EEG-inception: an accurate and robust end-to-end neural network for EEG-based motor imagery classification

  title={EEG-inception: an accurate and robust end-to-end neural network for EEG-based motor imagery classification},
  author={Ce Zhang and Young-Keun Kim and Azim Eskandarian},
  journal={Journal of Neural Engineering},
Objective. Classification of electroencephalography (EEG)-based motor imagery (MI) is a crucial non-invasive application in brain–computer interface (BCI) research. This paper proposes a novel convolutional neural network (CNN) architecture for accurate and robust EEG-based MI classification that outperforms the state-of-the-art methods. Approach. The proposed CNN model, namely EEG-inception, is built on the backbone of the inception-time network, which has showed to be highly efficient and… 

Anchored-STFT and GNAA: An extension of STFT in conjunction with an adversarial data augmentation technique for the decoding of neural signals

A novel feature extraction method called anchored Short Time Fourier Transform (anchoredSTFT), which is an advanced version of STFT, as it minimizes the trade-off between temporal and spectral resolution presented by STFT.

The evolution of AI approaches for motor imagery EEG-based BCIs

AI approaches applied to datasets collected in years and with dif-ferent devices but with coherent experimental paradigms are investigated with the aim of providing a concise yet comprehensive survey on the evolution and in-situence of AI techniques on MI EEG-based BCI data.

A Lightweight End-to-End Neural Networks for Decoding of Motor Imagery Brain Signal

The proposed end-to-end neural network named lightweight EEG-inception squeeze-and-excitation network (LiteEEG-ISENet) outperforms the existing method in terms of decoding performance and neural network memory efficiency.

Dual attentive fusion for EEG-based brain-computer interfaces

This study proposes a Dual Attentive Fusion Model (DAFM) for the EEG-based BCI and is the first to fuse spatial and temporal dimensions in an interactive attention module and outperforms state-of-the-art methods.

Emotion recognition while applying cosmetic cream using deep learning from EEG data; cross-subject analysis

This is the first study to apply a CNN-based deep learning method based on EEG data to evaluate preference for cosmetic creams and it is found that the classification performance is higher when using multi-band features than when using single-band feature.

EEG-Fest: Few-shot based Attention Network for Driver's Vigilance Estimation with EEG Signals

A generalized few-shot model, namely EEG-Fest, that can classify the query sample’s drowsiness with a few samples, identify whether a query sample is anomaly signals or not, and achieve subject independent classification is proposed.

Novel hybrid visual stimuli incorporating periodic motions into conventional flickering or pattern-reversal visual stimuli for steady-state visual evoked potential-based brain-computer interfaces

In this study, we proposed a new type of hybrid visual stimuli for steady-state visual evoked potential (SSVEP)-based brain-computer interfaces (BCIs), which incorporate various periodic motions into

Motor imagery evokes strengthened activation in sensorimotor areas and its effective connectivity related to cognitive regions in patients with complete spinal cord injury

It is demonstrated that motor related brain areas can be functionally preserved and activated through MI after CSCI, and the potential mechanism of MI in the motor rehabilitation of CSCi patients is revealed.



Image-based Motor Imagery EEG Classification using Convolutional Neural Network

  • Tao YangK. Phua R. So
  • Computer Science
    2019 IEEE EMBS International Conference on Biomedical & Health Informatics (BHI)
  • 2019
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.

Classification of High-Dimensional Motor Imagery Tasks Based on An End-To-End Role Assigned Convolutional Neural Network

This study proposes an end-to-end role assigned convolutional neural network (ERA-CNN) which considers discriminative features of each upper limb region by adopting the principle of a hierarchical CNN architecture and demonstrates the possibility of decoding user intention by using only EEG signals with robust performance using the ERA-CNN.

A novel deep learning approach for classification of EEG motor imagery signals

The results show that deep learning methods provide better classification performance compared to other state of art approaches, and can be applied successfully to BCI systems where the amount of data is large due to daily recording.

HS-CNN: A CNN with hybrid convolution scale for EEG motor imagery classification.

This work has proposed a hybrid-scale CNN architecture with a data augmentation method for EEG motor imagery classification that achieves an average classification accuracy of 91.57% and 87.6% on two commonly used datasets, which outperforms several state-of-the-art epilepsy classification methods.

Spatial-Frequency Feature Learning and Classification of Motor Imagery EEG Based on Deep Convolution Neural Network

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.

LSTM-Based EEG Classification in Motor Imagery Tasks

A one dimension-aggregate approximation (1d-AX) is employed to achieve robust classification, and Inspired by classical common spatial pattern, channel weighting technique is further deployed to enhance the effectiveness of the proposed classification framework.

A Channel-Projection Mixed-Scale Convolutional Neural Network for Motor Imagery EEG Decoding

An end-to-end EEG decoding framework, which employs raw multi-channel EEG as inputs is proposed, to boost decoding accuracy by the channel-projection mixed-scale convolutional neural network (CP-MixedNet) aided by amplitude-perturbation data augmentation.

EEG-Based Brain-Computer Interfaces Using Motor-Imagery: Techniques and Challenges

Electroencephalography (EEG)-based brain-computer interfaces (BCIs), particularly those using motor-imagery (MI) data, have the potential to become groundbreaking technologies in both clinical and

Motor Imagery EEG Signals Classification Based on Mode Amplitude and Frequency Components Using Empirical Wavelet Transform

This study proposes, for the first time, a novel data adaptive empirical wavelet transform (EWT) based signal decomposition method for improving the classification accuracy of MI based EEG signals and shows the effectiveness and great potential of EWT for BCI system applications.

A Deep Learning Scheme for Motor Imagery Classification based on Restricted Boltzmann Machines

A novel deep learning scheme based on restricted Boltzmann machine (RBM) is proposed, which shows that the performance improvement of FDBN over other selected state-of-the-art methods is statistically significant.