The ability to accurately identify human activities is essential for developing automatic rehabilitation and sports training systems. In this paper, large-scale exercise motion data obtained from a forearm-worn wearable sensor are classified with a convolutional neural network (CNN). Time-series data consisting of accelerometer and orientation measurements are formatted as images, allowing the CNN to automatically extract discriminative features. A comparative study on the effects of image formatting and different CNN architectures is also presented. The best performing configuration classifies 50 gym exercises with 92.1% accuracy.
@article{arxiv.1610.07031,
title = {Exercise Motion Classification from Large-Scale Wearable Sensor Data Using Convolutional Neural Networks},
author = {Terry Taewoong Um and Vahid Babakeshizadeh and Dana Kulić},
journal= {arXiv preprint arXiv:1610.07031},
year = {2017}
}