A Supplementary System for a Brain-Machine Interface Based on Jaw Artifacts for the Bidimensional Control of a Robotic Arm

摘要: Non-invasive Brain-Machine Interfaces (BMIs) are being used more and these days to design systems focused on helping people with motor disabilities. Spontaneous BMIs translate user's brain signals into commands control devices. On systems, by large, 2 different mental tasks can be detected enough accuracy. However, a large training time is required the system needs adjusted each session. This paper presents supplementary that employs BMI sensors, allowing use of (the system) same data acquisition device. designed robotic arm in two dimensions using electromyographical (EMG) extracted from electroencephalographical (EEG) recordings. These voluntarily produced users clenching their jaws. EEG (with EMG contributions) were registered analyzed obtain electrodes range frequencies which provide best classification results for 5 tasks. A stage, based 2-dimensional cursor, was volunteers get this control. Afterwards, extrapolated workspace. Although performed requires 70 minutes, final suggest shorter period (45 min), should able The compared similar spontaneous BMIs, our shows faster accurate performance. due nature signals. Brain potentials much difficult than jaw clenches. Additionally, presented also an improvement electrooculographic environment.