Multi-Class Motor Imagery EEG Decoding for Brain-Computer Interfaces

Recent studies show that scalp electroencephalography (EEG) as a non-invasive interface has great potential for brain-computer interfaces (BCIs). However, one factor that has limited practical applications for EEG-based BCI so far is the difficulty to decode brain signals in a reliable and efficient way. This paper proposes a new robust processing framework for decoding of multi-class motor imagery (MI) that is based on five main processing steps. (i) Raw EEG segmentation without the need of visual artifact inspection. (ii) Considering that EEG recordings are often contaminated not just by electrooculography (EOG) but also other types of artifacts, we propose to first implement an automatic artifact correction method that combines regression analysis with independent component analysis for recovering the original source signals. (iii) The significant difference between frequency components based on event-related (de-) synchronization and sample entropy is then used to find non-contiguous discriminating rhythms. After spectral filtering using the discriminating rhythms, a channel selection algorithm is used to select only relevant channels. (iv) Feature vectors are extracted based on the inter-class diversity and time-varying dynamic characteristics of the signals. (v) Finally, a support vector machine is employed for four-class classification. We tested our proposed algorithm on experimental data that was obtained from dataset 2a of BCI competition IV (2008). The overall four-class kappa values (between 0.41 and 0.80) were comparable to other models but without requiring any artifact-contaminated trial removal. The performance showed that multi-class MI tasks can be reliably discriminated using artifact-contaminated EEG recordings from a few channels. This may be a promising avenue for online robust EEG-based BCI applications.

• Publication year

  2012

• Venue

  Frontiers in Neuroscience

• Publication date

  2012-10-09

• Fields of study

  Medicine, Computer Science, Engineering

• Identifiers
  DOI 10.3389/fnins.2012.00151PMID 23087607PMCID 3466781
• External record

  Open on Semantic Scholar

• Source metadata

  Semantic Scholar, PubMed

• No claims are published for this paper.

• No concepts are published for this paper.

• LIBSVM: A library for support vector machines

  2011cited by this paper
• Movement

  2011cited by this paper
• Optimizing the Channel Selection and Classification Accuracy in EEG-Based BCI

  2011cited by this paper
• Continuous Three-Dimensional Control of a Virtual Helicopter Using a Motor Imagery Based Brain-Computer Interface

  2011cited by this paper
• Matlab FE_Toolbox - an universal utility for feature extraction of EEG signals for BCI realization

  2010cited by this paper
• Nonstationary Brain Source Separation for Multiclass Motor Imagery

  2010cited by this paper
• Removing muscle and eye artifacts using blind source separation techniques in ictal EEG source imaging.

  2009cited by this paper
• Automatic removal of eye movement artifacts from the EEG using ICA and the dipole model

  2009cited by this paper
• Multi-Class Independent Common Spatial Patterns: Exploiting Energy Variations of Brain Sources

  2008cited by this paper
• Single-Trial EEG Source Reconstruction for Brain–Computer Interface

  2008cited by this paper
• BCI Competition 2008 { Graz data set B

  2008influential reference
• Filter Bank Common Spatial Pattern (FBCSP) in Brain-Computer Interface

  2008cited by this paper
• An efficient P300-based brain-computer interface for disabled subjects.

  2008cited by this paper
• A fully automated correction method of EOG artifacts in EEG recordings.

  2007cited by this paper
• A survey of signal processing algorithms in brain–computer interfaces based on electrical brain signals

  2007cited by this paper
• EMG and EOG artifacts in brain computer interface systems: A survey.

  2007cited by this paper
• A Brain Computer Interface Based on Neural Network with Efficient Pre-Processing

  2006cited by this paper
• Non-Invasive Brain Computer Interface for Mental Control of a Simulated Wheelchair

  2006cited by this paper
• What disconnection tells about motor imagery: evidence from paraplegic patients.

  2005cited by this paper
• Noninvasive brain-actuated control of a mobile robot by human EEG

  2004cited by this paper
• Automatic removal of eye movement and blink artifacts from EEG data using blind component separation.

  2004cited by this paper
• Sample entropy analysis of neonatal heart rate variability.

  2002cited by this paper
• Brain-computer interfaces for communication and control.

  2002cited by this paper
• EVALUATION OF EVENT-RELATED DESYNCHRONIZATION ( ERD ) PRECEDING AND FOLLOWING VOLUNTARY SELF-PACED MOVEMENT

  2002cited by this paper
• The Nature of Statistical Learning Theory

  2000cited by this paper
• A Fast Fixed-Point Algorithm for Independent Component Analysis of Complex Valued Signals

  2000cited by this paper
• Physiological time-series analysis using approximate entropy and sample entropy.

  2000cited by this paper
• Current trends in Graz Brain-Computer Interface (BCI) research.

  2000cited by this paper
• Event-related EEG/MEG synchronization and desynchronization: basic principles.

  1999cited by this paper
• Fast and robust fixed-point algorithms for independent component analysis

  1999cited by this paper
• A Fast Fixed-Point Algorithm for Independent Component Analysis

  1997cited by this paper
• EEG-based discrimination between imagination of right and left hand movement.

  1997cited by this paper
• Event-related synchronization (ERS): an electrophysiological correlate of cortical areas at rest.

  1992cited by this paper
• Approximate entropy as a measure of system complexity.

  1991cited by this paper
• Evaluation of event-related desynchronization (ERD) preceding and following voluntary self-paced movement.

  1979cited by this paper
• Graphical display and statistical evaluation of event-related desynchronization (ERD).

  1977cited by this paper
• Event-related cortical desynchronization detected by power measurements of scalp EEG.

  1977cited by this paper
• A Coefficient of Agreement for Nominal Scales

  1960cited by this paper

• Computing Science, Communication and Security

  2026cites this paper
• Hierarchical attention enhanced deep learning achieves high precision motor imagery classification in brain computer interfaces

  2025cites this paper
• Using multivariate pattern analysis to increase effect sizes for event‐related potential analyses

  2024cites this paper
• EEG-based identification system using deep neural networks with frequency features

  2024cites this paper
• Performance Improvement with Reduced Number of Channels in Motor Imagery BCI System

  2024cites this paper
• Cortical signals analysis to recognize intralimb mobility using modified RNN and various EEG quantities

  2024cites this paper
• Multi-Task EEG Signal Classification Using Correlation-Based IMF Selection and Multi-Class CSP

  2023cites this paper
• A novel scheme based on information theory and transfer learning for multi classes motor imagery decoding

  2023cites this paper
• Beyond passive observation: feedback anticipation and observation activate the mirror system in virtual finger movement control via P300-BCI

  2023cites this paper
• UNCER: A framework for uncertainty estimation and reduction in neural decoding of EEG signals

  2023cites this paper
• Parallel genetic algorithm based common spatial patterns selection on time-frequency decomposed EEG signals for motor imagery brain-computer interface

  2023cites this paper
• A Critical Survey of EEG-Based BCI Systems for Applications in Industrial Internet of Things

  2023cites this paper
• Optimal Channel Selection for EEG-Based Enhanced Brain Robot Interface for Autonomous Wheelchair

  2023cites this paper
• Using Multivariate Pattern Analysis to Increase Effect Sizes for Event-Related Potential Analyses

  2023cites this paper
• Brain Computer Interface using Genetic Algorithm with modified Genome and Phenotype Structures

  2023cites this paper
• Functional Connectivity and Feature Fusion Enhance Multiclass Motor-Imagery Brain–Computer Interface Performance

  2023cites this paper
• Design and Validation of a Low-Cost Mobile EEG-Based Brain–Computer Interface

  2023cites this paper
• Decoding Multi-Class EEG Signals of Hand Movement Using Multivariate Empirical Mode Decomposition and Convolutional Neural Network

  2022cites this paper
• Adaptive binary multi-objective harmony search algorithm for channel selection and cross-subject generalization in motor imagery-based BCI

  2022cites this paper
• Decoding motor imagery with a simplified distributed dipoles model at source level

  2022cites this paper
• Recognition of multi-cognitive tasks from EEG signals using EMD methods

  2022cites this paper
• Uncertainty Detection in EEG Neural Decoding Models

  2022cites this paper
• High accuracy decoding of motor imagery directions from EEG-based brain computer interface using filter bank spatially regularised common spatial pattern method

  2022cites this paper
• Uncertainty Detection and Reduction in Neural Decoding of EEG Signals

  2021cites this paper
• A new phase-based feature extraction method for four-class motor imagery classification

  2021cites this paper
• Crossing time windows optimization based on mutual information for hybrid BCI.

  2021cites this paper
• Neural Encoding and Decoding

  2021cites this paper
• Classification of Four-Class Motor-Imagery Data for Brain-Computer Interfaces

  2021cites this paper
• Single upper limb functional movements decoding from motor imagery EEG signals using wavelet neural network

  2021cites this paper
• Brain-Computer Interface: Advancement and Challenges

  2021cites this paper
• Distinguishable spatial-spectral feature learning neural network framework for motor imagery-based brain–computer interface

  2021cites this paper
• Sequence-to-sequence deep neural network with spatio-spectro and temporal features for motor imagery classification

  2021cites this paper
• Representation Learning for Motor Imagery Recognition with Deep Neural Network

  2021cites this paper
• F-score Based EEG Channel Selection Methods for Emotion Recognition

  2021cites this paper
• A Neurophysiological Pattern as a Precursor of Work-Related Musculoskeletal Disorders Using EEG Combined with EMG

  2021cites this paper
• Evaluation on the Effect of EEG Pre-processing and Hyper parameters Tuning to the Performance of Convolutional Neural Network Motor Execution Classification

  2021cites this paper
• Brain Activity Recognition Method Based on Attention-Based RNN Mode

  2021cites this paper
• A Sensorimotor Rhythm-Based Brain–Computer Interface Controlled Functional Electrical Stimulation for Handgrasp Rehabilitation

  2020cites this paper
• Brain–machine interfaces using functional near-infrared spectroscopy: a review

  2020cites this paper
• EEG-based classification of lower limb motor imagery with brain network analysis.

  2020cites this paper
• A hierarchical meta-model for multi-class mental task based brain-computer interfaces

  2020cites this paper
• Electro-Encephalography and Electro-Oculography in Aeronautics: A Review Over the Last Decade (2010–2020)

  2020influential citation
• FBCSP and Adaptive Boosting for Multiclass Motor Imagery BCI Data Classification: A Machine Learning Approach

  2020cites this paper
• A Robust Multi-Channel EEG Signals Preprocessing Method for Enhanced Upper Extremity Motor Imagery Decoding

  2020cites this paper
• Multiclass MI-Task Classification Using Logistic Regression and Filter Bank Common Spatial Patterns

  2020cites this paper
• Decoding spectro-temporal representation for motor imagery recognition using ECoG-based brain-computer interfaces.

  2020cites this paper
• Feature subset and time segment selection for the classification of EEG data based motor imagery

  2020cites this paper
• Improved motor imagery brain-computer interface performance via adaptive modulation filtering and two-stage classification

  2020cites this paper
• Subject-based dipole selection for decoding motor imagery tasks

  2020cites this paper
• Efficient Biosignal Processing Using Hyperdimensional Computing: Network Templates for Combined Learning and Classification of ExG Signals

  2019influential citation
• Classification of multiple motor imagery using deep convolutional neural networks and spatial filters

  2019cites this paper
• A novel method for classification of BCI multi-class motor imagery task based on Dempster-Shafer theory

  2019cites this paper
• Feature extraction of four-class motor imagery EEG signals based on functional brain network

  2019cites this paper
• Decoding of motor imagery EEG based on brain source estimation

  2019cites this paper
• Multi-class Classification of EEG Spectral Data for Artifact Detection

  2019cites this paper
• A novel hybrid deep learning scheme for four-class motor imagery classification

  2019cites this paper
• Second Order Difference Plot to Decode Multi-class Motor Imagery Activities

  2019cites this paper
• Motor Imagery Classification with Covariance Matrices and Non-Negative Matrix Factorization

  2019cites this paper
• Decoding Motor Imagery Movements using Area of 2-D Phase Space Reconstruction

  2019cites this paper
• G-Causality Brain Connectivity Differences of Finger Movements between Motor Execution and Motor Imagery

  2019cites this paper
• Independent Decision Path Fusion for Bimodal Asynchronous Brain–Computer Interface to Discriminate Multiclass Mental States

  2019cites this paper
• A Novel BCI System Based on Hybrid Features for Classifying Motor Imagery Tasks

  2019cites this paper
• The Analysis Of Motor Imagery And SSVEPs For the BCI Application

  2019cites this paper
• A Randomised Ensemble Learning Approach for Multiclass Motor Imagery Classification Using Error Correcting Output Coding

  2018cites this paper
• Classification of Motor Imagery Tasks in Source Domain

  2018cites this paper
• Effect of EOG Signal Filtering on the Removal of Ocular Artifacts and EEG-Based Brain-Computer Interface: A Comprehensive Study

  2018cites this paper
• Feature Extraction and Classification Methods for Hybrid fNIRS-EEG Brain-Computer Interfaces

  2018cites this paper
• Effect of Different Movement Speed Modes on Human Action Observation: An EEG Study

  2018cites this paper
• Automatic Change Detection for Real-Time Monitoring of EEG Signals

  2018cites this paper
• A COMPARATIVE STUDY OF FEATURES AND CLASSIFIERS IN SINGLE-CHANNEL EEG-BASED MOTOR IMAGERY BCI

  2018influential citation
• A pairwise output coding method for multi-class EEG classification of a self-induced BCI

  2018cites this paper
• Comparison of Machine Learning Approaches for Motor Imagery Based Optical Brain Computer Interface

  2018cites this paper
• A Deep Convolutional Neural Network Based Classification Of Multi-Class Motor Imagery With Improved Generalization

  2018cites this paper
• Multi-modal, Multi-measure, and Multi-class Discrimination of ADHD with Hierarchical Feature Extraction and Extreme Learning Machine Using Structural and Functional Brain MRI

  2017cites this paper
• PSO-based feature selection and neighborhood rough set-based classification for BCI multiclass motor imagery task

  2017cites this paper
• Application of Convolutional Neural Networks to Four-Class Motor Imagery Classification Problem

  2017cites this paper
• Assessing motor imagery in brain‐computer interface training: Psychological and neurophysiological correlates

  2017cites this paper
• Multi-Person Brain Activity Recognition via Comprehensive EEG Signal Analysis

  2017influential citation
• Performance Evaluation of Empirical Mode Decomposition Algorithms for Mental Task Classification

  2017cites this paper
• EEG classification for motor imagery BCI using phase-only features extracted by independent component analysis

  2017cites this paper
• Shrinkage estimator based common spatial pattern for multi-class motor imagery classification by hybrid classifier

  2017cites this paper
• EEG-based multi-class motor imagery classification using variable sized filter bank and enhanced One Versus One classifier

  2017cites this paper
• Feature Selection for Motor Imagery EEG Classification Based on Firefly Algorithm and Learning Automata

  2017cites this paper
• Closed-Loop Hybrid Gaze Brain-Machine Interface Based Robotic Arm Control with Augmented Reality Feedback

  2017cites this paper
• Stability study of the optimal channel selection for emotion classification from EEG

  2017cites this paper
• Reservoir computing approaches to EEG-based detection of microsleeps.

  2017cites this paper
• General Concepts on Electroencephalography-Based Brain-Computer Interface Systems: A Review

  2017cites this paper
• Hybrid Brain–Computer Interface Techniques for Improved Classification Accuracy and Increased Number of Commands: A Review

  2017cites this paper
• Multiclass Classification for the Differential Diagnosis on the ADHD Subtypes Using Recursive Feature Elimination and Hierarchical Extreme Learning Machine: Structural MRI Study

  2016cites this paper
• Assessment of feature selection and classification methods for recognizing motor imagery tasks from electroencephalographic signals

  2016cites this paper
• Electroencephalographic Motor Imagery Brain Connectivity Analysis for BCI: A Review

  2016cites this paper
• Poor BCI Performers Still Could Benefit from Motor Imagery Training

  2016cites this paper
• EEG Source Imaging Enhances the Decoding of Complex Right-Hand Motor Imagery Tasks

  2016cites this paper
• Three-Class EEG-Based Motor Imagery Classification Using Phase-Space Reconstruction Technique

  2016cites this paper
• Multiclass motor imagery classification for BCI application

  2016cites this paper
• Adaptive nonlinear multivariate brain connectivity analysis of motor imagery movements using graph theory

  2016cites this paper
• Assessing EEG neuroimaging with machine learning

  2016cites this paper
• fNIRS-based brain-computer interfaces: a review

  2015cites this paper
• Adaptive semi-supervised classification to reduce intersession non-stationarity in multiclass motor imagery-based brain-computer interfaces

  2015influential citation
• Evaluation of less Common Independent Component Analysis Algorithms for Brain Computer Interface Preprocessing

  2015cites this paper