August 14, 2019 -Zachary Danziger, Ph.D., assistant professor in Florida International University’s Biomedical Engineering Department, received a five-year R01 grant from the National Institutes of Neurological Disorders and Stroke (NINDS) of the National Institutes of Health (NIH). This approximately 1.6 Million USD entitled “An Intracortical Brain-Computer Interface Model for High-Efficiency Development of Closed-Loop Neural Decoding Algorithms” will aid his research in developing advanced Brain-Computer Interfaces and puts him into a select group of RO1 funded researchers in the country. A unique aspect of the work is the novel experimental paradigm; human subjects will interact in real-time with a dynamic model of brain activity, created with modern machine learning tools, to allow his lab to evaluate and optimize algorithms designed understand a user’s basic intentions from their brain signals.
An intracortical brain-computer interface (iBCI) is used to record electrical signals directly from a person’s brain, predict their intention from those signals, then control an assistive device (e.g., a computer cursor, prosthetic limb, or powered wheelchair) according to those intentions. This technology enables severely paralyzed people to interact with the world. However, designing robust algorithms to extract intent from recordings of single neurons is extremely challenging, in large part because of the very limited access to humans, or even monkeys, from whom these invasive recordings can be made. The proposed work will develop a tool that scientists can use to design, test, and optimize the sophisticated computer programs that translate brain signals into device instructions without having to implant electrodes into a person’s brain until the program is completed and rigorously tested. This tool could increase the pace of discovery and development of brain-computer interfaces.
Dr. Danziger’s group will develop a model iBCI system that generates real-time biomimetic neural data by capturing the high-degree-of-freedom finger movements of able-bodied human subjects. To accomplish this, they will construct a modular recurrent neural network (RNN). The RNN will first be trained to predict the motor cortex activity of a monkey from the monkey’s own finger kinematics. Once the modular RNN is trained, its weights will be fixed and human finger kinematics will be used as the RNN inputs, which will generate subject-controlled emulated neural activity. The emulated neural activity will be passed to iBCI decoding algorithms that control computer cursors or other physical devices, allowing human subjects to interact directly with decoders in real time, closed-loop conditions. This model system will be low cost and noninvasive, making it possible to rapidly test and design novel iBCI decoders.
The project will be executed in close collaboration with non-human primate intracortical microelectrode array data expert Dr. Lee Miller at Northwestern University and machine-learning expert consultant Dr. Mathis from Harvard University.