Limits...
Temporal and spatial features of single-trial EEG for brain-computer interface.

Zhao Q, Zhang L - Comput Intell Neurosci (2007)

Bottom Line: Computer simulations on real experimental data indicate that independent residual analysis (IRA) method can provide efficient temporal features.Combining IRA features with the CSP method, we obtain the optimal spatial and temporal features with which we achieve the best classification rate.The high classification rate indicates that the proposed method is promising for an EEG-based brain-computer interface.

View Article: PubMed Central - PubMed

Affiliation: Department of Computer Science and Engineering, Shanghai Jiao Tong University, Shanghai 200240, China. qbzhao@sjtu.edu.cn

ABSTRACT
Brain-computer interface (BCI) systems create a novel communication channel from the brain to an output device bypassing conventional motor output pathways of nerves and muscles. Modern BCI technology is essentially based on techniques for the classification of single-trial brain signals. With respect to the topographic patterns of brain rhythm modulations, the common spatial patterns (CSPs) algorithm has been proven to be very useful to produce subject-specific and discriminative spatial filters; but it didn't consider temporal structures of event-related potentials which may be very important for single-trial EEG classification. In this paper, we propose a new framework of feature extraction for classification of hand movement imagery EEG. Computer simulations on real experimental data indicate that independent residual analysis (IRA) method can provide efficient temporal features. Combining IRA features with the CSP method, we obtain the optimal spatial and temporal features with which we achieve the best classification rate. The high classification rate indicates that the proposed method is promising for an EEG-based brain-computer interface.

No MeSH data available.


Related in: MedlinePlus

Different temporal amplitude fluctuations and spatialdistribution during left- and right-hand movement imagery. (a) A series of 3Dscalp maps representing potential distributions at a selected series of timepoints during left-hand movement imagery. (b) A series of 3D scalp mapsrepresenting potential distributions at a selected series of time points duringright-hand movement imagery.
© Copyright Policy
Related In: Results  -  Collection

License
getmorefigures.php?uid=PMC2267213&req=5

fig3: Different temporal amplitude fluctuations and spatialdistribution during left- and right-hand movement imagery. (a) A series of 3Dscalp maps representing potential distributions at a selected series of timepoints during left-hand movement imagery. (b) A series of 3D scalp mapsrepresenting potential distributions at a selected series of time points duringright-hand movement imagery.

Mentions: Since a focal ERD can be observed over the motorand/or sensory cortex even when a subject is only imagining a movement orsensation in the specific limb, this feature can be used well for BCI control:the discrimination of the imagination of movements of left hand versus righthand can be based on the somatotopic arrangement of the attenuation of the μ- and/or β-rhythms.Figure 2 shows the average scalp spectra distribution of left hand versus righthand in one trial. The μ- and/or β-rhythmsappeared in both left- and right-hand trials, it is difficult to distinguishthem only from frequency spectra of single trial; but they have differentcharacteristics of temporal amplitude fluctuations and spatial distribution(see Figure 3). Therefore, more advanced feature extraction methods should bedeveloped to extract the low diversification of ERD. The CSP algorithm is aneffective way to improve the classification performance. There still existsanother type of features different from the ERD reflecting imagined or intendedmovements, the movement-related potentials (MRP), denoting a negative DC shiftof the EEG signals in the respective cortical regions. This combinationstrategy utilizes both temporal and spatial characteristics of EEG data and isable to greatly enhance classification performance in offline studies. In thispaper, we focus only on improving the ERD-based classification.


Temporal and spatial features of single-trial EEG for brain-computer interface.

Zhao Q, Zhang L - Comput Intell Neurosci (2007)

Different temporal amplitude fluctuations and spatialdistribution during left- and right-hand movement imagery. (a) A series of 3Dscalp maps representing potential distributions at a selected series of timepoints during left-hand movement imagery. (b) A series of 3D scalp mapsrepresenting potential distributions at a selected series of time points duringright-hand movement imagery.
© Copyright Policy
Related In: Results  -  Collection

License
Show All Figures
getmorefigures.php?uid=PMC2267213&req=5

fig3: Different temporal amplitude fluctuations and spatialdistribution during left- and right-hand movement imagery. (a) A series of 3Dscalp maps representing potential distributions at a selected series of timepoints during left-hand movement imagery. (b) A series of 3D scalp mapsrepresenting potential distributions at a selected series of time points duringright-hand movement imagery.
Mentions: Since a focal ERD can be observed over the motorand/or sensory cortex even when a subject is only imagining a movement orsensation in the specific limb, this feature can be used well for BCI control:the discrimination of the imagination of movements of left hand versus righthand can be based on the somatotopic arrangement of the attenuation of the μ- and/or β-rhythms.Figure 2 shows the average scalp spectra distribution of left hand versus righthand in one trial. The μ- and/or β-rhythmsappeared in both left- and right-hand trials, it is difficult to distinguishthem only from frequency spectra of single trial; but they have differentcharacteristics of temporal amplitude fluctuations and spatial distribution(see Figure 3). Therefore, more advanced feature extraction methods should bedeveloped to extract the low diversification of ERD. The CSP algorithm is aneffective way to improve the classification performance. There still existsanother type of features different from the ERD reflecting imagined or intendedmovements, the movement-related potentials (MRP), denoting a negative DC shiftof the EEG signals in the respective cortical regions. This combinationstrategy utilizes both temporal and spatial characteristics of EEG data and isable to greatly enhance classification performance in offline studies. In thispaper, we focus only on improving the ERD-based classification.

Bottom Line: Computer simulations on real experimental data indicate that independent residual analysis (IRA) method can provide efficient temporal features.Combining IRA features with the CSP method, we obtain the optimal spatial and temporal features with which we achieve the best classification rate.The high classification rate indicates that the proposed method is promising for an EEG-based brain-computer interface.

View Article: PubMed Central - PubMed

Affiliation: Department of Computer Science and Engineering, Shanghai Jiao Tong University, Shanghai 200240, China. qbzhao@sjtu.edu.cn

ABSTRACT
Brain-computer interface (BCI) systems create a novel communication channel from the brain to an output device bypassing conventional motor output pathways of nerves and muscles. Modern BCI technology is essentially based on techniques for the classification of single-trial brain signals. With respect to the topographic patterns of brain rhythm modulations, the common spatial patterns (CSPs) algorithm has been proven to be very useful to produce subject-specific and discriminative spatial filters; but it didn't consider temporal structures of event-related potentials which may be very important for single-trial EEG classification. In this paper, we propose a new framework of feature extraction for classification of hand movement imagery EEG. Computer simulations on real experimental data indicate that independent residual analysis (IRA) method can provide efficient temporal features. Combining IRA features with the CSP method, we obtain the optimal spatial and temporal features with which we achieve the best classification rate. The high classification rate indicates that the proposed method is promising for an EEG-based brain-computer interface.

No MeSH data available.


Related in: MedlinePlus