Corpus ID: 38585021

Toward enhanced P 300 speller performance

@inproceedings{Krusienski2007TowardEP,
  title={Toward enhanced P 300 speller performance},
  author={D. J. Krusienski and E. W. Sellers and Dennis J. McFarland and Theresa M. Vaughan and Jonathan R. Wolpaw},
  year={2007}
}
This study examines the effects of expanding the classical P300 feature space on the classification performance of data collected from a P300 speller paradigm [Farwell LA, Donchin E. Talking off the top of your head: toward a mental prosthesis utilizing event-related brain potentials. Electroenceph Clin Neurophysiol 1988;70:510–23]. Using stepwise linear discriminant analysis (SWLDA) to construct a classifier, the effects of spatial channel selection, channel referencing, data decimation, and… Expand

Figures and Tables from this paper

A comparison of classification techniques for the P300 Speller.
TLDR
The results indicate that while all methods attained acceptable performance levels, SWLDA and FLD provide the best overall performance and implementation characteristics for practical classification of P300 Speller data. Expand
hannel selection methods for the P 300 Speller
The P300 Speller brain–computer interface (BCI) allows a user to communicate without muscle activity by reading electrical signals on the scalp via electroencephalogram. Modern BCI systems useExpand
Suppressing flashes of items surrounding targets during calibration of a P300-based brain-computer interface improves performance.
TLDR
The results of this research demonstrate that using suppression during calibration produces significantly more character selections/min than the standard checkerboard condition, and significantly fewer target flashes are needed per selection in the SUP condition as compared to the RCP condition. Expand
A principal component analysis ensemble classifier for P300 speller applications
TLDR
This work proposes an ensemble classifier that uses Principal Component Analysis (PCA) features to identify evoked P300 signals from EEG recordings to indicate a significant improvement in classification accuracy compared to traditional feature extraction and classification approaches. Expand
Channel selection methods for the P300 Speller
TLDR
Results are obtained demonstrating that active channel selection can improve speller accuracy for most users relative to a standard channel set, with particular benefit for users who experience low performance using the standard set. Expand
Non-target adjacent stimuli classification improves performance of classical ERP-based brain computer interface.
TLDR
This work promotes the searching of information on the peripheral stimulation responses to improve the performance of emerging visual ERP-based spellers by combining the classification of non-target adjacent stimuli with standard classification (target versus non- target). Expand
Concentration on performance with P300-based BCI systems: a matter of interface features.
TLDR
The performance of those users with lower concentration level can be improved by providing brain-computer interfaces with more interactive interfaces, and the impact of psychological features on BCI performance should be taken into account for future assistive technology systems. Expand
A hybrid BCI speller paradigm combining P300 potential and the SSVEP blocking feature.
TLDR
A novel hybrid BCI speller is developed to elicit P300 potential and SSVEP blocking (SSVEP-B) distinctly and simultaneously with the same target stimulus, indicating that the combination of P300 with an SSVEp-B improves target discrimination greatly and is superior to the control paradigm in spelling performance. Expand
A general P300 brain–computer interface presentation paradigm based on performance guided constraints
TLDR
A C(36,5) instance of C(m,n) called the "five flash paradigm" (FFP) is explored and compared to the CBP, which is a novel and effective general strategy for organizing stimulus groups. Expand
Motivation modulates the P300 amplitude during brain–computer interface use
TLDR
Motivation modulates the P300 amplitude in an ERP-BCI and may contribute to variance inBCI performance and should be monitored in BCI settings. Expand
...
1
2
3
4
5
...

References

SHOWING 1-10 OF 23 REFERENCES
Robust classification of EEG signal for brain-computer interface
TLDR
High accuracy, fast learning, and online performance make this P300 speller a potential communication tool for severely disabled individuals, who have lost all other means of communication and are otherwise cut off from the world, provided their disability does not interfere with the performance of the speller. Expand
An improved P300-based brain-computer interface
TLDR
The presented BCI achieves excellent performance compared to other existing BCIs, and allows a reasonable communication rate, while maintaining a low error rate. Expand
Spatiotemporal analysis of the late ERP responses to deviant stimuli.
We used a novel application of principal components analysis (spatiotemporal PCA) to decompose the event-related brain potentials (ERPs) obtained with a dense electrode array, with the purpose ofExpand
A P300-based brain–computer interface: Initial tests by ALS patients
TLDR
The results of offline classification suggest that a P300-based BCI can serve as a non-muscular communication device in both ALS, and non-ALS control groups. Expand
The mental prosthesis: assessing the speed of a P300-based brain-computer interface.
  • E. Donchin, K. Spencer, R. Wijesinghe
  • Computer Science, Medicine
  • IEEE transactions on rehabilitation engineering : a publication of the IEEE Engineering in Medicine and Biology Society
  • 2000
TLDR
The data indicate that a P300-based BCI is feasible and practical, however, these conclusions are based on tests using healthy individuals, which indicates that an off line version of the system can communicate at the rate of 7.8 characters a minute and achieve 80% accuracy. Expand
BCI competition 2003-data set IIb: support vector machines for the P300 speller paradigm
TLDR
An approach to analyze data from the P300 speller paradigm using the machine-learning technique support vector machines, which is fast, requires only 10 electrode positions and demands only a small amount of preprocessing. Expand
Support vector channel selection in BCI
TLDR
Recursive Feature Elimination and Zero-Norm Optimization which are based on the training of support vector machines (SVM) can provide more accurate solutions than standard filter methods for feature selection for EEG channels. Expand
Improving Transfer Rates in Brain Computer Interfacing: A Case Study
TLDR
The main objective was to improve the transfer rates based on offline analysis of EEG-data but within a more realistic setup closer to an online realization than in the original studies. Expand
Talking off the top of your head: toward a mental prosthesis utilizing event-related brain potentials.
TLDR
The analyses suggest that this communication channel can be operated accurately at the rate of 0.20 bits/sec, which means that subjects can communicate 12.0 bits, or 2.3 characters, per min. Expand
On the relationship between background EEG and the P300 event-related potential
TLDR
The results suggest that differences between individuals for EEG variation may contribute to P3 component variability, especially at the parietal recording site and under low target stimulus probability conditions when the P3 is largest and most stable. Expand
...
1
2
3
...