Deep Learning Enabled Neck Motion Detection Using a Triboelectric Nanogenerator.

Abstract

The state of neck motion reflects cervical health. To detect the motion state of the human neck is of important significance to healthcare intelligence. A practical neck motion detector should be wearable, flexible, power efficient, and low cost. Here, we report such a neck motion detector comprising a self-powered triboelectric sensor group and a deep learning block. Four flexible and stretchable silicon rubber based triboelectric sensors are integrated on a neck collar. With different neck motions, these four sensors lead-out voltage signals with different amplitudes and/or directions. Thus, the combination of these four signals can represent one motion state. Significantly, a carbon-doped silicon rubber layer is attached between the neck collar and the sensors to shield the external electric field (i.e., electrical changes at the skin surface) for a far more robust identification. Furthermore, a deep learning model based on the convolutional neural network is designed to recognize 11 classes of neck motion including eight directions of bending, two directions of twisting, and one resting state with an average recognition accuracy of 92.63%. This developed neck motion detector has promising applications in neck monitoring, rehabilitation, and control.