Using Riemannian geometry for SSVEP-based Brain Computer Interface (2015-01-14T00:00:00.000000Z)

TL;DR

The proposed online algorithm is evaluated and compared with state-of-the-art SSVEP methods, which are based on Canonical Correlation Analysis (CCA), and shown to improve both the classification accuracy and the information transfer rate in the online and asynchronous setup.

Abstract

Challenges for the next generation of Brain Computer Interfaces (BCI) are to mitigate the common sources of variability (electronic, electrical, biological) and to develop online and adaptive systems following the evolution of the subject's brain waves. Studying electroencephalographic (EEG) signals from their associated covariance matrices allows the construction of a representation which is invariant to extrinsic perturbations. As covariance matrices should be estimated, this paper first presents a thorough study of all estimators conducted on real EEG recording. Working in Euclidean space with covariance matrices is known to be error-prone, one might take advantage of algorithmic advances in Riemannian geometry and matrix manifold to implement methods for Symmetric Positive-Definite (SPD) matrices. Nonetheless, existing classification algorithms in Riemannian spaces are designed for offline analysis. We propose a novel algorithm for online and asynchronous processing of brain signals, borrowing principles from semi-unsupervised approaches and following a dynamic stopping scheme to provide a prediction as soon as possible. The assessment is conducted on real EEG recording: this is the first study on Steady-State Visually Evoked Potential (SSVEP) experimentations to exploit online classification based on Riemannian geometry. The proposed online algorithm is evaluated and compared with state-of-the-art SSVEP methods, which are based on Canonical Correlation Analysis (CCA). It is shown to improve both the classification accuracy and the information transfer rate in the online and asynchronous setup.

Authors

Emmanuel K. Kalunga

1 papers

S. Chevallier

1 papers

Quentin Barthélemy

1 papers

TL;DR

Abstract

Authors

References64 items

Self-calibration algorithm in an asynchronous P300-based brain–computer interface

Information geometry meets BCI spatial filtering using divergences

Robust Spatial Filtering with Beta Divergence

A review of kernels on covariance matrices for BCI applications

A New Generation of Brain-Computer Interface Based on Riemannian Geometry

SSVEP enhancement based on Canonical Correlation Analysis to improve BCI performances

Classification of covariance matrices using a Riemannian-based kernel for BCI applications

Kernel Methods on the Riemannian Manifold of Symmetric Positive Definite Matrices

On A Nonlinear Generalization of Sparse Coding and Dictionary Learning

The Riemannian Potato: an automatic and adaptive artifact detection method for online experiments using Riemannian geometry

Dynamic Stopping Improves the Speed and Accuracy of a P300 Speller

Electroencephalogram signals classification for sleep-state decision - a Riemannian geometry approach

BCI Signal Classification using a Riemannian-based kernel

Multiclass Brain–Computer Interface Classification by Riemannian Geometry

A subject transfer framework for EEG classification

Filter Bank Common Spatial Pattern Algorithm on BCI Competition IV Datasets 2a and 2b

Psychological predictors of SMR-BCI performance

Review of the BCI Competition IV

sw-SVM: sensor weighting support vector machines for EEG-based brain–computer interfaces

Online BCI Implementation of High-Frequency Phase Modulated Visual Stimuli

Channel selection procedure using riemannian distance for BCI applications

A framework for rapid visual image search using single-trial brain evoked responses

Single-trial analysis and classification of ERP components — A tutorial

Towards passive brain–computer interfaces: applying brain–computer interface technology to human–machine systems in general

Regularizing Common Spatial Patterns to Improve BCI Designs: Unified Theory and New Algorithms

Common Spatial Pattern revisited by Riemannian geometry

Regularized Common Spatial Pattern With Aggregation for EEG Classification in Small-Sample Setting

Riemannian Geometry Applied to BCI Classification

Information geometry in optimization, machine learning and statistical inference

Adaptation in P300 Brain–Computer Interfaces: A Two-Classifier Cotraining Approach

The Hybrid BCI

Towards a Cure for BCI Illiteracy

Evidences of cognitive effects over auditory steady-state responses by means of artificial neural networks and its use in brain-computer interfaces

EEG signal classification based on a Riemannian distance measure

An online multi-channel SSVEP-based brain–computer interface using a canonical correlation analysis method

Unsupervised Riemannian Clustering of Probability Density Functions

Clustering and dimensionality reduction on Riemannian manifolds

An Adaptive P300-Based Online Brain–Computer Interface

Evaluating the added predictive ability of a new marker: From area under the ROC curve to reclassification and beyond

Frequency Recognition Based on Canonical Correlation Analysis for SSVEP-Based BCIs

The BCI competition III: validating alternative approaches to actual BCI problems

Towards adaptive classification for BCI

A Shrinkage Approach to Large-Scale Covariance Matrix Estimation and Implications for Functional Genomics

Theoretical analysis of an improved covariance matrix estimator in non-Gaussian noise [radar detection applications]

A Differential Geometric Approach to the Geometric Mean of Symmetric Positive-Definite Matrices

Canonical Correlation Analysis: An Overview with Application to Learning Methods

Principal geodesic analysis for the study of nonlinear statistics of shape

The BCI competition 2003: progress and perspectives in detection and discrimination of EEG single trials

A well-conditioned estimator for large-dimensional covariance matrices

PCA+HMM+SVM for EEG pattern classification

Brain–computer interfaces for communication and control

Hidden Markov models for online classification of single trial EEG data

Single trial P3 epoch recognition in a virtual environment

Annual Review of Biophysics and Bioengineering

Automatic selection of the number of spatial filters for motor-imagery BCI

Could Anyone Use a BCI?

Optimization algorithms on matrix manifolds

Optimizing Spatial filters for Robust EEG Single-Trial Analysis

Introduction to Statistical Pattern Recognition

A Riemannian Framework for Tensor Computing

Introduction to Topological Manifolds

Electroencephalography: Basic Principles, Clinical Applications and Related Fields, Fourth Edition

Riemannian geometry and geometric analysis

Toward direct brain-computer communication.

Field of Study

Journal Information

Name