Exercise Motion Classification from Large-Scale Wearable Sensor Data Using Convolutional Neural Networks
This work addresses the need for accurate activity identification in rehabilitation and sports training systems, but it is incremental as it applies existing CNN methods to a new dataset with specific formatting optimizations.
The paper tackled the problem of classifying 50 gym exercises using data from a forearm-worn wearable sensor, achieving 92.1% accuracy by formatting time-series accelerometer and orientation data as images for a convolutional neural network.
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.