Decomposing Task-Relevant Information From Surface Electromyogram for User-Generic Dexterous Finger Force Decoding

• Published in: IEEE journal of biomedical and health informatics Vol. 28; no. 7; pp. 3907 - 3917
• Main Authors: Fan, Jiahao, Hu, Xiaogang
• Format: Journal Article
• Language: English
• Published: United States IEEE 01.07.2024; The Institute of Electrical and Electronics Engineers, Inc. (IEEE)
• Subjects: Adult; Algorithms; Amplitudes; Decoding; Decomposition; Dextrous fingers; Electrodes; Electromyography; Electromyography - methods; End effectors; feature decomposition; Female; Finger; finger force prediction; Fingers; Fingers - physiology; Force; Humans; Indexes; Male; Myoelectric control; Myoelectricity; Neural coding; neural interface; Neural networks; Predictions; Principal components analysis; Representations; Robot control; Root-mean-square errors; Signal Processing, Computer-Assisted; Surface electromyogram; Task analysis; Young Adult
• ISSN: 2168-2194; 2168-2208; 2168-2208
• DOI: 10.1109/JBHI.2024.3383598

Existing electromyographic (EMG) based motor intent detection algorithms are typically user-specific, and a generic model that can quickly adapt to new users is highly desirable. However, establishing such a model remains a challenge due to high inter-person variability and external interference with EMG signals. In this study, we present a feature disentanglement approach, implemented by an autoencoder-like architecture, designed to decompose user-invariant, motor-task-sensitive high-level representations from user-sensitive, task-irrelevant representations in EMG amplitude features. Our method is user-generic and can be applied to unseen users for continuous multi-finger force predictions. We evaluated our approach on eight subjects, predicting the force of three fingers (index, middle, and ring-pinky) concurrently. We assessed the decoder's performance through a rigorous leave-one-subject-out validation. Our developed approach consistently outperformed both the conventional EMG amplitude method and a commonly used feature projection approach, principal component analysis (PCA), with a lower force prediction error (RMSE: 6.91 <inline-formula><tex-math notation="LaTeX">\pm</tex-math></inline-formula> 0.45 % MVC; <inline-formula><tex-math notation="LaTeX">R^{2}</tex-math></inline-formula>: 0.835 <inline-formula><tex-math notation="LaTeX">\pm</tex-math></inline-formula> 0.026) and a higher finger classification accuracy (83.0 <inline-formula><tex-math notation="LaTeX">\pm</tex-math></inline-formula> 4.5%). The comparison with the state-of-the-art neural networks further demonstrated the superior performance of our method in user-generic force predictions. Overall, our methods provide novel insights into the development of user-generic and accurate neural decoding for myoelectric control of assistive robotic hands.