Upper Limb EMG
- Citation Author(s):
-
Muhammad Faisal (COMSATS University)
- Submitted by:
- Muhammad Faisal
- Last updated:
- DOI:
- 10.21227/r3s3-w304
- Data Format:
232 views
- Categories:
- Keywords:
Abstract
This study explores the potential of electromyography (EMG) decoding to enhance motor function outcomes, focusing on developing an innovative EMG-based hand movement classification system. Leveraging advanced signal processing and machine learning techniques, our objectives are twofold: (1) optimize EMG decoding performance through time-domain windowing, feature selection, and classifier optimization, and (2) assess the system's effectiveness in classifying 15 distinct finger movements. With a validation accuracy of 99.98%, this research contributes to the development of more accurate myoelectric control systems, improving rehabilitation outcomes and quality of life for individuals with neurological disorders.
Instructions:
A computer-based system utilizing the Delsys Trigno Avanti EMG system recorded EMG signals from 15 distinct finger movements. The system features wearable, wireless EMG sensors with a proprietary electrode configuration, enabling high-resolution muscle activity detection. Key features include adjustable EMG bandwidth, on-board signal processing, and seamless integration with IMU data. The compact, durable Trigno Avanti sensor is ideal for movement sciences, physical therapy, and sports science applications. Participants completed a brief screener survey to assess eligibility.
