Decoding three-dimensional arm movements for brain-machine interface

Abstract

Although estimation of 3-dimensional arm movements is crucial to control prosthetic devices using brain signals, there have been few non-invasive brain-machine interface (BMI) studies estimating arm movements. Here, we aimed to estimate 3-dimensional movements using magnetoencephalography (MEG) signals. For the movement decoding, we determined 68 MEG channels on motor-related area and 4 sub-frequency bands, 0.5–8, 9–22, 25–40 and 57–97Hz, based on event-related desynchronization (ERD) and synchronization (ERS). Our results demonstrate that non-invasive signals can estimate 3-dimensional movements with considerably high performance (mean r > 0.6). We also verified that low-frequency activity plays an important role in estimating a 3-dimensional movement trajectory. These results imply that disabled people will be able to control prosthetic devices without surgery in the near future.