ABSTRACT
Motor imagery (MI)–based brain–computer interface (BCI) is one of the standard concepts of BCI, in that the user can generate induced activity from motor cortex by imagining motor movements without any limb movement or external stimulus. In this chapter, we present a step-by-step tutorial on MI BCI and discuss the issues involved in each step. We describe detailed examples of our MI experiment with a general procedure from training session to testing session. In training session, we introduce and discuss recording devices and software, experimental settings, collecting MI data and questionnaires, offline analysis for inhibition of somatosensory rhythm, and training simple machine learning algorithms, including common spatial patterns and Fisher’s linear discriminant analysis. Next, we introduce basic procedures used in the testing session and discuss important issues including session variabilities of electroencephalogram signal and information transfer rate. Last, we summarize the tutorial and list the challenging issues that remain in MI BCI.
