Key points are not available for this paper at this time.
In this work, we evaluate the performance of a self-powered sensing unit for human activity recognition (HAR). The system consists of two triboelectric nanogenerators (TENGs),located in the insole of the left shoe. An Inertial Measurement Unit (IMU) is also attached to the ankle of the left foot, and it will serve to compare the performance of the TENG-based HAR to that of the IMU-based HAR. Five activities were included: walking on a flat surface, walking upstairs, walking downstairs, running, and jumping. All activities had a few seconds of idle before and after to help with data annotation. We observed that TENG data clearly shows all five distinct activities and machine learning techniques classified the activities with sufficient accuracy and minimal data preprocessing. The Random Forest algorithm performed the best with an accuracy of 88%. This work proves that TENG-based motion sensing is suitable for activity recognition in portable Internet of Things (IoT) devices with lower energy expenditure.
Harris et al. (Mon,) studied this question.