Limits...
Enhanced detection of visual-evoked potentials in brain-computer interface using genetic algorithm and cyclostationary analysis.

Gupta CN, Palaniappan R - Comput Intell Neurosci (2007)

Bottom Line: Next, bandpass or lowpass filtering is performed to reduce the EEG artifacts using these identified frequency ranges.The CS and GA methods need to be applied only to the training data; for the test data, the knowledge of the cyclic frequency bands and unmixing matrix would be sufficient for enhanced VEP detection.Hence, the framework could be used for online VEP detection.

View Article: PubMed Central - PubMed

Affiliation: Department of Computing and Electronic Systems, University of Essex, Wivenhoe Park, Colchester CO4 3SQ, UK.

ABSTRACT
We propose a novel framework to reduce background electroencephalogram (EEG) artifacts from multitrial visual-evoked potentials (VEPs) signals for use in brain-computer interface (BCI) design. An algorithm based on cyclostationary (CS) analysis is introduced to locate the suitable frequency ranges that contain the stimulus-related VEP components. CS technique does not require VEP recordings to be phase locked and exploits the intertrial similarities of the VEP components in the frequency domain. The obtained cyclic frequency spectrum enables detection of VEP frequency band. Next, bandpass or lowpass filtering is performed to reduce the EEG artifacts using these identified frequency ranges. This is followed by overlapping band EEG artifact reduction using genetic algorithm and independent component analysis (G-ICA) which uses mutual information (MI) criterion to separate EEG artifacts from VEP. The CS and GA methods need to be applied only to the training data; for the test data, the knowledge of the cyclic frequency bands and unmixing matrix would be sufficient for enhanced VEP detection. Hence, the framework could be used for online VEP detection. This framework was tested with various datasets and it showed satisfactory results with very few trials. Since the framework is general, it could be applied to the enhancement of evoked potential signals for any application.

No MeSH data available.


Five-trialscyclic spectrum for target RCIA.
© Copyright Policy
Related In: Results  -  Collection

License
getmorefigures.php?uid=PMC2266790&req=5

fig8: Five-trialscyclic spectrum for target RCIA.

Mentions: This dataset allowed a subject to communicate one ofthe 36 symbols presented on a 6 × 6 matrix. Thedataset had specifications of 36 classes, 64 EEG channels (0.1–60 Hz), 240 Hzsampling rate, 85 training, and 100 test trials, recorded with the BCI2000system. It followed the standard procedure developed by Farwell and Donchin forP300-based BCIs. The method assumes that the EEG epoch associated with therelevant column and the relevant row will contain a detectable P300 for asingle intensification, while the other epochs will not. The data presented toour framework were obtained by averaging together each combination of row andcolumn single-trial epochs. Thus, there were 6 rows by 6 columns = 36 row-columnintersection average (RCIA). The relationship between the number of trialsrequired and the speed of communication is direct. If detection could beachieved using just less trials, the system would allow communication at abetter rate. We tested the framework using only 5 trials from channel Cz todetect “I” which is the chosen target character in the above chosen dataset.With respect to the target character “I” detection, we discuss the proposedframework's performance diagrammatically below. Figures 6and 9show theconcatenated trials (target and nontarget RCIA) used for cyclostationaryanalysis while Figures 7–8and 10–11show their corresponding cyclic spectrumsfor varying number of trials.


Enhanced detection of visual-evoked potentials in brain-computer interface using genetic algorithm and cyclostationary analysis.

Gupta CN, Palaniappan R - Comput Intell Neurosci (2007)

Five-trialscyclic spectrum for target RCIA.
© Copyright Policy
Related In: Results  -  Collection

License
Show All Figures
getmorefigures.php?uid=PMC2266790&req=5

fig8: Five-trialscyclic spectrum for target RCIA.
Mentions: This dataset allowed a subject to communicate one ofthe 36 symbols presented on a 6 × 6 matrix. Thedataset had specifications of 36 classes, 64 EEG channels (0.1–60 Hz), 240 Hzsampling rate, 85 training, and 100 test trials, recorded with the BCI2000system. It followed the standard procedure developed by Farwell and Donchin forP300-based BCIs. The method assumes that the EEG epoch associated with therelevant column and the relevant row will contain a detectable P300 for asingle intensification, while the other epochs will not. The data presented toour framework were obtained by averaging together each combination of row andcolumn single-trial epochs. Thus, there were 6 rows by 6 columns = 36 row-columnintersection average (RCIA). The relationship between the number of trialsrequired and the speed of communication is direct. If detection could beachieved using just less trials, the system would allow communication at abetter rate. We tested the framework using only 5 trials from channel Cz todetect “I” which is the chosen target character in the above chosen dataset.With respect to the target character “I” detection, we discuss the proposedframework's performance diagrammatically below. Figures 6and 9show theconcatenated trials (target and nontarget RCIA) used for cyclostationaryanalysis while Figures 7–8and 10–11show their corresponding cyclic spectrumsfor varying number of trials.

Bottom Line: Next, bandpass or lowpass filtering is performed to reduce the EEG artifacts using these identified frequency ranges.The CS and GA methods need to be applied only to the training data; for the test data, the knowledge of the cyclic frequency bands and unmixing matrix would be sufficient for enhanced VEP detection.Hence, the framework could be used for online VEP detection.

View Article: PubMed Central - PubMed

Affiliation: Department of Computing and Electronic Systems, University of Essex, Wivenhoe Park, Colchester CO4 3SQ, UK.

ABSTRACT
We propose a novel framework to reduce background electroencephalogram (EEG) artifacts from multitrial visual-evoked potentials (VEPs) signals for use in brain-computer interface (BCI) design. An algorithm based on cyclostationary (CS) analysis is introduced to locate the suitable frequency ranges that contain the stimulus-related VEP components. CS technique does not require VEP recordings to be phase locked and exploits the intertrial similarities of the VEP components in the frequency domain. The obtained cyclic frequency spectrum enables detection of VEP frequency band. Next, bandpass or lowpass filtering is performed to reduce the EEG artifacts using these identified frequency ranges. This is followed by overlapping band EEG artifact reduction using genetic algorithm and independent component analysis (G-ICA) which uses mutual information (MI) criterion to separate EEG artifacts from VEP. The CS and GA methods need to be applied only to the training data; for the test data, the knowledge of the cyclic frequency bands and unmixing matrix would be sufficient for enhanced VEP detection. Hence, the framework could be used for online VEP detection. This framework was tested with various datasets and it showed satisfactory results with very few trials. Since the framework is general, it could be applied to the enhancement of evoked potential signals for any application.

No MeSH data available.