Limits...
Non-motor tasks improve adaptive brain-computer interface performance in users with severe motor impairment.

Faller J, Scherer R, Friedrich EV, Costa U, Opisso E, Medina J, Müller-Putz GR - Front Neurosci (2014)

Bottom Line: Auto-calibrating and adaptive ERD-based BCIs that users control with motor imagery tasks ("SMR-AdBCI") have proven effective for healthy users.We then simulated both, the SMR-AdBCI and the Auto-AdBCI configuration on the unseen data from the nine participants in Session 2 and compared the results.On the unseen data of Session 2 from individuals with SCI or stroke, we found that automatically selecting a user specific class-combination from motor-related and non motor-related mental tasks during initial auto-calibration (Auto-AdBCI) significantly (p < 0.01) improved classification performance compared to an adaptive ERD-based BCI that only used motor imagery tasks (SMR-AdBCI; average accuracy of 75.7 vs. 66.3%).

View Article: PubMed Central - PubMed

Affiliation: Laboratory of Brain-Computer Interfaces, Institute for Knowledge Discovery, Graz University of Technology Graz, Austria.

ABSTRACT
Individuals with severe motor impairment can use event-related desynchronization (ERD) based BCIs as assistive technology. Auto-calibrating and adaptive ERD-based BCIs that users control with motor imagery tasks ("SMR-AdBCI") have proven effective for healthy users. We aim to find an improved configuration of such an adaptive ERD-based BCI for individuals with severe motor impairment as a result of spinal cord injury (SCI) or stroke. We hypothesized that an adaptive ERD-based BCI, that automatically selects a user specific class-combination from motor-related and non motor-related mental tasks during initial auto-calibration ("Auto-AdBCI") could allow for higher control performance than a conventional SMR-AdBCI. To answer this question we performed offline analyses on two sessions (21 data sets total) of cue-guided, five-class electroencephalography (EEG) data recorded from individuals with SCI or stroke. On data from the twelve individuals in Session 1, we first identified three bipolar derivations for the SMR-AdBCI. In a similar way, we determined three bipolar derivations and four mental tasks for the Auto-AdBCI. We then simulated both, the SMR-AdBCI and the Auto-AdBCI configuration on the unseen data from the nine participants in Session 2 and compared the results. On the unseen data of Session 2 from individuals with SCI or stroke, we found that automatically selecting a user specific class-combination from motor-related and non motor-related mental tasks during initial auto-calibration (Auto-AdBCI) significantly (p < 0.01) improved classification performance compared to an adaptive ERD-based BCI that only used motor imagery tasks (SMR-AdBCI; average accuracy of 75.7 vs. 66.3%).

No MeSH data available.


Related in: MedlinePlus

Schematic depiction of the structure of one single trial.
© Copyright Policy - open-access
Related In: Results  -  Collection

License
getmorefigures.php?uid=PMC4196541&req=5

Figure 2: Schematic depiction of the structure of one single trial.

Mentions: We used a modified cue-guided Graz-BCI paradigm (Pfurtscheller and Neuper, 2001, see Figure 2). The participants were instructed to perform one of five different specific mental tasks starting from the appearance of the visual cue until the disappearance of the cue and the cross seven seconds later. Two of the mental tasks were motor-related: Sustained imagery of (1) a dorsiflexion of both feet (“Feet”) and (2) a palmar grasp of the right hand (“Hand”). The other three classes were non motor-related tasks: For condition (3), participants were instructed to mentally recall as many words as possible starting with a provided letter (“Word”). The letters were drawn from a uniform random distribution over the custom alphabet A, D, E, F, G, H, I, J, C, M, N, O, P, R, S, T, L, and V (adapted for Spanish language). For condition (4), participants were instructed to subtract a given subtrahend (randomly between 3 and 10) from a given minuend (randomly between 15 and 30) and to keep subtracting the subtrahend from the last difference (e.g., 17 − 9 = 8 ⇒ 8 − 9 = −1 ⇒ −1 − 9 = −10, etc.) for the duration of the imagery period (“Math”). For condition (5), participants were instructed to mentally navigate through a well known building (“Nav”). During each run (6 min long), we recorded 25 trials, five for each of the five cue conditions. The sequence of cues was random. In every session we recorded eight runs (i.e., 200 trials per session).


Non-motor tasks improve adaptive brain-computer interface performance in users with severe motor impairment.

Faller J, Scherer R, Friedrich EV, Costa U, Opisso E, Medina J, Müller-Putz GR - Front Neurosci (2014)

Schematic depiction of the structure of one single trial.
© Copyright Policy - open-access
Related In: Results  -  Collection

License
Show All Figures
getmorefigures.php?uid=PMC4196541&req=5

Figure 2: Schematic depiction of the structure of one single trial.
Mentions: We used a modified cue-guided Graz-BCI paradigm (Pfurtscheller and Neuper, 2001, see Figure 2). The participants were instructed to perform one of five different specific mental tasks starting from the appearance of the visual cue until the disappearance of the cue and the cross seven seconds later. Two of the mental tasks were motor-related: Sustained imagery of (1) a dorsiflexion of both feet (“Feet”) and (2) a palmar grasp of the right hand (“Hand”). The other three classes were non motor-related tasks: For condition (3), participants were instructed to mentally recall as many words as possible starting with a provided letter (“Word”). The letters were drawn from a uniform random distribution over the custom alphabet A, D, E, F, G, H, I, J, C, M, N, O, P, R, S, T, L, and V (adapted for Spanish language). For condition (4), participants were instructed to subtract a given subtrahend (randomly between 3 and 10) from a given minuend (randomly between 15 and 30) and to keep subtracting the subtrahend from the last difference (e.g., 17 − 9 = 8 ⇒ 8 − 9 = −1 ⇒ −1 − 9 = −10, etc.) for the duration of the imagery period (“Math”). For condition (5), participants were instructed to mentally navigate through a well known building (“Nav”). During each run (6 min long), we recorded 25 trials, five for each of the five cue conditions. The sequence of cues was random. In every session we recorded eight runs (i.e., 200 trials per session).

Bottom Line: Auto-calibrating and adaptive ERD-based BCIs that users control with motor imagery tasks ("SMR-AdBCI") have proven effective for healthy users.We then simulated both, the SMR-AdBCI and the Auto-AdBCI configuration on the unseen data from the nine participants in Session 2 and compared the results.On the unseen data of Session 2 from individuals with SCI or stroke, we found that automatically selecting a user specific class-combination from motor-related and non motor-related mental tasks during initial auto-calibration (Auto-AdBCI) significantly (p < 0.01) improved classification performance compared to an adaptive ERD-based BCI that only used motor imagery tasks (SMR-AdBCI; average accuracy of 75.7 vs. 66.3%).

View Article: PubMed Central - PubMed

Affiliation: Laboratory of Brain-Computer Interfaces, Institute for Knowledge Discovery, Graz University of Technology Graz, Austria.

ABSTRACT
Individuals with severe motor impairment can use event-related desynchronization (ERD) based BCIs as assistive technology. Auto-calibrating and adaptive ERD-based BCIs that users control with motor imagery tasks ("SMR-AdBCI") have proven effective for healthy users. We aim to find an improved configuration of such an adaptive ERD-based BCI for individuals with severe motor impairment as a result of spinal cord injury (SCI) or stroke. We hypothesized that an adaptive ERD-based BCI, that automatically selects a user specific class-combination from motor-related and non motor-related mental tasks during initial auto-calibration ("Auto-AdBCI") could allow for higher control performance than a conventional SMR-AdBCI. To answer this question we performed offline analyses on two sessions (21 data sets total) of cue-guided, five-class electroencephalography (EEG) data recorded from individuals with SCI or stroke. On data from the twelve individuals in Session 1, we first identified three bipolar derivations for the SMR-AdBCI. In a similar way, we determined three bipolar derivations and four mental tasks for the Auto-AdBCI. We then simulated both, the SMR-AdBCI and the Auto-AdBCI configuration on the unseen data from the nine participants in Session 2 and compared the results. On the unseen data of Session 2 from individuals with SCI or stroke, we found that automatically selecting a user specific class-combination from motor-related and non motor-related mental tasks during initial auto-calibration (Auto-AdBCI) significantly (p < 0.01) improved classification performance compared to an adaptive ERD-based BCI that only used motor imagery tasks (SMR-AdBCI; average accuracy of 75.7 vs. 66.3%).

No MeSH data available.


Related in: MedlinePlus