Scholarlink

Losing a limb is a life-altering event that significantly affects an individual’s independence and quality of life. Among prosthetic advancements, upper-limb prosthetics have gained greater attention due to their essential role in restoring functionality and autonomy. However, current upper-limb prosthetics are constrained by two primary limitations: restricted ranges of movement and limited simultaneous control. In this paper, we propose a modified CNN-LSTM hybrid architecture designed for continuous computation of four degrees of freedom (DOF), enabling control of the elbow angle (θ), the horizontal (X) and vertical (Y) positions of the wrist joint, and velocity (v) of arm movement. We specifically examine the effect of incorporating historical timesteps on enhancing the decoding performance of these parameters. Our results demonstrate significant enhancements in decoding accuracy when historical timesteps are incorporated surpassing state-of-the-art methods applied on the same dataset and other studies utilizing similar hybrid approaches on different datasets.

错误：搜索内容不能为空，请输入英文关键词
错误：关键词超出字数限制，请精简
高级检索

A Hybrid CNN-LSTM Deep Learning Framework for Multi-DOF Control of Upper-Limb Prosthetic Using EMG Signals

  • 会议论文

  • 发表日期：

    2025年

查看全文
  • Hend ElMohandes,
  • Neamat El Gayar,
  • Adrian Turcanu,
  • Roman Ruff

摘要

Losing a limb is a life-altering event that significantly affects an individual’s independence and quality of life. Among prosthetic advancements, upper-limb prosthetics have gained greater attention due to their essential role in restoring functionality and autonomy. However, current upper-limb prosthetics are constrained by two primary limitations: restricted ranges of movement and limited simultaneous control. In this paper, we propose a modified CNN-LSTM hybrid architecture designed for continuous computation of four degrees of freedom (DOF), enabling control of the elbow angle (θ), the horizontal (X) and vertical (Y) positions of the wrist joint, and velocity (v) of arm movement. We specifically examine the effect of incorporating historical timesteps on enhancing the decoding performance of these parameters. Our results demonstrate significant enhancements in decoding accuracy when historical timesteps are incorporated surpassing state-of-the-art methods applied on the same dataset and other studies utilizing similar hybrid approaches on different datasets.