Article

Noninvasive brain-computer interfaces (BCIs) use scalp-recorded electrical
activity from the brain to control an application. Over the past 20 years,
research demonstrating that BCIs can provide communication and control to
individuals with severe motor impairment has increased almost exponentially.
Although considerable effort has been dedicated to offline analysis for improving
signal detection and translation, far less effort has been made to conduct online
studies with target populations. Thus, there remains a great need for both
long-term and translational BCI studies that include individuals with
disabilities in their own homes. Completing these studies is the only sure means
to answer questions about BCI utility and reliability. Here we suggest an
algorithm for candidate selection for electroencephalographic (EEG)-based BCI
home studies. This algorithm takes into account BCI end-users and their
environment and should assist in study design and substantially improve subject
retention rates, thereby improving the overall efficacy of BCI home studies. It
is the result of a workshop at the Fifth International BCI Meeting that allowed
us to leverage the expertise of multiple research laboratories and people from
multiple backgrounds in BCI research.
CI - Copyright (c) 2015 American Congress of Rehabilitation Medicine. Published by
Elsevier Inc. All rights reserved.

Langue : ANGLAIS