A comprehensive review of sEMG-IMU sensor fusion for upper limb movements pattern recognition
Honglei Zhang, Sidi Mohamed Sid’El Moctar, Sofiane Boudaoud, Imad Rida
Abstract
This review provides a comprehensive analysis of sEMG-IMU sensor fusion techniques for upper limb movement pattern recognition. It offers detailed insights into the signal generation mechanisms of both surface electromyography (sEMG) and inertial measurement units (IMU), and critically explores multisensory fusion strategies aimed at enhancing recognition accuracy and reliability. Key stages in the pattern recognition process, including signal acquisition, signal pre-processing, feature extraction and learning, are systematically examined. Significant advancements in tasks including hand gesture recognition (HGR), hand sign language recognition (HSLR), human activity recognition (HAR), joint angle estimation (JAE), and force/torque estimation (FE/TE) are discussed, emphasizing the role of sEMG-IMU integration in achieving improved performance. The review further explores the practical applications of these technologies in areas such as rehabilitation, prosthetic control, and human–machine interaction (HMI). Finally, this review identifies the main challenges in sEMG-IMU sensor fusion and proposed potential future research directions, focusing on overcoming current limitations and advancing the development of more robust and accurate sensor fusion models.