Analysis of nonstationarities in EEG signals for improving brain-computer interface performance

@inproceedings{Krauledat2008AnalysisON,
  title={Analysis of nonstationarities in EEG signals for improving brain-computer interface performance},
  author={Matthias Krauledat},
  year={2008}
}
Brain-Computer Interface (BCI) research aims at the automatic translation o f neural commands into control signals. These can then be used to control applications s uch a text input programs, electrical wheelchairs or neuroprostheses. A BCI sy stem can, e.g., serve as a communication option for severely disabled patients or as an additional man-ma chine interaction channel for healthy users. In the classical “operant cond iti ing” approach, subjects had to undergo weeks or months of training to… 
Efficient EEG frequency band selection techniques for a robust motor imagery based brain-computer interface.
TLDR
Techniques towards a robust motor imagery based BCI by selecting the relevant frequency components carrying the discriminative information are proposed.
Improving Brain–Computer Interfaces Using Independent Component Analysis
TLDR
This chapter presents an up-to-date literature review on the applications of ICA in EEG-based BCIs and reports recent progress on an ICA-based zero-training BCI which aims to facilitate user training for a motor imagery BCI.
Machine-Learning-Based Coadaptive Calibration for Brain-Computer Interfaces
TLDR
Adaptive machine learning methods to eliminate offline calibration are investigated, the performance of 11 volunteers in a BCI based on the modulation of sensorimotor rhythms is analyzed, and an adaptation scheme that individually guides the user is presented.
Variability and Nonstationarity in Brain Computer Interfaces
TLDR
This research conducted an EEG imagined movement experiment with 8 participants taking part in two sessions, and participants received two types of feedback, namely continuous during movement imagination, or once immediately after movement imagination.
Machine-Learning Based Co-adaptive Calibration : Towards a Cure for BCI illiteracy
Brain-Computer Interfaces (BCIs) allow users to control a computer application by brain activity as acquired, e.g., by EEG. In our classic Machine Learning approach to BCIs, the participants
EEG Data Space Adaptation to Reduce Intersession Nonstationarity in Brain-Computer Interface
TLDR
A novel data space adaptation technique to linearly transform the EEG data from the target space (evaluation session) such that the distribution difference to the source space (training session) is minimized, and the results show that the proposed EEG-DSA algorithm in both the supervised and unsupervised versions significantly outperforms the results without adaptation.
Neural Network-Based Feature Extraction for Multi-Class Motor Imagery Classification
TLDR
An innovative idea of transforming an EEG signal into the weight vector of an unsupervised neural network called the autoencoder is proposed for the first time to solve the main issue in developing the EEG based BCI.
Stationary common spatial patterns for brain-computer interfacing.
TLDR
A method which regularizes CSP towards stationary subspaces (sCSP) is proposed and it is shown that this increases classification accuracy, especially for subjects who are hardly able to control a BCI.
Transferring Subspaces Between Subjects in Brain--Computer Interfacing
TLDR
This novel approach to learning from other subjects aims to reduce the adverse effects of common nonstationarities, but does not transfer discriminative information, and can not only achieve a significant increase in performance but also allow for a neurophysiologically meaningful interpretation.
BCI Channel Selection in Chronic Stroke Rehabilitation
TLDR
A 20-session dataset of 5 chronic stroke patients who have undergone BCI -functional electrical stimulation training was used to investigate the optimal configuration of channel selection in chronic stroke and a performance index has been proposed to provide a common ground of comparison between different configurations.
...
...

References

SHOWING 1-10 OF 220 REFERENCES
The Berlin Brain-Computer Interface: Report from the Feedback Sessions
TLDR
The Berlin Brain-Computer Interface (BBCI) uses well established motor competences in control paradigms and a machine learning approach to extract subject-specific discriminability from high-dimensional features and its adaptivity which respects the enormous inter-subject variability.
The Berlin brain-computer interface: EEG-based communication without subject training
TLDR
Experiments demonstrate that very high information transfer rates can be achieved using the readiness potential when predicting the laterality of upcoming left- versus right-hand movements in healthy subjects, and are encouraging for an EEG-based BCI system in untrained subjects that is independent of peripheral nervous system activity.
Online Control of a Brain-Computer Interface Using Phase Synchronization
TLDR
This paper investigates one method to extract the degree of phase synchronization between two electroencephalogram (EEG) signals by calculating the so-called phase locking value (PLV), and reveals that all subjects were able to control three mental states.
Combining Features for BCI
TLDR
The hypothesis that MRP and ERD reflect at least partially independent aspects of cortical processes and open a new perspective to boost BCI effectiveness is strengthened.
Improving speed and accuracy of brain-computer interfaces using readiness potential features
TLDR
Two directions in which brain-computer interfacing can be enhanced by exploiting the lateralized readiness potential are presented: for establishing a rapid response BCI system that can predict the laterality of upcoming finger movements before EMG onset even in time critical contexts, and to improve information transfer rates in the common BCI approach relying on imagined limb movements.
The Berlin Brain-Computer Interface: Machine Learning Based Detection of User Specific Brain States
TLDR
Results of a recent feedback study with six healthy subjects with no or very little experience with BCI control are encouraging for an EEG-based BCI system in untrained subjects that is independent of peripheral nervous system activity and does not rely on evoked potentials.
The BCI competition 2003: progress and perspectives in detection and discrimination of EEG single trials
TLDR
The BCI Competition 2003 was organized to evaluate the current state of the art of signal processing and classification methods and the results and function of the most successful algorithms were described.
The Berlin Brain-Computer Interface: Accurate performance from first-session in BCI-naive subjects
TLDR
It is demonstrated in a group of 14 fully BCI-naive subjects that 8 out of 14 BCI novices can perform at >84% accuracy in their very first BCI session, and a further four subjects at >70%.
Classifying Single Trial EEG: Towards Brain Computer Interfacing
TLDR
This work detects upcoming finger movements in a natural keyboard typing condition and predicts their laterality in a pseudo-online simulation, and compares discriminative classifiers like Support Vector Machines (SVMs) and different variants of Fisher Discriminant that possess favorable regularization properties for dealing with high noise cases.
Adaptation in Brain-Computer Interfaces
TLDR
This chapter investigates the effect of adaptation on the performance of the classifier embedded in three different BCI systems, all of them based on non-invasive electroencephalogram (EEG) signals.
...
...