Do Not Move! Entropy Driven Detection of Intentional Non-Control during Online SMR-BCI Operations (original) (raw)

Classification of Movement and Inhibition Using a Hybrid BCI

Brain-computer interfaces (BCIs) are an emerging technology that are capable of turning brain electrical activity into commands for an external device. Motor imagery (MI)—when a person imagines a motion without executing it—is widely employed in BCI devices for motor control because of the endogenous origin of its neural control mechanisms, and the similarity in brain activation to actual movements. Challenges with translating a MI-BCI into a practical device used outside laboratories include the extensive training required, often due to poor user engagement and visual feedback response delays; poor user flexibility/freedom to time the execution/inhibition of their movements, and to control the movement type (right arm vs. left leg) and characteristics (reaching vs. grabbing); and high false positive rates of motion control. Solutions to improve sensorimotor activation and user performance of MI-BCIs have been explored. Virtual reality (VR) motor-execution tasks have replaced simpler visual feedback (smiling faces, arrows) and have solved this problem to an extent. Hybrid BCIs (hBCIs) implementing an additional control signal to MI have improved user control capabilities to a limited extent. These hBCIs either fail to allow the patients to gain asynchronous control of their movements, or have a high false positive rate. We propose an immersive VR environment which provides visual feedback that is both engaging and immediate, but also uniquely engages a different cognitive process in the patient that generates event-related potentials (ERPs). These ERPs provide a key executive function for the users to execute/inhibit movements. Additionally, we propose signal processing strategies and machine learning algorithms to move BCIs toward developing long-term signal stability in patients with distinctive brain signals and capabilities to control motor signals. The hBCI itself and the VR environment we propose would help to move BCI technology outside laboratory environments for motor rehabilitation in hospitals, and potentially for controlling a prosthetic.

The Berlin Brain-Computer Interface: Machine Learning Based Detection of User Specific Brain States

J. Univers. Comput. Sci., 2006

The Berlin Brain-Computer Interface (BBCI) project develops an EEG-based BCI system that uses machine learning techniques to adapt to the specific brain signatures of each user. This concept allows to achieve high quality feedback already in the very first session without subject training. Here we present the broad range of investigations and experiments that have been performed within the BBCI project. The first kind of experiments analyzes the predictability of performing limbs from the premovement (readiness) potentials including successful feedback experiments. The limits with respect to the spatial resolution of the somatotopy are explored by contrasting brain patterns of movements of (1) left vs. right foot, (2) index vs. little finger within one hand, and (3) finger vs. wrist vs. elbow vs. shoulder within one arm. A study of phantom movements of patients with traumatic amputations shows the potential applicability of this BCI approach. In a complementary approach, voluntary m...

Non-causal spike filtering improves decoding of movement intention for intracortical BCIs

Journal of Neuroscience Methods, 2014

Multiple types of neural signals are available for controlling assistive devices through brain-computer interfaces (BCIs). Intracortically recorded spiking neural signals are attractive for BCIs because they can in principle provide greater fidelity of encoded information compared to electrocorticographic (ECoG) signals and electroencephalograms (EEGs). Recent reports show that the information content of these spiking neural signals can be reliably extracted simply by causally band-pass filtering the recorded extracellular voltage signals and then applying a spike detection threshold, without relying on "sorting" action potentials. We show that replacing the causal filter with an equivalent non-causal filter increases the information content extracted from the extracellular spiking signal and improves decoding of intended movement direction. This method can be used for real-time BCI applications by using a 4ms lag between recording and filtering neural signals. Across 18 sessions from two people with tetraplegia enrolled in the BrainGate2 pilot clinical trial, we found that threshold crossing events extracted using this non-causal filtering method were significantly more informative of each participant's intended cursor kinematics compared to threshold crossing events derived from causally filtered signals. This new method decreased the mean angular error between the intended and decoded cursor direction by 9.7° for participant S3, who was implanted 5.4 years prior to this study, and by 3.5° for participant T2, who was implanted 3 months prior to this study. Non-causally filtering neural signals prior to extracting threshold crossing events may be a simple yet effective way to condition intracortically recorded neural activity for direct control of external devices through BCIs.