AUTHOR=Schaeffer Marie-Caroline , Aksenova Tetiana 

TITLE=Data-Driven Transducer Design and Identification for Internally-Paced Motor Brain Computer Interfaces: A Review

JOURNAL=Frontiers in Neuroscience

VOLUME=Volume 12 - 2018

YEAR=2018

URL=https://www.frontiersin.org/journals/neuroscience/articles/10.3389/fnins.2018.00540

DOI=10.3389/fnins.2018.00540

ISSN=1662-453X

ABSTRACT=Brain-Computer Interfaces (BCI) are systems which establish a direct communication pathway between users’ brain activity and external effectors, and raise hopes that the quality of life of motor-impaired patients may thereby be improved. Motor BCIs more specifically aim at permitting severely motor-impaired users to regain limb mobility by controlling orthoses or prostheses. Motor BCI systems benefit patients if the decoded actions reflect the users’ intentions with an accuracy enabling them to efficiently interact with their environment. Adapting the BCI’s signal translation blocks to the user so as to reach a high decoding accuracy is one of the main challenges of BCI systems. Data-driven and user-specific transducer design and identification approaches are the particular topics of the present review, which focuses on internally-paced motor BCIs. Continuous kinematic biomimetic and mental-task decoders are reviewed. Static and dynamic decoding approaches, linear and nonlinear decoding, offline and real-time identification algorithms are considered. The current progress and challenges related to the design of clinical-compatible motor BCI transducers are additionally discussed.