Robustness-enhanced Myoelectric Control with GAN-based Open-set Recognition

Fuente: arXiv
Guardado en:
Detalles Bibliográficos
Autores principales: Wang, Cheng, Feng, Ziyang, Zhang, Pin, Cao, Manjiang, Yuan, Yiming, Chang, Tengfei
Formato: Preprint
Publicado: 2024
Materias:
Acceso en línea:
Etiquetas: Agregar Etiqueta
Sin Etiquetas, Sea el primero en etiquetar este registro!
_version_ 1866910973501112320
author Wang, Cheng
Feng, Ziyang
Zhang, Pin
Cao, Manjiang
Yuan, Yiming
Chang, Tengfei
author_facet Wang, Cheng
Feng, Ziyang
Zhang, Pin
Cao, Manjiang
Yuan, Yiming
Chang, Tengfei
contents Electromyography (EMG) signals are widely used in human motion recognition and medical rehabilitation, yet their variability and susceptibility to noise significantly limit the reliability of myoelectric control systems. Existing recognition algorithms often fail to handle unfamiliar actions effectively, leading to system instability and errors. This paper proposes a novel framework based on Generative Adversarial Networks (GANs) to enhance the robustness and usability of myoelectric control systems by enabling open-set recognition. The method incorporates a GAN-based discriminator to identify and reject unknown actions, maintaining system stability by preventing misclassifications. Experimental evaluations on publicly available and self-collected datasets demonstrate a recognition accuracy of 97.6\% for known actions and a 23.6\% improvement in Active Error Rate (AER) after rejecting unknown actions. The proposed approach is computationally efficient and suitable for deployment on edge devices, making it practical for real-world applications.
format Preprint
id arxiv_https___arxiv_org_abs_2412_15819
institution arXiv
publishDate 2024
record_format arxiv
spellingShingle Robustness-enhanced Myoelectric Control with GAN-based Open-set Recognition
Wang, Cheng
Feng, Ziyang
Zhang, Pin
Cao, Manjiang
Yuan, Yiming
Chang, Tengfei
Computer Vision and Pattern Recognition
Human-Computer Interaction
Signal Processing
Electromyography (EMG) signals are widely used in human motion recognition and medical rehabilitation, yet their variability and susceptibility to noise significantly limit the reliability of myoelectric control systems. Existing recognition algorithms often fail to handle unfamiliar actions effectively, leading to system instability and errors. This paper proposes a novel framework based on Generative Adversarial Networks (GANs) to enhance the robustness and usability of myoelectric control systems by enabling open-set recognition. The method incorporates a GAN-based discriminator to identify and reject unknown actions, maintaining system stability by preventing misclassifications. Experimental evaluations on publicly available and self-collected datasets demonstrate a recognition accuracy of 97.6\% for known actions and a 23.6\% improvement in Active Error Rate (AER) after rejecting unknown actions. The proposed approach is computationally efficient and suitable for deployment on edge devices, making it practical for real-world applications.
title Robustness-enhanced Myoelectric Control with GAN-based Open-set Recognition
topic Computer Vision and Pattern Recognition
Human-Computer Interaction
Signal Processing
url https://arxiv.org/abs/2412.15819