A novel EMG-based human-computer interface for persons with disability

This paper proposes a novel EMG-based human computer interface (HCI) for persons with disabilities. The interaction commands for the HCI consist of four commands, that are composed by combination of three elevation motions of shoulders such as left, right and both elevations. By comparing EMG signals on the Levator scapulae muscles with predetermined double threshold values, each elevation motion is recognized. To achieve a real-time EMG processing hardware, high- and low-pass filter, band-pass and -rejection filter, a full rectifier and a mean absolute value circuit are embedded on a board with a high-speed microprocessor. From experimental results using the implemented real-time EMG processing hardware, we show that the proposed wireless EMG-based HCI is feasible for the disabled.