Binary Controller Based on the Electrical Activity Related to Head Yaw Rotation

A human machine interface (HMI) is presented to switch on/off lights according the head left/right yaw rotation. The HMI consists of a cap, which can acquire brain’s electrical activity (i.e., an electroencephalogram, EEG) sampled at 500 Hz on 8 channels with electrodes that are positioned standard 10–20 system. In addition, includes controller based input–output function compute position (defined as left, right, and forward respect angle) considering short intervals (10 samples) signals coming from three in O1, O2, Cz. An artificial neural network (ANN) training Levenberg–Marquardt backpropagation algorithm was used identify function. tested 22 participants. proposed classifier achieved average accuracy 88% best value 96.85%. After calibration for each specific subject, binary verify its ability lamps turning movement. correct prediction movements greater than 75% 90% participants when performing test open eyes. If subjects carried out experiments closed eyes, reached correctness 11 22. One participant controlled light system both experiments, 100% success. control results this work be considered important milestone towards humanoid neck systems.