Limits...
Selective sensation based brain-computer interface via mechanical vibrotactile stimulation.

Yao L, Meng J, Zhang D, Sheng X, Zhu X - PLoS ONE (2013)

Bottom Line: The proposed system was based on event-related desynchronization/synchronization (ERD/ERS), which had a correlation with processing of afferent inflow in human somatosensory system, and attentional effect which modulated the ERD/ERS.The experiments were carried out on nine subjects (without experience in selective sensation), and six of them showed a discrimination accuracy above 80%, three of them above 95%.The proposed BCI modality might well cooperate with existing BCI modalities in the literature in enlarging the widespread usage of BCI system.

View Article: PubMed Central - PubMed

Affiliation: State Key Laboratory of Mechanical System and Vibration, Shanghai Jiao Tong University, Shanghai, China.

ABSTRACT
In this work, mechanical vibrotactile stimulation was applied to subjects' left and right wrist skins with equal intensity, and a selective sensation perception task was performed to achieve two types of selections similar to motor imagery Brain-Computer Interface. The proposed system was based on event-related desynchronization/synchronization (ERD/ERS), which had a correlation with processing of afferent inflow in human somatosensory system, and attentional effect which modulated the ERD/ERS. The experiments were carried out on nine subjects (without experience in selective sensation), and six of them showed a discrimination accuracy above 80%, three of them above 95%. Comparative experiments with motor imagery (with and without presence of stimulation) were also carried out, which further showed the feasibility of selective sensation as an alternative BCI task complementary to motor imagery. Specifically there was significant improvement ([Formula: see text]) from near 65% in motor imagery (with and without presence of stimulation) to above 80% in selective sensation on some subjects. The proposed BCI modality might well cooperate with existing BCI modalities in the literature in enlarging the widespread usage of BCI system.

Show MeSH
Comparison of baseline discrimination and taskline discrimination in sensation session.Baseline indicated the time from the 1st second to the 3rd second from the start of the trial(2 to 0 second before stimulus of the cue), Taskline indicated the time interval from the 4th second to the 7th second from the start of the trial(1 to 4 second post stimulus of the cue).
© Copyright Policy
Related In: Results  -  Collection


getmorefigures.php?uid=PMC3675213&req=5

pone-0064784-g004: Comparison of baseline discrimination and taskline discrimination in sensation session.Baseline indicated the time from the 1st second to the 3rd second from the start of the trial(2 to 0 second before stimulus of the cue), Taskline indicated the time interval from the 4th second to the 7th second from the start of the trial(1 to 4 second post stimulus of the cue).

Mentions: The time interval for on-line and off-line analysis of discrimination between left and right motor imagery or left and right stimulation selective sensation was chosen from the 4th second to the 7th second at the beginning of the trial(1 to 4 second post to the stimulus of the cue), and the frequency band was chosen to cover the alpha and beta band of 8 Hz to 26 Hz, using 4th-order butterworth filter. The processing procedure was the same for both motor imagery task and sensation task. A fold cross validation was adopted to evaluate the classification accuracy between left and right. It worked as follows: first randomly permutated the trials gathered in one session(160 left and right trials in our experiments), then equally divided into five partitions, every partition was used as an unknown test set which was classified by the classifier trained using the remaining four partitions, resulting a classification accuracy for each of the partition. Finally this process was repeated five times, generating 25 classification accuracies for statistical evaluation of the discrimination of the mental tasks. In convince of the discrimination between left and right selective sensation, baseline EEG of 2s before the indicating cue was extracted and evaluated in the same procedure, as shown in Fig. 4. Baseline activity showed no discriminative information of random chance level between the two classes, while taskline activity involved with subject’s mental task exhibited significant discrimination difference from the baseline with . Clearly, during the base-line period the subject performed nothing but waited for the indicating cue, so the EEG signals showed plain discriminative information. During the taskline period, six of them achieved a classification accuracy above 80%, and three of the six above 95%, while other three showed less discriminative information of about 60%. Fig. 5 showed the on-line classification of each subject across the run 2 to run 4(run 1 was used for establishing the classifier), and subjects s1, s2, s8 showed a stable performance.


Selective sensation based brain-computer interface via mechanical vibrotactile stimulation.

Yao L, Meng J, Zhang D, Sheng X, Zhu X - PLoS ONE (2013)

Comparison of baseline discrimination and taskline discrimination in sensation session.Baseline indicated the time from the 1st second to the 3rd second from the start of the trial(2 to 0 second before stimulus of the cue), Taskline indicated the time interval from the 4th second to the 7th second from the start of the trial(1 to 4 second post stimulus of the cue).
© Copyright Policy
Related In: Results  -  Collection

Show All Figures
getmorefigures.php?uid=PMC3675213&req=5

pone-0064784-g004: Comparison of baseline discrimination and taskline discrimination in sensation session.Baseline indicated the time from the 1st second to the 3rd second from the start of the trial(2 to 0 second before stimulus of the cue), Taskline indicated the time interval from the 4th second to the 7th second from the start of the trial(1 to 4 second post stimulus of the cue).
Mentions: The time interval for on-line and off-line analysis of discrimination between left and right motor imagery or left and right stimulation selective sensation was chosen from the 4th second to the 7th second at the beginning of the trial(1 to 4 second post to the stimulus of the cue), and the frequency band was chosen to cover the alpha and beta band of 8 Hz to 26 Hz, using 4th-order butterworth filter. The processing procedure was the same for both motor imagery task and sensation task. A fold cross validation was adopted to evaluate the classification accuracy between left and right. It worked as follows: first randomly permutated the trials gathered in one session(160 left and right trials in our experiments), then equally divided into five partitions, every partition was used as an unknown test set which was classified by the classifier trained using the remaining four partitions, resulting a classification accuracy for each of the partition. Finally this process was repeated five times, generating 25 classification accuracies for statistical evaluation of the discrimination of the mental tasks. In convince of the discrimination between left and right selective sensation, baseline EEG of 2s before the indicating cue was extracted and evaluated in the same procedure, as shown in Fig. 4. Baseline activity showed no discriminative information of random chance level between the two classes, while taskline activity involved with subject’s mental task exhibited significant discrimination difference from the baseline with . Clearly, during the base-line period the subject performed nothing but waited for the indicating cue, so the EEG signals showed plain discriminative information. During the taskline period, six of them achieved a classification accuracy above 80%, and three of the six above 95%, while other three showed less discriminative information of about 60%. Fig. 5 showed the on-line classification of each subject across the run 2 to run 4(run 1 was used for establishing the classifier), and subjects s1, s2, s8 showed a stable performance.

Bottom Line: The proposed system was based on event-related desynchronization/synchronization (ERD/ERS), which had a correlation with processing of afferent inflow in human somatosensory system, and attentional effect which modulated the ERD/ERS.The experiments were carried out on nine subjects (without experience in selective sensation), and six of them showed a discrimination accuracy above 80%, three of them above 95%.The proposed BCI modality might well cooperate with existing BCI modalities in the literature in enlarging the widespread usage of BCI system.

View Article: PubMed Central - PubMed

Affiliation: State Key Laboratory of Mechanical System and Vibration, Shanghai Jiao Tong University, Shanghai, China.

ABSTRACT
In this work, mechanical vibrotactile stimulation was applied to subjects' left and right wrist skins with equal intensity, and a selective sensation perception task was performed to achieve two types of selections similar to motor imagery Brain-Computer Interface. The proposed system was based on event-related desynchronization/synchronization (ERD/ERS), which had a correlation with processing of afferent inflow in human somatosensory system, and attentional effect which modulated the ERD/ERS. The experiments were carried out on nine subjects (without experience in selective sensation), and six of them showed a discrimination accuracy above 80%, three of them above 95%. Comparative experiments with motor imagery (with and without presence of stimulation) were also carried out, which further showed the feasibility of selective sensation as an alternative BCI task complementary to motor imagery. Specifically there was significant improvement ([Formula: see text]) from near 65% in motor imagery (with and without presence of stimulation) to above 80% in selective sensation on some subjects. The proposed BCI modality might well cooperate with existing BCI modalities in the literature in enlarging the widespread usage of BCI system.

Show MeSH