Classification of functional near-infrared spectroscopy signals corresponding to the right- and left-wrist motor imagery for development of a brain–computer interface.

Highlights: [•] Classification of fNIRS signals corresponding to the right- and left-wrist motor imagery. [•] Hemodynamic responses of the right-wrist imagery are distinguishable from those of left. [•] Signal slope improves the classification accuracy significantly than signal mean. [•] Enhanced performance on examination of subset of the response data. [ABSTRACT FROM AUTHOR]