SEMG-Based Complex Human In-Hand Motion Recognition for Dexterous Robotic Manipulation

• Published in: IEEE access Vol. 13; pp. 51042 - 51053
• Main Authors: Xue, Yaxu, Ru, Feifei, Du, Haojie, Yin, Kaiyang, Li, Pengfei, Ju, Zhaojie
• Format: Journal Article
• Language: English
• Published: Piscataway IEEE 2025; The Institute of Electrical and Electronics Engineers, Inc. (IEEE)
• Subjects: Accuracy; Algorithms; Bionics; Brain modeling; Classification algorithms; Complexity; Control methods; Data analysis; Decision trees; Electromyography; ensemble empirical mode decomposition; Feature extraction; gradient boosting decision tree; Hand (anatomy); Hands; human in-hand motion; Human motion; Machine learning; Motion perception; multivariate autoregressive; Noise; Prediction algorithms; Recognition; Robot sensing systems; SEMG; Signal processing; Signal processing algorithms; Signal quality
• ISSN: 2169-3536; 2169-3536
• DOI: 10.1109/ACCESS.2025.3550265

Surface electromyography (SEMG) signals have emerged as a natural and intuitive control method, offering significant advantages for the operation of bionic hands. This technology has been widely applied in various fields, including medical rehabilitation and human-computer interaction. This paper proposes an innovative human in-hand motion (HIM) recognition system that leverages SEMG signals to identify 10 self-defined in-hand operations.Firstly, acknowledging that conventional gestures and postures are insufficient to capture the complexity of human hand operations, we designed 10 HIM sets,including classical motions such as transfer, translation, and rotation. The original SEMG signals were collected using high-precision sensors.Subsequently, the collected SEMG signals were denoised using the ensemble empirical mode decomposition (EEMD) algorithm, effectively mitigating noise interference and enhancing signal quality. Feature extraction was then performed using the multivariate autoregressive (MVAR) method, which provides detailed nonlinear data analysis and captures the intricate temporal dynamics of the SEMG signals. Finally, the gradient boosting decision tree (GBDT) algorithm was employed to analyze the extracted features comprehensively. The results were discussed from three perspectives: the accuracy of human in-hand motion recognition, the inter-subject variability in motion recognition rates, and the comparative performance of different machine learning methods.The experimental results demonstrate that the proposed SEMG-based HIM recognition system achieves a high accuracy of 92.78% in identifying the 10 different HIMs. This study highlights the potential of integrating advanced signal processing and machine learning techniques to enhance the functionality and precision of bionic hand control systems.