine image information across a video over longer time periods than previously attempted, and proposes two methods capable of handling full length videos.
Continuous emotion detection using EEG signals and facial expressions
TLDR
For the first time, this paper continuously detect valence from electroencephalogram (EEG) signals and facial expressions in response to videos and the results of multimodal fusion between facial expression and EEG signals are presented.
...
...