CRIS

Permanent URI for this communityhttps://scripta.up.edu.mx/handle/20.500.12552/1

Browse

Settings

Author: search.filters.author.Escobedo-Gordillo, AndrésHas files: Yes

Search Results

Now showing 1 - 1 of 1
  • Loading...
    Thumbnail Image
    Some of the metrics are blocked by your 
    consent settings
    Item type:Publication,
    Orthosis Control Based on Electromyographic Signals and Machine Learning
    (Springer Nature Switzerland, 2025)
    Escobedo-Gordillo, Andrés
    ;
    Díaz, Fernando
    ;
    Villa, Jesús
    ;
    Sepúlveda, Miguel
    ;
    García-Casas, Sebastián
    The human hand is indispensable for daily activities, and those who suffer from dysfunction due to strokes or accidents often require therapy to improve their condition. This study has developed a hand orthosis that uses surface Electromyographic (sEMG) signals and machine learning to address therapeutic needs and improve the quality of life for individuals with reduced motor skills in their hands and/or wrists. While current orthoses meet therapy requirements, they do not incorporate machine learning (ML) or sEMG sensors to optimize performance and accessibility. This chapter describes a remote-controlled, electro-mechanical orthosis that can replicate six basic movements of the human hand using three sEMG channels and ML. Our dataset of 14,400 samples, each labeled with a hand gesture, was generated by eight participants. The orthosis is comfortable and customizable for different users, as shown in prototype testing. The convolutional neural network (CNN) used achieves an accuracy of 90.38% with an inference time of 1.515 ms. Therefore, this orthosis system has significant potential for further development and practical application in patients who require such intervention. ©The authors ©Springer.