Eye blink detection for the implantable system for functional restoration of orbicularis oculi muscle

In this work, the blink detection algorithm for an embedded closed-loop system for a restoration of facial muscle functions in the case of unilateral facial nerve paralysis is proposed. The algorithm is based on a real-time assessment of a spectral power of the electromyographic signal, which is recorded from the orbicularis oculi muscle with implanted needle electrodes on the healthy side of the patient's face. Once a blink is detected, the stimulation command is sent to the module of the functional electrical stimulation, which elicits the contraction of muscles on the paralyzed side of the face. The algorithm was tested on the electromyographic signals, which were recorded from the orbicularis oculi muscle of the healthy subject performing daily routine activity tasks (head movements, vocalization, etc). The resulting 93 % sensitivity and 63 % precision values are obtained.