Scholarlink

The human hand plays a vital role in numerous daily activities, performing a crucial part of the body’s functionality. The objective of this research is to interpret the finger movements using upper limb EMG signals. While the individuals typically engage in regular exercises, unilateral amputees face challenges in performing these activities with one hand only. For them, a hand-robotic assistive device becomes essential. This paper presents a study on the classification of various finger movements from a set of hand movements using EMG signals sourced from the online “Ninapro-DB4” database employing a machine learning model for classification. It introduces a simulation strategy in Unity software using forward kinematics to visualize the movements and achieves the highest accuracy of 84.5% while considering 5 hand movements.

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

Myoelectric Signal Based Finger Movement Classification and Simulation

  • 会议论文

  • 发表日期：

    2026年

查看全文
  • Eashita Chowdhury,
  • Shailesh Bamoriya,
  • Pallab Das,
  • Cheruvu Siva Kumar,
  • Manjunatha Mahadevappa

摘要

The human hand plays a vital role in numerous daily activities, performing a crucial part of the body’s functionality. The objective of this research is to interpret the finger movements using upper limb EMG signals. While the individuals typically engage in regular exercises, unilateral amputees face challenges in performing these activities with one hand only. For them, a hand-robotic assistive device becomes essential. This paper presents a study on the classification of various finger movements from a set of hand movements using EMG signals sourced from the online “Ninapro-DB4” database employing a machine learning model for classification. It introduces a simulation strategy in Unity software using forward kinematics to visualize the movements and achieves the highest accuracy of 84.5% while considering 5 hand movements.