Parkinson's Disease EMG Data Augmentation and Simulation with DCGANs and Style Transfer.

Journal: Sensors (Basel, Switzerland)
PMID:

Abstract

This paper proposes two new data augmentation approaches based on Deep Convolutional Generative Adversarial Networks (DCGANs) and Style Transfer for augmenting Parkinson's Disease (PD) electromyography (EMG) signals. The experimental results indicate that the proposed models can adapt to different frequencies and amplitudes of tremor, simulating each patient's tremor patterns and extending them to different sets of movement protocols. Therefore, one could use these models for extending the existing patient dataset and generating tremor simulations for validating treatment approaches on different movement scenarios.

Authors

  • Rafael Anicet Zanini
    Laboratory of Robotics and Cognitive Science (LaRoCS), Universidade Estadual de Campinas (UNICAMP), Campinas SP 13083-852, Brazil.
  • Esther Luna Colombini
    Laboratory of Robotics and Cognitive Science (LaRoCS), Universidade Estadual de Campinas (UNICAMP), Campinas SP 13083-852, Brazil.