Brain-machine interfaces (BMIs) aid disabled humans. BMI systems face challenges such as interfacing with neural tissue, selecting the most appropriate control signals, acquiring data and decoding patient intent in implantable or wearable computers. They must be able to adapt to different variety of behavioral states. Today's hybrid BMI systems consume less power and are made to chronically extract control commands from the nervous system. In terms of signal processing approaches, one challenge for BMI data analysis is learning how to handle large multi-input multi-output systems with signal representations that span continuous and discrete time. BMI systems also need sufficient information on spatio-temporal representation made by assemblies of neurons. BMIs success is dependent on the ability to first extract control features from neural activity related to goal-directed behavior.
ASJC Scopus subject areas
- Signal Processing
- Electrical and Electronic Engineering
- Applied Mathematics