Abstract
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.
Recommended Citation
J. C. Sanchez et al., "Technology And Signal Processing For Brain-machine Interfaces," IEEE Signal Processing Magazine, vol. 25, no. 1, pp. 29 - 40, Institute of Electrical and Electronics Engineers, Jan 2008.
The definitive version is available at https://doi.org/10.1109/MSP.2008.4408440
Department(s)
Electrical and Computer Engineering
International Standard Serial Number (ISSN)
1053-5888
Document Type
Article - Journal
Document Version
Citation
File Type
text
Language(s)
English
Rights
© 2025 Institute of Electrical and Electronics Engineers, All rights reserved.
Publication Date
01 Jan 2008
Comments
National Science Foundation, Grant CNS-0540304