Operation action recognition using wearable devices with inertial sensors

Abstract

The recognition of the operations are important for the factories management. In the paper, we propose an operation action recognition method based on two wearable devices containing inertial sensors. A mobile solution that leverages wristbands to capture the motions of operations is comfortable for workers. We first design the features based on the physical parameters of operation actions. To systematically preprocess the data, the features which consist of spectral entropy, the sum of acceleration, angular rate and angle are extracted. Support Vector Machine is used to recognize the operations. Four different operation actions of different persons are implemented in the experiments. The results indicate that the proposed method can recognition operation actions with high accuracy.