Siamese Neural Networks for EEG-based Brain-computer Interfaces

  title={Siamese Neural Networks for EEG-based Brain-computer Interfaces},
  author={Soroosh Shahtalebi and A. Asif and Arash Mohammadi},
  journal={2020 42nd Annual International Conference of the IEEE Engineering in Medicine \& Biology Society (EMBC)},
Motivated by the inconceivable capability of human brain in simultaneously processing multi-modal signals and its real-time feedback to the outer world events, there has been a surge of interest in establishing a communication bridge between the human brain and a computer, which are referred to as Brain-computer Interfaces (BCI). To this aim, monitoring the electrical activity of brain through Electroencephalogram (EEG) has emerged as the prime choice for BCI systems. To discover the underlying… 

Figures and Tables from this paper

Classification of Imagined Speech Using Siamese Neural Network
The proposed framework would help to increase the classification performance of imagined speech for a small amount of data and implement an intuitive communication system using Siamese neural network encoder, which can learn discriminant features from a small dataset.
CNN-based framework using spatial dropping for enhanced interpretation of neural activity in motor imagery classification
An architecture of Convolutional Neural Networks (CNN) with an enhanced interpretation of the spatial brain neural patterns that mainly contribute to the classification of MI tasks is developed, showing that the highest contribution clusters over the sensorimotor cortex with a differentiated behavior of rhythms.
Runtime Detection of Executional Errors in Robot-Assisted Surgery
A runtime monitoring system for the detection of executional errors during surgical tasks through the analysis of kinematic data that incorporates dual Siamese neural networks and knowledge of surgical context, including surgical tasks and gestures, to learn the differences between normal and erroneous surgical trajectories from small training datasets.
Impact of Class Imbalance on Convolutional Neural Network Training in Multi-class Problems
A systematic analysis aimed at understanding how the issue of class inequality affects the efficiency of a convolutionary neural network trained for a task of image classification is presented, and a technique for correcting the overtraining and that the network generalization is presented.


Feature Space Reduction for Single Trial EEG Classification based on Wavelet Decomposition
A level-based classification approach that couples the Wavelet decomposition with Riemannian manifold spatial learning (WvRiem) is proposed and is evaluated on the BCI Competition IV2a dataset and noticeably outperforms its counterparts.
Brain–computer interfaces in neurological rehabilitation
Ternary ECOC classifiers coupled with optimized spatio-spectral patterns for multiclass motor imagery classification
A modified version of the ECOC classifiers adopted to EEG classification problems which deploys ternary class codewords is utilized, coupled with a Bayesian framework to compute the optimized spatio-spectral filters to extract the most discriminative feature sets of different classes.
Evolving Signal Processing for Brain–Computer Interfaces
The current neuroscientific questions and data processing challenges facing BCI designers are discussed and some promising current and future directions to address them are outlined.
Optimal spatial filtering of single trial EEG during imagined hand movement.
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.
A Novel Bayesian Framework for Discriminative Feature Extraction in Brain-Computer Interfaces
A novel Bayesian framework for discriminative feature extraction for motor imagery classification in an EEG-based BCI in which the class-discriminative frequency bands and the corresponding spatial filters are optimized by means of the probabilistic and information-theoretic approaches is proposed.
EEG Source Imaging Enhances the Decoding of Complex Right-Hand Motor Imagery Tasks
This study extends previous EEG source imaging work to decoding natural hand/wrist manipulations by applying a novel technique to classifying four complex motor imaginations of the right hand: flexion, extension, supination, and pronation, and suggests ESI is able to enhance BCI performance of decoding complex right-hand motor imagery tasks.
A Bayesian Framework to Optimize Double Band Spectra Spatial Filters for Motor Imagery Classification
The proposed Bayesian framework to simultaneously optimize a number of filter banks and spatial filters according to the patterns of brain activity for each subject outperforms its counterparts and introduces a robust framework for motor imagery studies.
Separable Common Spatio-Spectral Patterns for Motor Imagery BCI Systems
A novel method for extraction of discriminant spatio-spectral EEG features in MI-BCI, which competes closely with filter-bank CSP (FBCSP), and can even outperform the FBCSP if enough training data are available.
Regularized Common Spatial Pattern With Aggregation for EEG Classification in Small-Sample Setting
A regularized CSP (R-CSP) algorithm is proposed, where the covariance-matrix estimation is regularized by two parameters to lower the estimation variance while reducing the estimation bias.