`

Timezone: »

 
Poster
Multiscale Semi-Markov Dynamics for Intracortical Brain-Computer Interfaces
Daniel Milstein · Jason Pacheco · Leigh Hochberg · John D Simeral · Beata Jarosiewicz · Erik Sudderth

Tue Dec 05 06:30 PM -- 10:30 PM (PST) @ Pacific Ballroom #176 #None
in Posters Tue »

Intracortical brain-computer interfaces (iBCIs) have allowed people with tetraplegia to control a computer cursor by imagining the movement of their paralyzed arm or hand. State-of-the-art decoders deployed in human iBCIs are derived from a Kalman filter that assumes Markov dynamics on the angle of intended movement, and a unimodal dependence on intended angle for each channel of neural activity. Due to errors made in the decoding of noisy neural data, as a user attempts to move the cursor to a goal, the angle between cursor and goal positions may change rapidly. We propose a dynamic Bayesian network that includes the on-screen goal position as part of its latent state, and thus allows the person’s intended angle of movement to be aggregated over a much longer history of neural activity. This multiscale model explicitly captures the relationship between instantaneous angles of motion and long-term goals, and incorporates semi-Markov dynamics for motion trajectories. We also introduce a multimodal likelihood model for recordings of neural populations which can be rapidly calibrated for clinical applications. In offline experiments with recorded neural data, we demonstrate significantly improved prediction of motion directions compared to the Kalman filter. We derive an efficient online inference algorithm, enabling a clinical trial participant with tetraplegia to control a computer cursor with neural activity in real time. The observed kinematics of cursor movement are objectively straighter and smoother than prior iBCI decoding models without loss of responsiveness.

Keywords: Graphical Models · Time Series Analysis · Brain--Computer Interfaces and Neural Prostheses

Author Information

Daniel Milstein (Brown University)
Jason Pacheco (Brown University)
Leigh Hochberg (Brown, MGH, VA, Harvard)
John D Simeral (Brown University)

Dr. Simeral is a Assistant Professor of Engineering (Research) at Brown University, a Research Biomedical Engineer with the Department of Veterans Affairs Rehabilitation R&D Service, and leader of the focus area Restoring Communication and Mobility in the VA Center for Neurorestoration and Neurotechnology. His research is dedicated to integrating neuroscience and engineering disciplines to create unprecedented neural prosthetic technologies to enable communication and control of assistive devices by individuals with paralysis or locked-in syndrome resulting from spinal cord injury, ALS (Lou Gehrig's disease), stoke and other neurological disorders. He directs development of the system architecture, hardware and software for the BrainGate Neural Interface System (in clinical trial, IDE) that decodes intracortical brain signals into commands to control computer cursors, dexterous prosthetic robotic arms and hands, and other assistive technologies. In addition to research expertise in the neurophysiological basis of movement, Dr. Simeral has a decade of industry engineering experience including the design of massively parallel computer systems and high performance microelectronic VLSI microprocessors.

Beata Jarosiewicz (Stanford University)
Erik Sudderth (University of California, Irvine)

More from the Same Authors