Limits...
A collaborative brain-computer interface for improving human performance.

Wang Y, Jung TP - PLoS ONE (2011)

Bottom Line: In a demonstration system using the Voting method, the classification accuracy of predicting movement directions (reaching left vs. reaching right) was enhanced substantially from 66% to 80%, 88%, 93%, and 95% as the numbers of subjects increased from 1 to 5, 10, 15, and 20, respectively.Furthermore, the decision of reaching direction could be made around 100-250 ms earlier than the subject's actual motor response by decoding the ERP activities arising mainly from the posterior parietal cortex (PPC), which are related to the processing of visuomotor transmission.Taken together, these results suggest that a collaborative BCI can effectively fuse brain activities of a group of people to improve the overall performance of natural human behavior.

View Article: PubMed Central - PubMed

Affiliation: Swartz Center for Computational Neuroscience, Institute for Neural Computation, University of California San Diego, San Diego, California, United States of America. yijun@sccn.ucsd.edu

ABSTRACT
Electroencephalogram (EEG) based brain-computer interfaces (BCI) have been studied since the 1970s. Currently, the main focus of BCI research lies on the clinical use, which aims to provide a new communication channel to patients with motor disabilities to improve their quality of life. However, the BCI technology can also be used to improve human performance for normal healthy users. Although this application has been proposed for a long time, little progress has been made in real-world practices due to technical limits of EEG. To overcome the bottleneck of low single-user BCI performance, this study proposes a collaborative paradigm to improve overall BCI performance by integrating information from multiple users. To test the feasibility of a collaborative BCI, this study quantitatively compares the classification accuracies of collaborative and single-user BCI applied to the EEG data collected from 20 subjects in a movement-planning experiment. This study also explores three different methods for fusing and analyzing EEG data from multiple subjects: (1) Event-related potentials (ERP) averaging, (2) Feature concatenating, and (3) Voting. In a demonstration system using the Voting method, the classification accuracy of predicting movement directions (reaching left vs. reaching right) was enhanced substantially from 66% to 80%, 88%, 93%, and 95% as the numbers of subjects increased from 1 to 5, 10, 15, and 20, respectively. Furthermore, the decision of reaching direction could be made around 100-250 ms earlier than the subject's actual motor response by decoding the ERP activities arising mainly from the posterior parietal cortex (PPC), which are related to the processing of visuomotor transmission. Taken together, these results suggest that a collaborative BCI can effectively fuse brain activities of a group of people to improve the overall performance of natural human behavior.

Show MeSH

Related in: MedlinePlus

Scalp maps and temporal waveforms of ERP signals.(A) Grand average 128-channel scalp maps of ERPs and difference waves (left-right) across all subjects at 210 ms and 320 ms. Black dots indicate positions of two selected electrodes near the PPC. (B) Average ERP waveforms across all subjects on two PPC electrodes in left- and right-reaching conditions and their difference. Dash lines mark peaks of difference waves at 210 ms and 320 ms. ERPs at two PPC electrodes show significant differences between left and right conditions using a paired t-test across subjects (left PPC: p<10−5 at 210 ms and p<10−6 at 320 ms, right PPC: p<10−6 at 210 ms and p<10−4 at 320 ms). The shaded intervals indicate areas where differences between left and right conditions are significant (p<0.05).
© Copyright Policy
Related In: Results  -  Collection


getmorefigures.php?uid=PMC3105048&req=5

pone-0020422-g005: Scalp maps and temporal waveforms of ERP signals.(A) Grand average 128-channel scalp maps of ERPs and difference waves (left-right) across all subjects at 210 ms and 320 ms. Black dots indicate positions of two selected electrodes near the PPC. (B) Average ERP waveforms across all subjects on two PPC electrodes in left- and right-reaching conditions and their difference. Dash lines mark peaks of difference waves at 210 ms and 320 ms. ERPs at two PPC electrodes show significant differences between left and right conditions using a paired t-test across subjects (left PPC: p<10−5 at 210 ms and p<10−6 at 320 ms, right PPC: p<10−6 at 210 ms and p<10−4 at 320 ms). The shaded intervals indicate areas where differences between left and right conditions are significant (p<0.05).

Mentions: We used independent component analysis (ICA) as an unsupervised spatial filtering technique to remove artifacts arising from eye and muscle movements. For each subject, all trials were band-pass filtered (1–30 Hz), concatenated, and then decomposed using the EEGLAB toolbox [30]. To retain the low-frequency EEG activities, ICA weights of the decomposition were applied to original unfiltered data before artifact removal. To extract the direction-specific activity of the ERPs, we compared the spatiotemporal patterns of EEG corresponding to different movement directions. As shown in Figure 5, we found a hemispheric asymmetry over the parietal cortex during the delay period (0–700 ms) in which motor planning can be presumed to have continued until the cued movement onset (appeared after 700 ms). Two lateral electrodes representing PPC activities showed a significant contralateral negativity and ipsilateral positivity with respect to the intended movement direction (Figure 5b). Across all subjects, difference waves between reaching left and reaching right conditions showed two peaks located at 210 ms and 320 ms after the direction cue. ERP scalp maps of two conditions and their difference at these two selected frames were illustrated in Figure 5a.


A collaborative brain-computer interface for improving human performance.

Wang Y, Jung TP - PLoS ONE (2011)

Scalp maps and temporal waveforms of ERP signals.(A) Grand average 128-channel scalp maps of ERPs and difference waves (left-right) across all subjects at 210 ms and 320 ms. Black dots indicate positions of two selected electrodes near the PPC. (B) Average ERP waveforms across all subjects on two PPC electrodes in left- and right-reaching conditions and their difference. Dash lines mark peaks of difference waves at 210 ms and 320 ms. ERPs at two PPC electrodes show significant differences between left and right conditions using a paired t-test across subjects (left PPC: p<10−5 at 210 ms and p<10−6 at 320 ms, right PPC: p<10−6 at 210 ms and p<10−4 at 320 ms). The shaded intervals indicate areas where differences between left and right conditions are significant (p<0.05).
© Copyright Policy
Related In: Results  -  Collection

Show All Figures
getmorefigures.php?uid=PMC3105048&req=5

pone-0020422-g005: Scalp maps and temporal waveforms of ERP signals.(A) Grand average 128-channel scalp maps of ERPs and difference waves (left-right) across all subjects at 210 ms and 320 ms. Black dots indicate positions of two selected electrodes near the PPC. (B) Average ERP waveforms across all subjects on two PPC electrodes in left- and right-reaching conditions and their difference. Dash lines mark peaks of difference waves at 210 ms and 320 ms. ERPs at two PPC electrodes show significant differences between left and right conditions using a paired t-test across subjects (left PPC: p<10−5 at 210 ms and p<10−6 at 320 ms, right PPC: p<10−6 at 210 ms and p<10−4 at 320 ms). The shaded intervals indicate areas where differences between left and right conditions are significant (p<0.05).
Mentions: We used independent component analysis (ICA) as an unsupervised spatial filtering technique to remove artifacts arising from eye and muscle movements. For each subject, all trials were band-pass filtered (1–30 Hz), concatenated, and then decomposed using the EEGLAB toolbox [30]. To retain the low-frequency EEG activities, ICA weights of the decomposition were applied to original unfiltered data before artifact removal. To extract the direction-specific activity of the ERPs, we compared the spatiotemporal patterns of EEG corresponding to different movement directions. As shown in Figure 5, we found a hemispheric asymmetry over the parietal cortex during the delay period (0–700 ms) in which motor planning can be presumed to have continued until the cued movement onset (appeared after 700 ms). Two lateral electrodes representing PPC activities showed a significant contralateral negativity and ipsilateral positivity with respect to the intended movement direction (Figure 5b). Across all subjects, difference waves between reaching left and reaching right conditions showed two peaks located at 210 ms and 320 ms after the direction cue. ERP scalp maps of two conditions and their difference at these two selected frames were illustrated in Figure 5a.

Bottom Line: In a demonstration system using the Voting method, the classification accuracy of predicting movement directions (reaching left vs. reaching right) was enhanced substantially from 66% to 80%, 88%, 93%, and 95% as the numbers of subjects increased from 1 to 5, 10, 15, and 20, respectively.Furthermore, the decision of reaching direction could be made around 100-250 ms earlier than the subject's actual motor response by decoding the ERP activities arising mainly from the posterior parietal cortex (PPC), which are related to the processing of visuomotor transmission.Taken together, these results suggest that a collaborative BCI can effectively fuse brain activities of a group of people to improve the overall performance of natural human behavior.

View Article: PubMed Central - PubMed

Affiliation: Swartz Center for Computational Neuroscience, Institute for Neural Computation, University of California San Diego, San Diego, California, United States of America. yijun@sccn.ucsd.edu

ABSTRACT
Electroencephalogram (EEG) based brain-computer interfaces (BCI) have been studied since the 1970s. Currently, the main focus of BCI research lies on the clinical use, which aims to provide a new communication channel to patients with motor disabilities to improve their quality of life. However, the BCI technology can also be used to improve human performance for normal healthy users. Although this application has been proposed for a long time, little progress has been made in real-world practices due to technical limits of EEG. To overcome the bottleneck of low single-user BCI performance, this study proposes a collaborative paradigm to improve overall BCI performance by integrating information from multiple users. To test the feasibility of a collaborative BCI, this study quantitatively compares the classification accuracies of collaborative and single-user BCI applied to the EEG data collected from 20 subjects in a movement-planning experiment. This study also explores three different methods for fusing and analyzing EEG data from multiple subjects: (1) Event-related potentials (ERP) averaging, (2) Feature concatenating, and (3) Voting. In a demonstration system using the Voting method, the classification accuracy of predicting movement directions (reaching left vs. reaching right) was enhanced substantially from 66% to 80%, 88%, 93%, and 95% as the numbers of subjects increased from 1 to 5, 10, 15, and 20, respectively. Furthermore, the decision of reaching direction could be made around 100-250 ms earlier than the subject's actual motor response by decoding the ERP activities arising mainly from the posterior parietal cortex (PPC), which are related to the processing of visuomotor transmission. Taken together, these results suggest that a collaborative BCI can effectively fuse brain activities of a group of people to improve the overall performance of natural human behavior.

Show MeSH
Related in: MedlinePlus