A5021224274- EEG and Brain-Computer Interfaces
- Neuroscience and Neural Engineering
- Neural dynamics and brain function
- Optical Imaging and Spectroscopy Techniques
- Vagus Nerve Stimulation Research
- Neurological disorders and treatments
- Functional Brain Connectivity Studies
University of Houston
2018-2021
We are developing an autonomously updating brain machine interface (BMI) utilizing reinforcement learning principles. One aspect of this system is a neural critic that determines reward expectations from activity. This then used to update BMI decoder toward improved performance the user's perspective. Here we demonstrate ability classify trial value given activity primary motor cortex (M1), using features single/multi units (SU/MU), and local field potentials (LFPs) with prediction...
Accurate and cost-effective seizure severity tracking is an important step towards limiting the negative effects of seizures in epileptic patients. Electroencephalography (EEG) employed as a means to track due its high temporal resolution. In this research, state detection was performed using mixed-filter approach reduce number channels. We first found two optimized EEG features (one binary, one continuous) wrapper feature selection. This selection process reduces required channels two,...
Real-time continuous tracking of seizure state is necessary to develop feedback neuromodulation therapy that can prevent or terminate a early. Due its high temporal resolution, scalp coverage, and non-invasive applicability, electroencephalography (EEG) good candidate for tracking. In this research, we make multiple estimations using mixed-filter channels found over the entire sensor space; then by applying Kalman filter, produce single estimation made up these individual estimations. Using...
Abstract We are developing an autonomously updating brain machine interface (BMI) utilizing reinforcement learning principles. One aspect of this system is a neural critic that determines reward expectations from activity. This then used to update BMI decoder towards improved performance the user’s perspective. Here we demonstrate ability classify trial value given activity primary motor cortex (M1), using features single/multi units (SU/MU), and local field potentials (LFPs) with prediction...