Development of Assistive Technology Devices Using an EEG Headset

Two signal-processing algorithms have been developed to detect the head movements from a human subject. The head movement was measured by two signals from a gyroscope (representing x- and y-axis) integrated in an EEG headset (EEG neuroheadset, Emotiv Systems). These signals were acquired into a PC wirelessly to determine four possible head movements: left, right, up, and down using two different algorithms based on cross-correlation and clipping. A series of tests was conducted with two subjects to evaluate the performance of both algorithms. The results showed that the cross-correlation method detected head movements with 75% accuracy while the clipping method performed slightly better than the cross-correlation method with 81% accuracy. These algorithms will be further improved and integrated with a brain-computer interface for the purpose of assisting people with disabilities.