Brain–machine interfaces [book]

Girijesh Prasad
2018 Oxford Scholarship Online  
A brain–machine interface (BMI) is a biohybrid system intended as an alternative communication channel for people suffering from severe motor impairments. A BMI can involve either invasively implanted electrodes or non-invasive imaging systems. The focus in this chapter is on non-invasive approaches; EEG-based BMI is the most widely investigated. Event-related de-synchronization/ synchronization (ERD/ERS) of sensorimotor rhythms (SMRs), P300, and steady-state visual evoked potential (SSVEP) are
more » ... tential (SSVEP) are the three main cortical activation patterns used for designing an EEG-based BMI. A BMI involves multiple stages: brain data acquisition, pre-processing, feature extraction, and feature classification, along with a device to communicate or control with or without neurofeedback. Despite extensive research worldwide, there are still several challenges to be overcome in making BMI practical for daily use. One such is to account for non-stationary brainwaves dynamics. Also, some people may initially find it difficult to establish a reliable BMI with sufficient accuracy. BMI research, however, is progressing in two broad areas: replacing neuromuscular pathways and neurorehabilitation.
doi:10.1093/oso/9780199674923.003.0049 fatcat:brrhksej3fb5hpwzkfmptvd7zm