Poster #15: Gabriel Santana – Data augmentation of electromyography data to improve machine-learning performance

<< Return to the Virtual URS Main Page

Faculty mentor: Caleb Thomson

In this study, we aim to improve the performance and reduce the data collection of popular machine-learning algorithms for decoding motor intent from electromyography (EMG) data through data augmentation. Data augmentation can include adding noise and dropping out data. We found that augmenting EMG data with gaussian noise did not produce statistically significant results in improving performance. Future work will explore additional data augmentation techniques that may improve performance.

Click below to hear me present my poster!
Questions or comments? Contact me at: gabriel.santana@utah.edu

<< Return to the Virtual URS Main Page